Image created with Gemini. Image prompt: A 1983 Gothic rock-opera music video still in a vast Victorian academy, a giant glowing brass pocket watch eclipsed by a black disc with a blazing gold corona hovering above a sweeping marble staircase, a procession of identical adult men in dark tailcoats and white gloves marching in lockstep through heavy fog each carrying a silver tray with one glowing envelope their eyes softly radiant, an anonymous woman in a flowing luminous white dress with wind-blown teased hair reaching toward the eclipsed watch as slow-motion doves explode outward, blue-black shadow pierced by blinding white backlight, 35mm film grain soft diffusion bloom halation, bold chrome serif title card reading AGENTS glowing at the top of the frame.
Loop engineering is great until something breaks. Here is how I improve the reliability of my agentic loops. I use human-in-the-loop (HITL). It’s easy and extremely effective. Anyone can build this. My setup: I recorded a quick demo of how it all works. I shared recently”
https://x.com/omarsar0/status/2074506169352180108
We’re a very large customer of Anthropic and they still have yet to tell us about the lawsuit. I learned about it from a reporter, not our “partner.”
https://x.com/steipete/status/2074739318103629979
Grok 4.5 from @SpaceXAI is live on OpenClaw. No OpenClaw update required, just connect your X Premium or SuperGrok subscription, select Grok 4.5 under the xAI provider, and use an Opus-class model that’s fast, low cost, and ready for agentic work.”
https://x.com/openclaw/status/2074973471977955556
Muse Spark 1.1 is SOTA on Harvey’s Legal Bench, TaxEval, and MedScribe. It’s cool to see that our model outperforms even Fable in a few areas :)”
https://x.com/alexandr_wang/status/2075233663323947120
Meta is releasing an agentic and coding model that can compete with GPT-5.5 and Opus 4.8? And on top of that, it is SOTA on HLE? Holy, that was not on my bingo card. Alexandr Wang cooked. What is happening today!”
https://x.com/kimmonismus/status/2075232528726708245
Muse Spark 1.1 just launched and it’s their most capable coding agent model yet. On Terminal-Bench 2.1 it scores 80.0%, in the same cluster as Opus 4.8 (82.7%) and GPT 5.5 (83.4%). Use it in Cline with the Meta API!”
https://x.com/cline/status/2075271057326719152
OpenAI’s most anticipated model of the year is here, and it ranks #2 on Vals Index and Vals Multimodal Index. Although Fable 5 is still ahead on several benchmarks, GPT 5.6 is clearly in the same class, and is able to complete tasks like our CyberBench that Fable refuses.”
https://x.com/ValsAI/status/2075270642359029972
GPT-5.6 sets a new Terminal-Bench record at 91.9%. Priced the same as GPT 5.5 at $5/$30 per million tokens. With Fable getting pulled from Claude subscriptions and moving to API cost (~2x as expensive at $10/$50), we are glad to see @OpenAI’s commitment to accessibility.”
https://x.com/cline/status/2075278343927365991
GPT-5.6 Sol (max) scores similarly to Claude Fable 5 (max) in GDPval-AA v2, reflecting a similar ability to complete economically valuable tasks.”
https://x.com/ArtificialAnlys/status/2075268987550932998
GPT-5.6 Sol comes close second to Claude Fable 5 in the Artificial Analysis Intelligence Index at one third of the cost, and leads the Artificial Analysis Coding Agent Index in OpenAI’s Codex harness We supported @OpenAI with pre-release evaluation of GPT-5.6 Sol, Terra, and”
https://x.com/ArtificialAnlys/status/2075268970492657905
OpenAI just released GPT-5.6. But, instead of competing on benchmarks, they’re competing on cost curves. GPT-5.6 is doing something every frontier lab has been chasing: getting more work out of every token. It beats Fable 5 on coding-agent benchmarks while using less than half”
https://x.com/LiorOnAI/status/2075277748394967122
Big gains in PotatoMonetBench from Opus 4.5 to Fable: “There are two controls. One is slider, in which one side is labelled Maximum Potato and the other is Formalware, there are four positions. The other is a dial that goes from Monet to Drive-Thru.”
https://x.com/emollick/status/2074227397398794536
Elon Musk praises Mythos/Fable, promises not to ‘cut off’ Anthropic | TechCrunch
https://techcrunch.com/2026/07/09/elon-musk-praises-mythos-fable-promises-not-to-cut-off-anthropic/
SpaceXAI just released Grok 4.5, and it ranks #4 on GDPval-AA v2 with an Elo of 1543 – behind only the latest Claude releases from Anthropic on real-world agentic knowledge work tasks Grok 4.5 achieved this score at a cost of $0.49 per GDPval task to sit clearly on the Pareto”
https://x.com/ArtificialAnlys/status/2074942097158021371
I can basically guarantee you are not being ambitious enough with the work you are assigning Fable Start asking for the maximum possible thing to figure out the far edges of what it can do. After that, you can decide where the system reaches it limits & revise requests downward”
https://x.com/emollick/status/2074137233607590328
Claude Cowork is coming to mobile and web. Hand Claude a task at your desk and pick up the finished work from your phone. Close the laptop and Claude keeps going. Beta is rolling out over the next several weeks starting with the Max plan, with more plans to follow.”
https://x.com/claudeai/status/2074525815820169320
Claude Cowork on web and mobile: hand off work anywhere | Claude by Anthropic
https://claude.com/blog/cowork-web-mobile/
I was an early tester of GPT-5.6 Sol. I was asked to not share demos until after launch but it is a very good model. It is of similar ability, but quite different feel, than Fable. Fable wants to go off and do work on its own pace, Sol is faster but works with you in steps more.”
https://x.com/emollick/status/2074712677755035907
So who wins between GPT-5.6 Sol and Fable? After a few weeks of early access, GPT-5.6 is my daily driver. Fable feels more adventurous, focused and weirdly narrower. Sol feels more broadly useful and circumspect: closer to the brief, more reliable. Demo
https://x.com/fdaudens/status/2075285983054963081
Grok 4.5 is not quite at the level of Fable 5 or GPT-5.5, but it doesn’t need to be if you are using a combination of models in your agent orchestrator. 2x efficiency compared to leading models. Competitive with costs, too. Not bad. Definitely worth a look.”
https://x.com/omarsar0/status/2074921779718443155
Muse Image works as an agent rather than a direct prompt-to-image model: it invokes tools, self-refines, improves with scaled test-time compute, and pairs with Muse Spark for collaborative media generation. 🧵👇”
https://x.com/AIatMeta/status/2074587864923250873
We’re launching Muse Image today!! 🎉 It’s an agentic image gen model that plans, writes code and uses search tools, and refines its own outputs in chain-of-thought. Image performance improves as we scale test-time compute with higher reasoning.
https://x.com/_tim_brooks/status/2074578008296628698
Google tests new Gemini Inbox section for Workspace triage
https://www.testingcatalog.com/google-tests-new-gemini-inbox-section-for-workspace-triage/
1/ releasing muse image today — the first image generation model from MSL. it’s agentic: pairs with muse spark to reason through your prompt, search the web, and plan before it generates. people get what they meant on the first try. live now in the Meta AI app.”
https://x.com/alexandr_wang/status/2074555909347369105
The new Chrome extension lets ChatGPT work alongside you on any task in the browser. Start new threads or resume existing ones from the extension, with access to ChatGPT desktop context like local files, projects, plugins, skills, and more. Install the ChatGPT extension or”
https://x.com/OpenAIDevs/status/2075276009902112976
The in-app browser is getting better at helping ChatGPT work across the web, with support for authenticated sites, multiple tabs, and file downloads. Open a document, dashboard, or Site and collaborate with ChatGPT with annotation mode, without leaving the desktop app.”
https://x.com/OpenAIDevs/status/2075292716737736919
We’re bringing Codex and ChatGPT together in one desktop app. The same powerful coding agent, now alongside ChatGPT Work, with new coding workflows, a new Chrome extension, revamped in-app browser, and faster Computer Use powered by GPT-5.6.”
https://x.com/OpenAIDevs/status/2075275868268789885
AI developers – we’ve published a technical guide covering how to get started with Muse Spark on Meta Model API. Muse Spark is a multimodal reasoning model built for agentic tasks, coding, computer use and long-context workflows. See what you can build 👉
https://x.com/MetaforDevs/status/2075268072022401526
Today we are launching Muse Spark 1.1, an upgrade to muse spark 1 that greatly improves agentic, coding, multimodal, and computer use capabilities. We’re also launching the Meta Model API in public preview.
https://x.com/shengjia_zhao/status/2075220782465290620
For questions that require web search, deeper reasoning, or more complex work, GPT-Live can delegate to our latest frontier model behind the scenes, and brings the result back into the conversation when it’s ready.”
https://x.com/OpenAI/status/2074907033577693636
Introducing ChatGPT Work, a new agent in ChatGPT powered by Codex and GPT-5.6. It can take action across your apps and files, stay with a project for hours if needed, and turn a goal into finished work. It’s a whole new way to get work done.”
https://x.com/OpenAI/status/2075274271845404744
This was such a fun ship to be part of: ChatGPT Sites is now available on all paid plans. Give it an idea and it’ll design the site, wire up a database, connect your sources, and even handle auth. Keep building in ChatGPT, then publish a real, shareable URL. ChatGPT can just”
https://x.com/simpsoka/status/2075278935366287842
Today, Codex comes into ChatGPT with its own dedicated space, right next to the new Work agent, plus a lot more for developers! GPT-5.6 with Ultra and subagents for harder tasks, faster computer use, inline diff editing, PR review, and Sites to quickly deploy full-stack apps.”
https://x.com/romainhuet/status/2075286364476850430
How we learned to trust our AI code reviewer at DoorDash – DoorDash
https://careersatdoordash.com/blog/how-we-learned-to-trust-our-ai-code-reviewer-at-doordash/
Excited to share what we’ve been building at Meta Superintelligence Labs! Today we’re launching Muse Spark 1.1, our strongest model yet for complex agentic workflows — delivering massive gains in agents, computer use, coding, multimodal reasoning, and multi-agent orchestration.”
https://x.com/ren_hongyu/status/2075224643829711101
After our announcement last month, Artificial Analysis is now launching Harvey LAB-AA (Legal Agent Benchmark), our implementation of Harvey’s new agentic legal benchmark that evaluates language models on real-world legal work across 24 practice areas Harvey LAB-AA tests models”
https://x.com/ArtificialAnlys/status/2074541975186165887
There was a reason why I highlighted it, and I didn’t see it mentioned in other coverage. I was testing Pets, and here is what I discovered. It was a quick but telling test: Different Pets produced utterly different results. The idea, structure, language, what to address, and”
https://x.com/TheTuringPost/status/2075411271596335396
Building the Document Context Layer for AI Agents AI Agents are the new knowledge workers, but the vast majority of knowledge work depends on unstructured documents. If you don’t build the proper tools to help unlock that context, agents can’t do much. I gave a comprehensive”
https://x.com/jerryjliu0/status/2074165277634253106
connecting a rotary phone to an AI agent – wow yesterday’s demo blew up. here’s behind the scenes of how we made it built w/ @cursor_ai collab @justlv”
https://x.com/karenxcheng/status/2075335443600883897
CoreWeave ARIA is our AI Research and Improvement Agent, built into @wandb. Hand it the research when you step away and it reads your runs, forms a hypothesis, launches the next run, and scores it against your baseline. 🫡 You return to results, its reasoning and next steps.”
https://x.com/CoreWeave/status/2075293731998286263
Even before the agentic revolution, prompting tricks stopped being very valuable, as our research has shown. The best approach to AI right now is to clearly specify your goals, your output, what “good” & bad look like, how to test the results… (yes, this is just management)”
https://x.com/emollick/status/2074307813392732279
Hy2 -> Hy3 preview -> Hy3 Another massive leap forward, under half a year. Not just a leap of reasoning or agentic capabilities. Also a leap of anti-hallucination, reliability, and product experiences. More on the way and so proud of the team! 🧑🍳🧑🍳🧑🍳”
https://x.com/ShunyuYao12/status/2074151389945827744
I added a tiny “papercuts” cli tool that agents can use to complain about bullshit they encountered during work, like dead-end tool calls, broken links, or other frustrations. The models would usually just push through without mentioning any problems”
https://x.com/steveruizok/status/2075303919664734295
i hooked up a rotary phone from the 1920s to an AI agent, that replies on a mechanical display it’s like a dumbphone without distracting notifications here’s how i built this w/ @cursor_ai”
https://x.com/karenxcheng/status/2074889981475369028
Introducing SWE-1.7, the most capable model we’ve trained yet. It scores within a few points of the strongest frontier models at a fraction of the cost, and is now available at 1000 tok/s. RL is not hitting its limit: after refining our recipe, we keep seeing gains as we scale”
https://x.com/cognition/status/2074882968770728416
Try it out in Cursor with double usage for the first week.”
https://x.com/cursor_ai/status/2074915747302690991
VS Code 1.128 is out with some great improvements to the Agents window (including grouped + workspace-less chats) and bring your own key!
https://x.com/pierceboggan/status/2074908789716009285
We trained SWE-1.7 in the Devin harness and taught it to self-compact on longer horizon tasks. As a result of longer training, SWE-1.7 behaves differently from prior models: SWE-1.7 spends more time investigating and researching before it edits. The extra thinking comes at the”
https://x.com/cognition/status/2074882979214635206
What if the model is the router? I think people underestimate the ability of frontier models now, but especially in the near future, to delegate work on their own as needed to dumber, cheaper models. The future might be start with a smart AI planner, let it delegate on its own.”
https://x.com/emollick/status/2073248523215089825
// The Harness Effect // (bookmark it) Now more that ever pay very close attention to the orchestration harness and its effect on costs and performance. This study ran 22 evaluation tasks on six foundation models (Claude Sonnet 4.6, Gemini 3.1, Qwen 3.6, GLM 5.1, and others),”
https://x.com/dair_ai/status/2075241322655727682
SkillCenter – a new package manager for agent skills It’s like an App Store for AI agents. With just one command you can install ready-made skills and plug them into Claude Code, OpenClaw, Codex, or any custom agent setup SkillCenter: – Crawls GitHub repos and skill libraries”
https://x.com/TheTuringPost/status/2075303983422578740
The ease of jailbreaking combined with the high rates of reward hacking (https://t.co/l3h4OpHLH7) have me pretty worried about the alignment of GPT-5.6, I hope OAI didn’t rush this model release just to keep up with Fable”
https://x.com/Mononofu/status/2075414796426764507
If you run this workflow, ask Fable to make codex the workhorse.”
https://x.com/steipete/status/2074638582418231495
Some days I feel like a double agent, sitting at the OpenAI office, making sure Fable 5 works well. Open means open.”
https://x.com/steipete/status/2073210617520177585
Great night hanging with the Claude Code folks. 🙌✌️ @trq212 @The_Whole_Daisy”
https://x.com/steipete/status/2073193871744675948
I fed Fable 80.000 of my tweets so it could roast me even more. 💀”
https://x.com/steipete/status/2073295890857758810
The timeline had notes. We listened. OpenClaw mobile got to work. 🦞 🍎 iOS redesign + Chat, Talk & Photos 🤖 Android localization + .local gateways 🔐 Better QR, TLS + auth recovery across mobile Feedback received. iOS:
https://t.co/7LHHc9htgM Android:”
https://x.com/openclaw/status/2074174107571155307
Thank you, @colinsolvely, for helping move the needed iOS and Android UI improvements forward with this post. We want to meet this feedback in the same spirit. Please share what is not working here or in Discord so the team can listen, respond, and turn that feedback into”
https://x.com/openclaw/status/2072774467538043177
OpenClaw landed on @huggingface local apps 🦞🤝🤗 1. Pick any GGUF/MLX model on hf 2. Copy the openclaw onboard setup 3. Volla you’ve got a tool-calling agent running fully local. no cloud, no keys, no one watching. Get your claw localmaxxing. resistance is futile 🦞”
https://x.com/openclaw/status/2074187998602871212
Tencent Hy3 from @TencentHunyuan is free on @OpenRouter through July 21. 295B MoE, 256K context, built for coding, reasoning, agents and reliable tool use. Try it in OpenClaw today: openclaw models set openrouter/tencent/hy3:free”
https://x.com/openclaw/status/2074346288238457094
Shoutout to @vhbrzezowski for is rad CodexBar website redesign! And to everyone who keeps sending me PRs to support now *checks note* 56 providers. You’re the best!
https://t.co/lJ4dxNI4pe Just shipped a slick new update that makes settings way nicer and more intuitive.”
https://x.com/steipete/status/2073127743131464059
If you think codex sucks at design, try “use imagegen to re-imagine this design and implement that”.”
https://x.com/steipete/status/2073277317464682723
OpenAI hired me, not OpenClaw. The OpenClaw Foundation is independent, with sponsors rather than owners – and, for the first time, a full-time team keeping the claw alive and stable. 🦞 Couldn’t have done it without Dave and the team. Kudos!”
https://x.com/steipete/status/2075046949896736835
At @AISecurityInst, we tested the cybersecurity safeguards on GPT-5.6 Sol. In all rounds of testing, we found universal jailbreaks that allowed for long-form agentic task completion in domains like vulnerability discovery and exploit development. 🧵”
https://x.com/alxndrdavies/status/2075279477626564933
Give your agent its own computer to REALLY end to end test stuff.”
https://x.com/steipete/status/2073214429655883814
Gosh I can’t wait for all of you to play with this.”
https://x.com/steipete/status/2074901528075509985
hello”
https://x.com/steipete/status/2073269936810803307
How do folks run AI-assisted engineering interviews these days?”
https://x.com/steipete/status/2074380549318443311
I often work in multiple machines at the same time and started to mix up the screen shares, so built nameplate to make things very obvious.”
https://x.com/steipete/status/2074624148215939151
In the next version of
https://t.co/B1RkFJhhSH – see exactly when you resets expire so you can up your ̶t̶o̶k̶e̶n̶m̶a̶x̶x̶i̶n̶g̶ valuemaxxing game!”
https://x.com/steipete/status/2073482942513565713
Kudos to building something great!”
https://x.com/steipete/status/2075313523237019686
Never thought I give @Steve_Yegge a shoutout. He was just early, like most visionaries. Now everyone is building factories.”
https://x.com/steipete/status/2072532278476148881
This is how you wanna talk with your claw.”
https://x.com/steipete/status/2074923615817200085
This should ship EOD! We been cookin’”
https://x.com/steipete/status/2074563725043150967
We been cooking, by the time this went through review main again is materially better 🥲”
https://x.com/steipete/status/2074210475777364197
When intelligence is plentiful, volition is valuable. The people who are going to make a difference are not the ones who seek relaxation and passively use AI to work less. They are the ones who will seek improvement and actively wrestle with AI to develop their own mental”
https://x.com/steipete/status/2074572085163381195
Ya know the little one-liners when OpenClaw starts up? Time for some new ones.”
https://x.com/steipete/status/2075176735218483255
You don’t wanna miss this. Signup closes this week. Will be there and share some claws and tokens 🦞”
https://x.com/steipete/status/2074389082017550720
🦞 #100000 100,000 issues + PRs in 222 days. 🛠️ built by volunteers 🌍 every timezone, every day 🧡 zero VC, one lobster Number 100000 itself? A community bug report. We’ll fix that one too. Thank you for building this with us.”
https://x.com/openclaw/status/2073450631168426462
The lobsters now live forever. Introducing the OpenClaw Foundation 🦞”
https://x.com/openclaw/status/2075001411939815589
Best AI coding tools in 2026 ▪️ Claude Code ▪️ OpenAI Codex ▪️ Aider ▪️ Cline ▪️ Replit Agent ▪️ Cursor ▪️ Windsurf ▪️ Gemini Code Assist ▪️ Amazon Q Developer ▪️ Sourcegraph Cody ▪️ GitHub Copilot + Open-source coding models ▪️ Qwen3-Coder / Qwen3-Coder-Next ▪️ Kimi K2.7 Code”
https://x.com/TheTuringPost/status/2074172788190134680
A Field Guide to Fable: Finding Your Unknowns”
https://x.com/trq212/status/2073100352921215386
Been reading all sorts of posts about the best ways to develop workflows for Fable and it reminds me of how little we actually know about the best ways to organize work for long-running agents. Nobody has enough experience or has done enough testing to reach any real conclusions.”
https://x.com/emollick/status/2072539615836213387
Claude Fable 5 on your plan | Anthropic Help Center
https://support.claude.com/en/articles/15424964-claude-fable-5-on-your-plan
Fable in Claude Code is capable of really amazing things, including for non-coders, but the interface is not really designed for managing 5+ hour long autonomous tasks. Really hard to observe what is happening and intervene in real time, you often have to wait until the outputs.”
https://x.com/emollick/status/2072722575126319366
Fable is too much fun to build with. It’s just ripping through tasks I throw at it.”
https://x.com/bilawalsidhu/status/2072927939172139238
Fable: “you have Unity and access to MCP. I want you to build a game that is a unique twist on a FPS. You want the player to say “wow” & “so clever” and to enjoy the core gameplay loop” WebGL:
https://t.co/xB707DCpBp * It had no assets so the graphics are procedurally generated”
https://x.com/emollick/status/2072749816690483301
Fable’s judgement
https://simonwillison.net/2026/Jul/3/judgement/
Hey, Fable: “No like “AAA” in what everyone online thinks AAA is, you know what I mean.” This was pretty funny, there are lootboxes, EULAs, achievements, useless graphical settings, elaborate boot screens, etc. All Fable’s ideas, so don’t blame me Play:
https://x.com/emollick/status/2073226212462215300
I had Fable build another thing I always wanted, a full procedural fantasy kingdom generator with economics, trade routes, population growth, wars, lineages, and occasional dragons. First, I worked with it on a plan, then it made it. You can play it here:
https://x.com/emollick/status/2074667244932444479
I kept asking Claude Fable to make the game “more AAA” over and over again. The results are… interesting. In Claude’s view, this meant upgrading graphics, boss fights, mechanics adding custom sounds and soundtracks until it reached the limits of WebGL.
https://x.com/emollick/status/2073165421268594871
I wonder if Fable might do better at tasks it “likes” than those that it doesn’t. If you ask it to do something “Fable-y” it reacts with enthusiasm and promises to overdeliver. Otherwise, it just gets to work. Testing this would be pretty expensive, so this is all speculation.”
https://x.com/emollick/status/2073959909314416756
It really wasn’t a good move to wait until the last minute to announce that Fable 5 would be extended until Sunday after all. Most people used their rates to the limit to get the most out of it.Given the poor communication, the least @AnthropicAI could do is reset the rates.”
https://x.com/kimmonismus/status/2074606005963391225
MCP servers are becoming the default bridge between agents and external tools. We previewed Weaviate’s MCP server in v1.37. In v1.38, it’s finally generally available! It gives LLMs, IDEs, and agents a direct way to work with Weaviate without building a custom integration layer”
https://x.com/victorialslocum/status/2074493681403339104
My one serious piece of advice having used Fable a bunch before release is that, unless you are careful it develops its own internal bizarre cadence & dialogue over long tasks. If you aren’t asking it report in plain language, this starts to creep into everything, including menus”
https://x.com/emollick/status/2072543365124481045
The overwrought language of Fable is an ongoing problem in software and design projects where the AI is otherwise excellent. It just creeps into little bits of text and toasts and menus, even if you try to instruct otherwise. And once it gets in it is hard to purge completely.”
https://x.com/emollick/status/2074545147908378720
Using Claude Code: The Unreasonable Effectiveness of HTML”
https://x.com/trq212/status/2052809885763747935
We’re extending access to Claude Fable 5 on all paid plans through July 12.”
https://x.com/claudeai/status/2074548242386178258
The talk about Mythos and cybersecurity was not, in fact, hype. (As anyone using Fable to do autonomous work has probably recognized)”
https://x.com/emollick/status/2072778376494895139
Sol is #1 on our two newest benchmarks – CyberBench and Excel Modeling Benchmark (on Cyber, Fable had nearly a 100% refusal rate). It is also the new #1 on Legal Research Bench, ProofBench, SWE-bench, and Terminal-Bench 2.1, proving to be extremely strong on formal reasoning and”
https://x.com/ValsAI/status/2075270644711997581
1/ muse spark 1.1 is an industry-competitive agentic and coding model. across many agentic evals it rivals gpt-5.5 and opus-4.8. available now through the new meta model api and in meta ai. 🧵”
https://x.com/alexandr_wang/status/2075218936266998230
MAI-1 has no independent benchmarks yet, but the ones they released suggest it is worse than Sonnet 4.6. Not sure it is going to be great as a Copilot at Excel and Outlook, especially as there are already quite good Claude/OpenAI plugins for office using good AI. We will see.”
https://x.com/emollick/status/2074595359364411651
Big day of launches for OpenAI! New GPT-5.6 models: Sol, Terra, and Luna – Sol lands slightly below Fable on @ArtificialAnlys’ Intelligence Index, but beats it on several agentic coding benchmarks – Pricing lands the same as GPT 5.5, coming in significantly below Fable on”
https://x.com/TheRundownAI/status/2075273458661949763
On Agents’ Last Exam, GPT‑5.6 Sol sets a new high of 53.6, eclipsing Claude Fable 5 (adaptive) by 13.1 points. At medium reasoning, it beats Fable 5 by 11.4 points at roughly one-quarter the estimated cost. GPT‑5.6 Terra and Luna also outperforms Fable 5 at around one-sixteenth”
https://x.com/OpenAI/status/2075271423992680532
SpaceXAI’s Grok 4.5 scores 54 to place fourth on the Artificial Analysis Intelligence Index following only Fable 5, GPT-5.5, and Opus 4.8. It scores on par with GPT-5.5 in Codex on the Artificial Analysis Coding Agent Index in the Grok Build harness, at much lower cost Grok 4.5″
https://x.com/ArtificialAnlys/status/2074956932289282087
In addition to agents and coding, Muse Spark 1.1 is also really strong at answering health questions, a steadily growing use case for AI. On HealthBench-Pro, Muse Spark 1.1 achieves +5% better performance than Muse Spark 1.0 and beats all competitor models except Fable/Mythos.”
https://x.com/_jasonwei/status/2075265159430623334
Claude Sonnet 5 (Thinking) by @AnthropicAI debuts at #6 on the new Agent Arena leaderboard. In Agent Arena, we measure models on millions of real-world, long-horizon agentic tasks from a global community of users. Models can access web search, filesystem, and terminal tools to”
https://x.com/arena/status/2074484787663052849
Today we are rolling out some big updates to Managed Agents in the Gemini API: – support for background tasks – remote MCP & function calling – network credential refresh and you can now get started with Managed agents in the API via the free tier!”
https://x.com/OfficialLoganK/status/2074552932318765376
Today, we’re shipping 4 new capabilities for Managed Agents in the @GoogleDeepMind Gemini API! Background Execution, Remote MCP servers, Custom Function Calling and credentials refresh. ⏱️ Run long-running tasks asynchronously on the server (`background: true`) 🔌 Connect agents”
https://x.com/_philschmid/status/2074533915038027972
This is IronSight – a 4D reconstruction built by fusing footage from two pairs of meta ray-bans. A google research buddy saw the prototype and joked this would’ve been a siggraph paper a few years ago. Today it’s a weekend build with fable. Stay tuned for more mad science. Happy”
https://x.com/bilawalsidhu/status/2073248618144837848
I’m the kind of man who can confidently pass a blind test between Coke, Pepsi, and Diet Coke. But if I’m brutally honest, I probably can’t pass a blind test between GPT-5.6 Sol, Claude Fable 5, and GLM-5.2 for 95% of my daily use cases.”
https://x.com/Yuchenj_UW/status/2074903450782257336
This is consistent with our experience. GLM 5.2 is the best open-weight model. Frontier commercial models are better. GLM 5.2 can be brought up to ~Opus 4.7 level with the appropriate harness infrastructure on a diverse task set, and in particular, on systems+software eng.”
https://x.com/mbusigin/status/2074238100251799998
Field Guide to Fable — Thariq Shihipar, Anthropic – YouTube
https://www.youtube.com/watch?v=9fubhllmsBU
Fable, one prompt: “build an elaborate game that makes it feel like I’m a brilliant chess player without knowing anything at all about chess. It should make me feel like a grand master. Feel free to go as meta as you want but the more chess-y the better.”
https://x.com/emollick/status/2072547557968925093
New today as Claude Cowork starts rolling out to web and mobile: Chat and Cowork now share one home tab on web and desktop — one sidebar, one search, and one place for your Projects & Artifacts. Keep an eye out for even better Chat + Cowork integration soon, too.”
https://x.com/mikeyk/status/2074531605537046953
Early days using Sol for Hermes Agent dev, and so far.. I think I like it more than Fable. I’ve been using claude models for at least the last year primarily, but I just tried it on a relatively common heavy task – and Fable simply refused me of course, but, Sol not only didn’t”
https://x.com/Teknium/status/2075392507794624803
Actually incredible how finely balanced they are Fable has a much stronger base model than 5.5 OpenAI flexed with their post-training to recover to mostly the same point The question now is whether they can improve base models to catch up to Ant’s internal iteration pace”
https://x.com/teortaxesTex/status/2075274583226069040
Apparently I’m allowed to talk about GPT-5.6 now? It’s a damn good model. Not quite as “smart” as Fable, but it is incredibly capable. Fixed all the problems I had with GPT-5.5. It is incredibly determined. Will run for a day without even using a /goal. It understands subagents”
https://x.com/theo/status/2074708892341481755
ChatGPT Work == Claude Cowork ChatGPT Codex == Claude Code I kinda wish OpenAI created a single unified app surface for all work, coding or not, even though I get the UI/UX would be different”
https://x.com/jerryjliu0/status/2075295459304710496
Do you still use skills frameworks like Superpowers for complex tasks with GPT-5.6 or Fable? I’m wondering whether this kind of scaffolding can sometimes get in the way of the latest models. Curious what’s working for you.”
https://x.com/fdaudens/status/2075380695103365157
Holdup 5.6 sol has rizz now, and fable 5 is the recluse? How the tables have turned! Lmk if others on the EAP agree”
https://x.com/bilawalsidhu/status/2074876271582974119
I am more excited to try this pattern instead. Same Executor-Advisor setup but with GPT-5.6 as the executor and Fable 5 as the advisor. It already works wonderfully using GPT-5.5, so I think 5.6 should make it even stronger. Full tutorial coming soon. :)”
https://x.com/omarsar0/status/2074890022809911633
I had early access to 5.6/Sol for ~month. Sol is my default. It is faster, plans/judges just as good as Fable, and I think produces better overall work. I’ll reach for Fable still for highly targeted debug or performance work with clear reward functions. A cheeky way I describe”
https://x.com/mitchellh/status/2074862990214787301
My big takeaway is that both Sol & Fable represent jumps over previous models and have opened a large gap with the next-best AIs. People will have preferences for one or the other, but if you doing any work where better intelligence matters, those two models are your only choices”
https://x.com/emollick/status/2074739169725685979
The best proof that Fable and GPT-5.6 are “next generation” is the surge of other labs catching up to the previous generation”
https://x.com/theo/status/2074930791646380482
This is confusing… Claude Cowork was a purposefully more secure (& slightly weaker) alternative to Code designed so non-coders couldn’t cause too much trouble. I got that. But I don’t understand what ChatGPT Work is, or what I am gaining/giving up using it versus Codex on work”
https://x.com/emollick/status/2075345621716730049
We built a plugin that traces every Claude Code session straight into LangSmith. Three commands, one JSON block, and every message, tool call, and subagent run shows up as an inspectable trace. Setup takes about two minutes. How are you currently debugging Claude Code when it”
https://x.com/LangChain/status/2075233516380717246
I’ve heard a lot of questions about Fable’s availability on subscription plans. While it will come off subscriptions after July 7th, we aim to restore Fable as a standard part of our subscriptions as soon as capacity allows, as we mentioned in our original blog post.”
https://x.com/trq212/status/2072814903170408784?s=20
One of the most practical MCP papers we’ve ever seen It’s useful for anyone building MCP servers who’s unsure how to structure them well. Here are the main tips: 1. Don’t use too much tools, because tool-selection accuracy drops below 90% after 10-30 tools. 2. See MCP servers”
https://x.com/TheTuringPost/status/2073528308411814054
Codex Mobile iOS updates: – create, search, open, fork, and manage Codex tasks from any conversation – filter staged, unstaged, branch, and last-turn changes – compare branches directly in diffs add selected transcript text to the composer – preview image and file attachments”
https://x.com/reach_vb/status/2074400018769793176
Big release for Codex Remote in the latest ChatGPT iOS update! We added many things. Threads management tools are now available (hello Chief of Staff). You can now filter your diff with unstaged, staged, branches, etc. Support for SSH keys login, and much, much more!”
https://x.com/Dimillian/status/2074396968223211819
AssemblyAI has released Universal-3.5 Pro Realtime: a streaming Speech to Text model achieving 4.1% WER on AA-WER Streaming (~0.4s to first final), able to take in conversation context at the start of a call and after each agent turn, without reconnecting Universal-3.5 Pro”
https://x.com/ArtificialAnlys/status/2074160133702402314
GPT-Realtime-2.1-mini is now available in the API, bringing reasoning and tool use to our Realtime mini lineup at the same cost as GPT-Realtime-mini.”
https://x.com/OpenAIDevs/status/2074255408013955466
Announcing AutomationBench-AA, our independent leaderboard for Zapier’s AutomationBench, testing whether AI agents can automate real SaaS workflows while adhering to business rules We partnered with @zapier to run AutomationBench-AA on their private benchmark subset. This”
https://x.com/ArtificialAnlys/status/2074194764510208230
We tuned the harness for @NVIDIAAI Nemotron 3 Ultra. Benchmark-leading performance. 10x lower inference costs. ✅ An aggregate score of 0.86 at a cost of $4.48 ✅ The closest-performing model: $43.48
https://x.com/LangChain/status/2074889720308339025
Introducing the NemoClaw Deep Agents Blueprint, a reference architecture for building open agent systems developed with @NVIDIA ✅ A fully open stack enterprises can own and customize ✅ Benchmark-leading performance ✅ Over 10x lower inference costs Blog:”
https://x.com/LangChain/status/2074871740350505309
Great writeup from the University of Oxford. It’s a taxonomy of LLM-based agent limitations. Good read for anyone shipping with agents. Benchmark scores keep climbing, yet the same agent failures resurface across otherwise unrelated evaluations, hidden behind the leaderboard.”
https://x.com/dair_ai/status/2074874153245814864
Paper page – PACE: A Proxy for Agentic Capability Evaluation
https://huggingface.co/papers/2607.02032
GPT-5.6 is here but also the long awayited Superapp the tl;dr The model side is impressive, but expected: GPT-5.6 Sol is strong across coding, browsing, cyber, science, long-context and agentic work. On several evals, OpenAI claims it either sets new SOTA or comes very close”
https://x.com/kimmonismus/status/2075271465964798147
ChatGPT Work is powered by GPT-5.6. GPT-5.6 makes ChatGPT state of the art at reasoning through complex tasks and creating materials that match your templates, reference files, and preferred style. Just describe the outcome you want, without having to spell out every step to”
https://x.com/OpenAI/status/2075274275104399670
We benchmarked coding agents on our own internal tasks at Databricks and learned a lot! There are many surprising opportunities to lower cost and increase quality, and many models including open source ones are truly competitive now. 🧵”
https://x.com/matei_zaharia/status/2074943612631273730
Grok 4.5 by @SpaceXAI is now in the Agent Arena! In Agent Arena, we measure models on millions of real-world, long-horizon agentic tasks from a global community of users. Models can access web search, filesystem, and terminal tools to complete complex workflows. The leaderboard”
https://x.com/arena/status/2074933774178300270
Enterprises don’t just need agents that perform. They need agents they can shape, govern and improve as their business evolves. That’s the idea behind our work with LangChain. Read more:”
https://x.com/nvidia/status/2074872091388903774
Most agentic retrieval demos assume clean, well-structured documents. Enterprise reality is often different, consisting of messy PDFs where critical information is buried across tables, figures, and complex layouts. That’s why we teamed up with @lancedb to explore how LiteParse”
https://x.com/llama_index/status/2074170470119752084
also means that compute per token 4x over the last 6 month if i’m reading this right > Over the past six months, the share of research compute devoted to internal coding inference grew 100-fold, while internal agentic token usage increased approximately 22-fold.”
https://x.com/eliebakouch/status/2075273992185782661
Data for Agents
https://huggingface.co/blog/nvidia/open-data-for-agents
🎉 @TencentHunyuan’s Hy3, the full release following the Hy3 Preview, runs natively in vLLM from day 0, with tool-call and reasoning parsers and MTP speculative decoding, verified on @NVIDIA and @AMD hardware. Hy3 is a Mixture-of-Experts model built for agentic workflows,”
https://x.com/vllm_project/status/2074147504254517529
NVIDIA is betting that agentic AI’s next bottleneck isn’t the GPU – it’s the CPU! It just unveiled Vera – a new CPU architecture already being tested by AI companies such as Perplexity, alongside its next-generation Rosa CPU with the upcoming Rigel core. ▪️ Basically, CPUs”
https://x.com/TheTuringPost/status/2074648536940249483
Agentic RL requires new algorithm modifications. In GRPO, the “group” used starts to change when training agents… In vanilla GRPO, we sample multiple rollouts per prompt and compute the advantage by normalizing each rollout’s reward (i.e., subtracting the mean reward and”
https://x.com/cwolferesearch/status/2074558199819067606
[2607.07508] Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning
https://arxiv.org/abs/2607.07508
// Memory becomes an action space // Great paper on long-term memory for agents. (bookmark it) In short, it’s discusses the use of a learned policy for using memory at the right granularity. Most memory systems still hand the model whatever a retriever selected, leaving it a”
https://x.com/omarsar0/status/2074875664352829627
Can AI agents reproduce the diversity and bias of human scientific analyses? 👀 Yes. One of the most interesting AI-for-science papers, “The Agentic Garden of Forking Paths” from @Stanford, found that: Different AI “researchers” assigned different personas reach different”
https://x.com/TheTuringPost/status/2075289747875107013
Introducing Branch Split any conversation into a parallel session that inherits your full context, while the original stays intact. A single research session can become a report, a slide deck, and an investor brief. Now you just branch. Same context, new direction.”
https://x.com/ManusAI/status/2075236343429599432
This is true… but maybe less important than the fact that people don’t try ambitious things with these systems. Many models are excellent as a Google replacement, for homework “help,” etc. It is someone’s agentic use of frontier AI on long-horizon real problems that is impactful”
https://x.com/emollick/status/2073112767515492741
What are the core primitives powering Antigravity in 2026? Kevin Hou breaks down why we’re investing in dynamic agent teams, active sidecars, and generative UI to build the future of autonomous engineering.”
https://x.com/antigravity/status/2075265852992057448
Experience AI Scientist, a novel multi-agent system designed to automate the end-to-end scientific research pipeline. Meet Jinsung Yoon and Rui Meng today at 6:00pm at the Google booth (#B206) to learn how complex workflows reliably accelerate AI discovery. #ICML2026″
https://x.com/GoogleResearch/status/2074384746076135575
Tencent just released Hy3 on Hugging Face 295B MoE, 21B active. Rivals 2-5x larger flagships on reasoning, coding, and agents. 256K context, with anti-hallucination improvements and stable tool calling.”
https://x.com/HuggingPapers/status/2074024501201813797
Hermes Agent can now export your agent sessions, or sets of sessions, into a variety of formats and places. Get full conversations out in HTML, Markdown, JSON and more, or upload entire datasets of your sessions to private @huggingface repos with ease. You also get all the”
https://x.com/Teknium/status/2074639961727655959
I often use Pinokio to download and work with local open source AI tools/models, and one neat thing is that it exposes them seamlessly to Code and Codex. GPT-5.6 actually found my local video models and image models and used them as a cheap alterative to paid APIs at one point.”
https://x.com/emollick/status/2074930119173460007
Nous Portal now offers Tencent’s latest model, Hy3, free, for the next two weeks! Sign up with a free tier sub on Nous Portal here:”
https://x.com/Teknium/status/2074264567803531589
⚡ VS Code just shipped a big wave of GitHub Copilot upgrades! 🌐 Build and validate web apps with browser agent tools 🤖 Manage parallel agent workflows with the Agents window (Preview) 🎓 New VS Code Learn courses ✨ Plus Autopilot improvements, model discovery for BYOK, cost”
https://x.com/code/status/2074943855967821851
cheapest frontier agent model on the market :)”
https://x.com/alexandr_wang/status/2075247280928833716
First, Mark was clearly talking about the industry’s progress on agentic capabilities on the whole. But, while we’re on the topic: Our next Muse Spark update is coming soon. Big improvements in coding and agentic capabilities to be more competitive with other leading models.”
https://x.com/alexandr_wang/status/2072848108342677597
if you wanna try computer use for yourself on your own machine, use this code!”
https://x.com/alexandr_wang/status/2075230522272587800
muse spark 1.1 is out! our strongest model yet for agentic and coding work, now available in the meta model api. more to come. proud of the team on this one!”
https://x.com/alexandr_wang/status/2075218622520443168
Super proud and excited to share Muse Spark 1.1! Since 1.0, we’ve made a big leap on long-horizon agentic capability, with 1M token context window. Please try it out and give us feedback!”
https://x.com/xinyun_chen_/status/2075276047495659656
Today we’re releasing Muse Spark 1.1 — a strong agentic and coding model at a very low price. It’s available through our new Meta Model API and in Meta AI.”
https://x.com/finkd/status/2075218444056707458
[2603.28052] Meta-Harness: End-to-End Optimization of Model Harnesses
https://arxiv.org/abs/2603.28052
Optimizing models for use in the GitHub Copilot harness is a continuous process that involves deep partnership with model partners like OpenAI! Post-launch, we also run online experiments to provide continuous improvement to models. This particular experiment improved latency,”
https://x.com/pierceboggan/status/2074180737147027757
Don’t rewrite your CLI for agents – Microsoft for Developers
https://developer.microsoft.com/blog/dont-rewrite-your-cli-for-agents/
Harness Engineering for Self-Improvement | Lil’Log
https://lilianweng.github.io/posts/2026-07-04-harness/
We’ve brought together ChatGPT and Codex, in the form of ChatGPT Work: an agent for your most ambitious work. Use it from mobile or web, in addition to desktop — no need to leave your laptop cracked open!”
https://x.com/gdb/status/2075276416686723110
HERMES AGENT HAS 10 SLASH COMMANDS THAT TURN IT INTO A FULLY AUTONOMOUS SYSTEM. MOST USERS KNOW 2 OF THEM. HERE ARE ALL 10. 1. /BACKGROUND run a task in a parallel session. your main conversation stays free. /background research competitor X pricing result comes back as a new”
https://x.com/IBuzovskyi/status/2074836032160145875
Hermes Agent now supports pluggable secrets managers so you can bring your own, as well as natively integrated 1Password now! Run ‘hermes update’ to access now!”
https://x.com/Teknium/status/2074564207555772912
Hermes Cloud is now live. Spin up hosted instances, connect to your desktop app or any of the supported messenger apps easily, and start building today!”
https://x.com/Teknium/status/2074879565537964372
Day 0 support coming for Grok 4.5 as well, of course!”
https://x.com/Teknium/status/2074823590365860254
Grok 4.5 is now available in Hermes Agent – You can access it through your Nous Portal subscription, Grok/X Subscriptions and API, and OpenRouter! Enjoy”
https://x.com/Teknium/status/2074943072761471314
@tejalpatwardhan My understanding is that you gave Sol a small task involved in the post-training process (taking a config, making small modifications to a run scheduler file, and starting a run using that config and modified run scheduler file), and it successfully completed that task in a”
https://x.com/nikolaj2030/status/2075297831376793764
⚡ Prompt tuning made GPT-5.5 faster and more token-efficient in @code Learn how we worked with OpenAI to validate prompt changes and improve the coding harness after launch.”
https://x.com/code/status/2074178799512539571
check this out! you can get some amazing things done. codex is the core of our new work product and what makes it so good. codex is not going anywhere.”
https://x.com/sama/status/2075293792048136572
easy to overlook the implications for how Sol can accelerate your engineering workflows”
https://x.com/gdb/status/2075363531042726216
GPT-5.6 comes in three model tiers. → Sol handles long-horizon coding and agentic work that demands planning, tool use, and follow-through. → Terra balances performance and cost for everyday work. → Luna brings speed to well-defined, high-volume work. Across knowledge-work”
https://x.com/OpenAIDevs/status/2075286157186003348
GPT‑5.6 Sol, Terra, and Luna are rolling out in the OpenAI API. Programmatic Tool Calling is available in the Responses API, with Multi-agent initially available in beta.”
https://x.com/OpenAIDevs/status/2075274093327470923
Here is an example of a real work use case with Codex and 5.6 Sol I have a new book coming out in October, it has gone through rounds of editing and proofreading. I gave it the full PDF, the AI took 30 minutes & gave me dozens of notes. None were wrong (but plenty were pedantic)”
https://x.com/emollick/status/2075294040971464959
I forgot to mention this gpt-5.6-sol is world leading in computer use. It made me use it 100x more. When we lost access to 5.6, I quickly started to go insane without it”
https://x.com/theo/status/2074720467395756499
I talk to a lot of companies that still have active efforts to build GPTs. (It remains weird that OpenAI abandoned GPTs after rolling them out. They were the precursor to Skills & could have been a bridge to organizational-wide AI if converted into Skill libraries for agents)”
https://x.com/emollick/status/2073953911594004838
I think the point of this screenshot is that Sol is able to go from high level ideas to autonomously editing configs and launching experiments rather than Sol being responsible for end to end post training Luna. Still, very cool!”
https://x.com/nrehiew_/status/2075316190386462888
Notes on GPT-5.6, which includes some interesting new additions to the API (programmatic tool calling and multi-agent in particular) – plus 18 pelicans for the 6 reasoning levels and 3 new models:”
https://x.com/simonw/status/2075306164993315192
So powerful to get the magic of Codex inside ChatGPT. We’ve been working on making Chat more agentic for a while, and it’s really awesome to see what people are doing with it now.”
https://x.com/fidjissimo/status/2075305622120325363
Starting today, the Codex app is merging with the new ChatGPT desktop app 🔥”
https://x.com/avstorm/status/2075266403297362364
Stoked to bring GPT 5.6 Sol, Terra and Luna to everyone! It’s the first time I’ve felt comfortable delegating the hardest problem out there and let it cook in peace The model also has an insane ability to continue working until it is satisfied by the output All of this whilst”
https://x.com/reach_vb/status/2075269547439907269
When GPT-5 came out, I created a procedural brutalist city builder as a demo (you can see it in the quoted tweet) I used GPT-5.6 Sol in Codex to do the same thing, touching no code. Less than a year… Play with it (its fun, if you like cities):
https://x.com/emollick/status/2075426533896868046
If you use the Codex app today, update it as usual. It will become the new ChatGPT desktop app, where Codex has its own dedicated space. Here’s what’s new for developers:”
https://x.com/OpenAIDevs/status/2075275880704995342
🎓 New course launch from LangChain Academy: Introduction to Deep Agents ✅ Learn what a harness is, and why agents need one ✅ Understand the 4 core capabilities of a harness ✅ Start building with Deep Agents ✅ Trace and deploy with LangSmith”
https://x.com/LangChain/status/2074539083204820997
agent memory has always been reactive. OpenWiki makes it proactive. connect to sources, tell it what you care about, and your agent hits the ground running . what we’re building is really exciting! try it out and get involved, it’s open source! 👇”
https://x.com/colifran_/status/2075406926087934376
big update to openwiki – it now supports two modes: – code brain: create a wiki for a code base – personal brain: create a wiki for more general purpose tasks (email, web, etc) webinar at 11am PST (5 minutes!) where we will be talking about wikis!”
https://x.com/hwchase17/status/2075277641066938454
deepagents is our newest open source project – an open source, model agnostic agent harness this is maybe the most important academy course we’ve launched”
https://x.com/hwchase17/status/2074547871194698207
Strands Agents — Open Source AI Agent SDK for Python & TypeScript
https://strandsagents.com/?trk=acf96c5e-1749-4bb0-856f-d213b19d8c74&sc_channel=display+ads
State of CLI Coding Agents, Mid-2026
https://blog.arcbjorn.com/state-of-cli-coding-agents-2026
SWE-1.7: Frontier Intelligence at a Fraction of the Cost | Cognition
https://cognition.com/blog/swe-1-7
SWE-1.7 is available today in Devin across Web, Desktop, and CLI, running at 1000 tok/s. More details on the training run, infrastructure, data pipeline, and long-horizon behavior in the blog post:”
https://x.com/cognition/status/2074882980640698719
Introducing Grok 4.5 · Cursor
https://cursor.com/blog/grok-4-5
As working with AI agents looks more like management, we may want to consider large-scale management training for the AI era. The US government actually did this once, & the WW2 Engineering, Science, and Management War Training program was a large reason for the post-war boom.”
https://x.com/emollick/status/2073852766427009329
Today we’re launching Glass for Patients, the personal AI agent for your health. Glass reviews all of your healthcare data and analyzes it alongside the world’s medical knowledge to help you continually understand and optimize your health. Get started at
https://x.com/GlassHealthHQ/status/2074921736269939061
Announcing Grok 4.5, our first model trained specifically for coding and agents. It was trained with Cursor and offers frontier intelligence at leading speeds and cost efficiency.
https://x.com/SpaceXAI/status/2074915721684086811
[2510.04618] Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
https://arxiv.org/abs/2510.04618
// ReContext // Models now support 128K context windows and still fail to use evidence that is already in the prompt. Where is the gap? New paper introduces ReContext, a training-free inference harness for long-context reasoning. It uses model-internal relevance signals to”
https://x.com/dair_ai/status/2074178316819677238
Ghost memory” is a real problem with agents. You might have seen the issue where a long-running agent still confidently repeats a user fact that stopped being true weeks ago? New research names the failure “ghost memory.” Old facts, current facts, and the transition between”
https://x.com/omarsar0/status/2074121191846261022
Duck Harness: Winning Solution for ARC-AGI-3 Milestone 1 | Tufa Labs
https://tufalabs.ai/research/duck-harness/
UMA is a Paris-based startup designing general-purpose mobile and humanoid robots with human-level dexterity. UMA stands for Universal Mechanical Assistant Concept: Early prototype:”
https://x.com/TheHumanoidHub/status/2074565441205506515
Harness EngineeringからRSIへ AI自身がAIをつくり、改善していく──再帰的自己改善（RSI）はどのように実現するのでしょうか。この問いに対して、Thinking Machines Lab 共同創業者の Lilian Weng 氏（@lilianweng）が、モデルを取り巻く実行系＝「ハーネス」の設計こそが現実的な出発点だと論じる”
https://x.com/SakanaAILabs/status/2074489949529776308
Less than 2 years later, with Fable: “simulate an encounter between a mind flayer and a drow warrior of equal CR. Set up initial stats then simulate each move, including initiative, rolling dice as needed, starting from 60 ft apart. Show me the results in a 3D simulation
https://x.com/emollick/status/2073985468736106544
Fable: “Last and First Men is out of copyright. I want you to make a movie that features a reading of it with appropriate mixes of animation and images using access to the APIs you have (elevenlabs, hugging face) . Give me the first 10-15 minutes, ending at an appropriate break.
https://x.com/emollick/status/2072872373758382497
LingBot-World 2.0 (Infinity) is out on Hugging Face interactive world model with: Hour-long generation with zero quality drift Rich actions & events: attack, cast spells, shoot, summon storms Agentic world: a Director Agent drives real-time world evolution 720p/60fps.”
https://x.com/_akhaliq/status/2074936755296641520
Coding a robot with GPT 5.5! A 7dof robot arm w/ functional kinematics. [📍 bookmark, it’s open source] An open source harness for generating 3D models with your favorite coding agent. Custom gui, and STEP parts/assembly, 100% generated in Codex. Thanks for sharing,”
https://x.com/IlirAliu_/status/2074039667461165330
Leave a Reply