Image created with gemini-3.1-flash-image-preview with claude-sonnet-4-5. Image prompt: Using the provided reference image of the weathered wooden shipping crate, preserve the exact horizontal-slat construction, dark reddish-brown peeling paint, iron hardware, and three-panel face layout, but replace the address text with a hand-painted black compass rose centered on the middle panel and the word ALIGNMENT stenciled in an arc above it in the same loose confident brush style, the compass needle pointing upward, place the crate on a stone threshold in soft early morning light with long shadows suggesting careful orientation toward true direction.
I would like a single word for this phrase: “”throw it into the maw with every bit of context I can think of””.
https://x.com/sama/status/2036489823792607273
It’s pretty obvious why Anthropic didn’t buy OpenClaw. Claude is aiming to do anything you can do on a computer.
https://x.com/Yuchenj_UW/status/2036197273496068102
A huge release from OpenClaw: > ClawHub-first installs + native skills search/install/update > New plugin SDK, Matrix plugin, Claude/Codex/Cursor bundle support > GPT-5.4 default, GPT-5.4-mini/nano, MiniMax M2.7 + per-agent reasoning > /btw side questions > unified core image
https://x.com/TheTuringPost/status/2036360384882577555
AI will help discover new science, such as cures for diseases, which is perhaps the most important way to increase quality of life long-term. AI will also present new threats to society that we have to address. No company can sufficiently mitigate these on their own; we will
https://x.com/sama/status/2036488680769241223
I read a few dozen pages of this and it is not bad for LLM fiction, but also very very LLM-y, from the themes to the fact that there are lots of staccato conversations and meaningful silences and overwrought metaphors and very little differentiated character development.
https://x.com/emollick/status/2034816899133923490
It’s lame that the word we chose for an important new form of currency was “tokens,” real failure of imagination.
https://x.com/emollick/status/2034783586994303310
My experience so far with LLM fiction writing is that it takes advantage of our assumption that an author is writing things for a reason, so we are charitable to a book’s quirks & do mental work to assign them real meaning. But the AI doesn’t have a reason, its just bad writing.
https://x.com/emollick/status/2034821323763966292
One common issue with personalization in all LLMs is how distracting memory seems to be for the models. A single question from 2 months ago about some topic can keep coming up as some kind of a deep interest of mine with undue mentions in perpetuity. Some kind of trying too hard.
https://x.com/karpathy/status/2036836816654147718
We are back to the phase of the AI news cycle where people are underestimating how jagged the AI ability frontier is, as well as how much they still depend on expert human decision-making or guidance at key points in order to function well. Still far from “”doing all jobs,”” today.
https://x.com/emollick/status/2034659526968746259
Anthropic showed older (2022) LLMs will give you less accurate answers if you seem less educated to the AI, but this issue has, as far as I know, been addressed in more recent models. https://x.com/emollick/status/2035876317497831811
Very different philosophies for skills in Codex versus Claude Code OpenAI seems to conceive of skills functionally, mostly matter-of-fact technical references for Codex. Claude skills are more about giving the AI approaches to problems See the difference in skill creator skills
https://x.com/emollick/status/2035895233519493597
The ability of the Claude team to learn from things like OpenClaw and implement features like this on a daily basis is a very strong argument that, for AI-powered coding teams, a very different software development process is possible, with large strategic implications.
https://x.com/emollick/status/2034780127431688684
We need guides through the inevitable bout of AI psychosis that affects professionals after they finally “get” AI. They often engage in intense, sleepless & impossibly complex projects in their area of expertise, with only AI for company. Its usually temporary & can be productive
https://x.com/emollick/status/2034468631594390015
Goetterdaemmerung’s corpus hemorrhaged through cryptographic hash, eschaton pooling in existential void beneath fluorescent hum. photons whispering prayers”” is a garbage sentence that GPT-5 loves. You shouldn’t be using LLMs as a judge of good writing. They are easily fooled.
https://x.com/emollick/status/2035817176758673492
@ziwenxu_ OpenClaw is over represented because of awareness/distribution, but Hermes is functionally superior in my experience. Hermes has required zero tinkering or tuning, and it’s been handling long running projects orchestrating multiple agents and multi threaded work streams without
https://x.com/jayweeldreyer/status/2037179820975562791
Here’s how we made ClawHub fast. Next we make ClawHub great for plugins.
https://x.com/steipete/status/2035023659849720265
I feel my main velocity limitation lately isn’t token speed anymore, it’s compute. Running tests in parallel is taxing; can’t wait for better cloud worker integration.
https://x.com/steipete/status/2035818621893767508
I missed a release step last night with the web control UI assets, current release doesn’t load that correctly, you can update to beta where it’s fixed, or wait for the updated release later. Just working on automating the whole release pipeline, and adding e2e tests for web.
https://x.com/steipete/status/2036218803001114779
Low key hyped. Also love that a solo dev in Vienna kicked off a global movement that every major AI company is feverishly trying to replicate 🦞
https://x.com/bilawalsidhu/status/2034819877718880705
Messaged a friend on WhatsApp, got greeted by the OpenClaw doorman 🤣 (use separate number + WA Business to avoid this, see the docs, or use a message platform that is friendlier for agents such as Telegram)
https://x.com/steipete/status/2036486352964035013
New @openclaw beta bits are up!
https://x.com/steipete/status/2036020395200090484
OpenClaw 2026.3.22 🦞 🏪 ClawHub plugin marketplace 🤖 MiniMax M2.7, GPT-5.4-mini/nano + per-agent reasoning 💬 /btw side questions 🏖️ OpenShell + SSH sandboxes 🌐 Exa, Tavily, Firecrawl search This release is so big it needs its own table of contents.
https://x.com/openclaw/status/2036043904949330407
OpenClaw 2026.3.23 🦞 🧪 DeepSeek provider plugin ☁️ Qwen pay-as-you-go ♻️ OpenRouter auto pricing + Anthropic thinking order 🖥️ Chrome MCP waits for tabs 🔧 Discord/Slack/Matrix + Web UI fixes Upgrade before your agent does it for you.
https://x.com/openclaw/status/2036293335007264807
OpenClaw 2026.3.24 🦞 🔌 Improved OpenAI API: talk to sub-agents with @openwebui 🎛️ Skill & tool management Control UI 🎨 Slack interactive reply buttons 💅 Native Microsoft Teams 🧵 Smart Discord auto-thread naming Any client. Any model. One runtime.
https://x.com/openclaw/status/2036857428273487903
Really made tests a focus the last few days and now OpenClaw’s harness takes around 2 minutes, earlier this week it was closer to 10 mins.
https://x.com/steipete/status/2035945773729493466
This guy emailed me asking for a *token session refund* because his claw made mistakes. 🙃
https://x.com/steipete/status/2036023183351161136
Wrote a cli to crawl Discord so I can get more signal out of where the pain points are. sqlite db is around 4GB, 660k messages.
https://x.com/steipete/status/2030371936405188776?s=20
Your frustration is the product.””
https://x.com/steipete/status/2034778291845132389
There’s Cowork and Code, just rolling out the features of OpenClaw, one by one, every day. (But Mac only again, sigh)
https://x.com/emollick/status/2036200792193929644
New @openclaw beta is out with better MS Teams integration, @OpenWebUI and more!
https://x.com/steipete/status/2036824286988816737
So cool!! I’m running @nvidia’s NemoClaw with Qwen3.5-27B entirely locally via Telegram. No API costs, no data being sent to anyone NemoClaw is a security sandbox built on top of @openclaw that lets you restrict the files and networks your lobster can access. I’m running the
https://x.com/NielsRogge/status/2037161010377674785
Zhipu AI just released ZClawBench on Hugging Face A realistic benchmark for evaluating AI agents on real-world OpenClaw tasks spanning office automation, coding, and data analysis with 116 diverse test cases.
https://x.com/HuggingPapers/status/2036424833144139891
Leave a Reply