“Introducing Harvey Agents: https://x.com/harvey__ai/status/1899491666429632907
“Our new API primitive: the Responses API. Combining the simplicity of Chat Completions with the tool-use of Assistants, this new foundation provides more flexibility in building agents. Web search, file search, or computer use are a couple lines of code! https://x.com/OpenAIDevs/status/1899531367056064814
“this is a tremendous accomplishment from the team. i am obviously biased but i think it’s one of the most well-designed and useful APIs ever, and that people will really love it.” / X https://x.com/sama/status/1899579431905305027
“we trained a new model that is good at creative writing (not sure yet how/when it will get released). this is the first time i have been really struck by something written by AI; it got the vibe of metafiction so right. PROMPT: Please write a metafictional literary short story” / X https://x.com/sama/status/1899535387435086115
“Harvey released Workflows AI agents for legal tasks, with reasoning, planning, and adapting capabilities In blind reviews, lawyer evaluators rated legal work produced by workflow agents as equal to or better than that of human lawyers https://x.com/rowancheung/status/1899713342484173043
“MANUS AI: HYPE VS. REALITY 🔍 @peakji (co-founder of @ManusAI_HQ) confirmed rumors: ✅ Built on Anthropic Claude Sonnet, not their own foundation model ✅Has access to 29 tools and uses @browser_use open-source for browser control ✅User communicates with executor agent and not https://x.com/_philschmid/status/1899046957860979178
“📊 Introducing the Agentic LLM Leaderboard: A new way to compare how different LLMs perform when powering agents! See how models stack up on various benchmarks, with clear comparisons between vanilla and agentic setups. Built with smolagents framework 🤖 Kudos @AymericRoucher https://x.com/fdaudens/status/1899251429518270813
“The popular AI agent “Manus” launched in China is automating about 50 tasks, and the scenario is too dystopian. It’s said to be more accurate than DeepSeek. It can simultaneously perform SNS analysis, financial transactions, research, purchasing, and more. https://x.com/thinking_panda/status/1897951585990590469
“OpenAI’s Agents SDK is Transforming AI Agent Development” / X https://x.com/AtomSilverman/status/1899862633341477221
“I think China’s second DeepSeek moment is here. This AI agent called ‘Manus’ is going crazy viral in China right now. Probably only a matter of time until it hits the US. It’s like Deep Research + Operator + Claude Computer combined, and it’s REALLY good. https://x.com/rowancheung/status/1898093008601395380
“OpenAI is reportedly planning specialized AI agents for tasks like Ph.D.-level research Three agent tiers expected: —Business professionals ($2k/mo) —Advanced devs ($10k/mo) —PhD-level researchers ($20k/mo) OAI charges $200/mo for its Operator agent: https://x.com/rowancheung/status/1897554278576685425
“We’re launching new tools to help developers build reliable and powerful AI agents. 🤖🔧 Timestamps: 01:54 Web search 02:41 File search 03:22 Computer use 04:07 Responses API 10:17 Agents SDK https://x.com/OpenAIDevs/status/1899531225468969240
“🤖 Agents SDK—our new open-source SDK for orchestrating multi-agent workflows, improving upon Swarm. Configure agents with built-in tools, hand off tasks, add safety guardrails, and visualize execution traces for debugging and optimizing performance. https://x.com/OpenAIDevs/status/1899531857143972051
“🔎 Web search—integrate with a few lines of code and your agent can get up-to-date answers from the web (with citations). Available in preview: https://x.com/OpenAIDevs/status/1899531516448768103
Pentagon to give AI agents a role in planning, operations • The Register https://www.theregister.com/2025/03/05/dod_taps_scale_to_bring/
“OpenAI released new DIY tools for building custom AI agents, including: A CUA model-powered Responses API with tools for web browsing, computer use, and file management An open-source Agents SDK to orchestrate single and multi-agent systems https://x.com/rowancheung/status/1899713252637991092
“I tested Manus AI. It’s the closest thing I’ve experienced to a truly autonomous AI agent. I can’t wait till this thing can use desktop apps like Premiere and Photoshop. It low key feels like baby AGI. Here’s my 10 minute review: https://x.com/bilawalsidhu/status/1898945929970843842
“🤖 OpenAI Responses API Yesterday OpenAI released a new Responses API, including built-in tools and management of conversation state. You can now build with these features in LangChain! Try it out with `pip install langchain-openai==0.3.9rc1` Docs in 🧵 https://x.com/LangChainAI/status/1899888134793683243
“OpenAI announces new Responses API for easily building AI Agents 1. Responses API A single API that unifies Chat Completions and tool usage. Build agents with multiple “turns” in one request. Built-In Tools: – Web Search Tool: Get timely answers with clear citations. Uses a https://x.com/scaling01/status/1899510452473790537
“Introducing the Responses API: the new primitive of the OpenAI API. It is the culmination of 2 years of learnings designing the OpenAI API, and the foundation of our next chapter of building agents. 🧵Here’s the story of how we designed it: https://x.com/athyuttamre/status/1899541471532867821
(3) ⚡️The new OpenAI Agents Platform – Latent.Space https://www.latent.space/p/openai-agents-platform
“OpenAI just launched the Agents SDK – a simple yet powerful toolkit for building AI apps that can actually do things in the real world! I summarized everything you need to know about it and how it is going to be a game changer for anyone building agents. https://x.com/AtomSilverman/status/1899511053601698073
“The prices for OpenAI’s upcoming agents have been leaked. They range from $2000-20,000 per month. A corporation will only pay these prices if it receives a corresponding value from the agents. And I trust OpenAI to deliver. In any case, these costs indicate that the upcoming https://x.com/kimmonismus/status/1897321124687413581
“NEW: OpenAI announces new tools for building agents. Here is everything you need to know: https://x.com/omarsar0/status/1899530784832459043
“We made an agent that can generate @3blue1brown style videos about *anything*. We’ve also released a benchmark for animated educational videos so we can systematically improve this tech! Some notes below:” / X https://x.com/KrishRShah/status/1897062578347757940
“Sudowrite had one of its biggest days of new signups ever yesterday! We’ve always wanted to give authors an AI model of their own. Something made just for them. Stories help us understand and empathize with one another, and these days, we need stories more than ever. We https://x.com/superamit/status/1898104609836876075
“It’s 2025 and most content is still written for humans instead of LLMs. 99.9% of attention is about to be LLM attention, not human attention. E.g. 99% of libraries still have docs that basically render to some pretty .html static pages assuming a human will click through them.” / X https://x.com/karpathy/status/1899876370492383450
“Have not played with Manus (the much hyped agent from China) yet but this seems credible The current frontier LLMs are very good & their abilities have not been fully explored even by the labs making them. Too much waiting for mysterious new LLMs, too little pushing what we have” / X https://x.com/emollick/status/1898930212521283848
“Cloudflare just dropped an AI Agent framework to build AI agents that persist state, execute tasks, browse the web, and call AI models in real-time. All of that with just a few lines of Code. 100% opensource. https://x.com/Saboo_Shubham_/status/1895891753024307590
“Opera just released Browser Operator AI Agent It’s an autonomous browser AI Agent that can do the tasks you might just find too complex or too boring. The future of browsing is autonomous web agents. https://x.com/Saboo_Shubham_/status/1896976402546831519
“I am hosting a FREE webinar if you are interested in learning how to build effective agentic workflows with OpenAI’s Agents SDK. Join me here: https://x.com/omarsar0/status/1899571435938677222
“We are proud to partner with @deutschetelekom to make Perplexity Assistant the native feature on their new AI Phone. https://x.com/perplexity_ai/status/1896560542556533217
“How C.H. Robinson saves 600+ hours/day automating orders with LangGraph and LangSmith @CHRobinson handles 37+ million shipments a year and is using AI to move logistics faster. With LangGraph and LangSmith, they automated 5,500+ email order requests a day. Learn about how they: https://x.com/LangChainAI/status/1899475651863978410
“Really interesting work coming out of Toronto on automating social science with AI from a number of researchers. Worth paying attention to.” / X https://x.com/emollick/status/1898841523585716478
“This is extremely promising and the best use case of Operator so far! @OpenAI ChatGPT Operator is great for testing my local dev environment to see if my feature is working! Tunnel Operator to your local dev env and let it test your feature. Waiting for an API and @cursor_ai https://x.com/kieranklaassen/status/1882585726560469173
“So cool that this designer built her portfolio using v0 — without any prior coding experience https://x.com/alirtariq/status/1894423036771578285
“Made a new guide to writing faster MLX and avoiding some common perf cliffs. https://x.com/awnihannun/status/1899861832774668399
“Build more wrappers. We haven’t even begun to max out the permutations of the building blocks at our disposal. Wrappers aren’t the problem. Lack of imagination is.” / X https://x.com/bilawalsidhu/status/1899240240822342013
“Manus AI is pretty good at vibe coding games. Just gave one prompt: “code a threejs game where you control an f-117 nighthawk and can drop bombs over a data center and accumulate points for how many runaway AGIs you destroyed.” And got this: https://x.com/bilawalsidhu/status/1898814743193768014
“🚢 The @weaviate_io team keeps shipping! 🤖 We recently released the 𝗗𝗮𝘁𝗮𝗯𝗮𝘀𝗲 𝗤𝘂𝗲𝗿𝘆 𝗔𝗴𝗲𝗻𝘁, and today, we’re launching the 𝗧𝗿𝗮𝗻𝘀𝗳𝗼𝗿𝗺𝗮𝘁𝗶𝗼𝗻 𝗔𝗴𝗲𝗻𝘁! 🔥 Personally, I’m most excited about this one because it doesn’t just let you query the https://x.com/bobvanluijt/status/1899521133940011476
“A heartwarming case of ChatGPT being very useful, identifying a medical emergency. It would be great in the future to have the model realize that it’s asked about a life critical situation, and then do a free temporary upgrade to the most capable model. https://x.com/BorisMPower/status/1899116786819219582
“Today we’re introducing Template Hub, the first step in offloading global work done by humans to agents. https://x.com/convergence_ai_/status/1897648414029955378
“Meet consistenX, an MVP I built in just 4 days using @lovable_dev. This tool keeps me engaged on X by allowing me to jot down and refine my tweet ideas seamlessly. Plus, it helps me create focused time blocks for dedicated use of X. → https://x.com/gbadamosixxl/status/1897060059647222025
“”With AI and AI-assisted coding, the cost of prototyping has plummeted and this is generating a new way to invent things” @AndrewYNg during his keynote speech at AI Dev 25. https://x.com/DeepLearningAI/status/1900593192497520842
“During the Panel Discussion on Building AI Applications in 2025, @romanchernin from @nebiusai shared this key takeaway: “The advice I would love to give myself. Everything changes so fast. Focusing on solving real problems is important. You have to keep that focus on real https://x.com/DeepLearningAI/status/1900636957740323302
“Coders are over-represented on this site, so discussion on AI access is assumed to be about APIs, but, for most people, AI means using a chatbot, and usually the ChatGPT interface. It is through those interfaces that AI will prove to be useful, or not. At least for now. https://x.com/emollick/status/1897812093576917244
“The success of v0 is partially due to great @shadcn /ui integration. Notion arguably has the best UI kit for knowledge work apps. Also auth/permissions/etc. built in. Very strong starting point for building dynamic apps.” / X https://x.com/mathemagic1an/status/1899625715391508585
“MCP is all the rage these days, and I read something along the lines of “MCP is better than traditional APIs because agents will dynamically adapt if you change the number of args in a tool, so versioning is less painful” 👀 I might be way off the mark but…this is still a huge” / X https://x.com/jerryjliu0/status/1899489337412378909
“This API shape is genuinely much nicer than the Chat Completions one. Just wish we could fast-forward 24 months into the future and skip the part where we’ll have to support both APIs for every feature!” / X https://x.com/corbtt/status/1899585079695069580
“Stack Overflow UI reimagined using Windsurf Vs V0. Built in less than 10 minutes. Insane 🔥 https://x.com/TheMahekUnnisa/status/1894625855672127918
“📄 File search—retrieve precise information from large document collections, with built-in query optimization and custom reranking. https://x.com/OpenAIDevs/status/1899531586950795662
“Coding is getting easier but building software is not; so many challenges associated with data management, state management, deployment/scaling and more remain hard.” / X https://x.com/sarahcat21/status/1899734834282405990
Transforming Game Asset Creation With Genies’ AIGC-Powered System – Genies https://genies.com/blog/transforming-game-asset-creation-with-genies-aigc-powered-system
“For my birthday my wife built this ‘love letter’ app using v0 without any coding experience and just four prompts on the free plan.😭🫶 https://x.com/spoonyvu/status/1895875151809691949
Sakana AI on X: “The AI Scientist Generates its First Peer-Reviewed Scientific Publication We’re proud to announce that a paper produced by The AI Scientist-v2 passed the peer-review process at a workshop in ICLR, a top AI conference. Read more about this experiment → https://t.co/LpLYLnZMCQ
“In the last 7 minutes I have built a pdf -> text converter app using @Replit . Now I plan to add @elevenlabsio integration so I can listen to my books. I think I can be unstopable with @bubble + @Replit stack 🤩 https://x.com/bestbubbledev/status/1896947792712741081
“Introducing our latest blog on WebDev Arena: A Live LLM Leaderboard for Web App Development! How does WebDev Arena work? Submit a prompt → Two LLMs battle it out → You vote on the better web app. Since launching in Dec 2024, we’ve gathered 100,000+ community votes evaluating https://x.com/lmarena_ai/status/1899181467252711593
“This tool helps you create an authentic LinkedIn presence with our AI-powered persona builder. https://x.com/VikashSparxIT/status/1894426083011039283
“What if AI agents could pause conversations to present a form for collecting data instead of relying on messy back-and-forth tool calling loops? 😎The good part, the collected data does not need to be processed by AI! I’ve built a demo using Langgraph Prebuilt Swarm Agents, https://x.com/turungkadircan/status/1896269494936322138
“I taught a grad course on AI Agents at UCSD CSE this past quarter. All lecture slides, homeworks & course projects are now open sourced! I provide a grounding going from Classical Planning & Simulations -> RL Control -> LLMs and how to put it all together https://x.com/rajammanabrolu/status/1896962193893339390
“A key to AI agents is an ability to self-correct. The world is full of odd errors and weirdness, and if AI can’t recognize and problem-solve when it hits a wall, errors compound & the agent is useless It doesn’t always, but here is Manus hitting problems & improvising solutions https://x.com/emollick/status/1899192116443509139
Microsoft appears to be working on 3D gaming experiences for Copilot | TechCrunch https://techcrunch.com/2025/03/10/microsoft-appears-to-be-working-on-3d-gaming-experiences-for-copilot/
“Built this Hyperliquid dashboard for a few coins using Replit & some vibe coding – Replit Agent is great tbh Features i’ve added: Real-time Order Book Analysis Advanced Market Metrics: Bid-ask spread and spread percentage Order book imbalance (ratio between bid and ask volume) https://x.com/0xAmSS/status/1896551065174077490
“Excited about our latest global partnership. We’ll be working with LG CNS to co-develop SOTA agentic Korean models that seamlessly integrate with North to accelerate enterprise AI adoption in South Korea! https://x.com/aidangomez/status/1899133769161797880
“💫 New @DeepLearningAI course: Long-term Agentic Memory with LangGraph Learn about how to build an agent with long term memory from @AndrewYNg and @hwchase17 (@LangChainAI CEO). In this course, you’ll learn to: ✔️ How to apply three types of memory — semantic, episodic, and https://x.com/LangChainAI/status/1900588929772122383
“Reka open-sourced Flash 3, a 21B parameter reasoning model —Matches o1-mini on benchmarks —32k context length —Ideal for on-device deployment —Finetuned on synthetic and public datasets —Powers Nexus, Reka’s platform for creating and managing AI agents https://x.com/rowancheung/status/1899713297584173449
“No one becomes a clinician to do paperwork, but it’s becoming a bigger and bigger administrative burden, taking time and attention away from actually treating and supporting patients. That’s why we’re introducing Microsoft Dragon Copilot, the industry’s first AI assistant for https://x.com/satyanadella/status/1896581949298536757
“Scale AI bagged a multimillion-dollar deal from the U.S. Department of Defense Scale and its tech partners will lead Thunderforge, DoD’s program to deploy AI agents for military planning and ops This will support decision-making for military leaders https://x.com/rowancheung/status/1897554362391548060
“The team behind Manus partnered with Alibaba’s Qwen to develop a Chinese version of its autonomous agent The collaboration will integrate Manus with Qwen’s open-source models and computing infra This comes just after Manus went viral last week! https://x.com/rowancheung/status/1899713389439377678
“🦜💬Introducing Agent Chat UI An OSS web app for interacting with any LangGraph app (PY & JS/TS) via a chat interface Agent Chat can render: – Human/AI Messages – Tool Calls/Results – Human in the Loop – Generative UI (tomorrow 👀) Watch the video, and try it out today 👇 https://x.com/LangChainAI/status/1899497457459122535
“X users can now trigger the Grok AI assistant by replying to posts with “@grok.” Once tagged with a question, Grok replies with the answer Perplexity has also been doing this to provide quick access (and gain traction). https://x.com/rowancheung/status/1899003647272317248
Microsoft’s new Dragon Copilot is an AI assistant for healthcare | The Verge https://www.theverge.com/news/622528/microsoft-dragon-copilot-ai-healthcare-assistant
“🏗️ Full-Stack Agent Development Tutorial Build powerful end-to-end agent applications with this comprehensive guide showcasing LangGraph and CopilotKit integration. Key features: – CoAgent function calling – Full-stack implementation – UI development Dive into the tutorial 👉 https://x.com/LangChainAI/status/1896304507434217535
“Congratulations to Lightspeed-backed @Moveworks for surpassing $100M ARR and doubling its customer base in the last two years! Their generative AI Copilot allows employees to go beyond searching for information allowing them to take action within the enterprise applications they https://x.com/lightspeedvp/status/1838650516383109145
“Build an agentic corrective RAG, step-by-step: – It can search through your docs – and fallback to web search if needed https://x.com/akshay_pachaar/status/1897853624187076758
“Microsoft launched ‘Dragon Copilot’, an AI assistant for healthcare It merges voice dictation with ambient listening to handle clinical documentation and surface relevant information They’re claiming it’s already saving clinicians ~5 min/patient https://x.com/adcock_brett/status/1898775589441442100
“Microsoft is reportedly developing MAI, a new family of AI models matching frontier offerings from industry leaders With the tech, the company is looking to reduce reliance on OpenAI for its Copilot suite for free and Pro users https://x.com/rowancheung/status/1899003602657481127
“In the future, every moving object in the physical world will be an AI agent” / X https://x.com/adcock_brett/status/1899500640755450016
“🦜🪞LangGraph-Reflection This prebuilt graph is an agent that uses a reflection-style architecture to check and improve an initial agent’s output. This reflection agent uses two subagents: – A “main” agent, which is the agent attempting to solve the users task – A “critique” https://x.com/LangChainAI/status/1899493848843477178
“I just built a CRO AI chat using the new @Replit Agent V2 powered by Claude Sonnet 3.7! The chat can analyze uploaded files (two of my favorite CRO books) and provide detailed answers based on them. This could be an excellent training tool for junior CRO specialists or even for https://x.com/victorpaycro/status/1894537790622503097
“For years, @GroupMe has helped friends, teams, and communities stay connected. Now with Copilot, planning and chatting is easier than ever. Need homework help? A quick suggestion? The perfect reply? Copilot in GroupMe is your group chat companion, just ask and keep things https://x.com/yusuf_i_mehdi/status/1899853293750538451
“I made an AI agent that creates static image ads for you (that actually convert) Here’s how it works: – Enter product URL – Choose proven template – Our AI agent tailors it to your brand (without being cringe) If you use CreativeOS, its like that, but automated https://x.com/safwaankay/status/1895593746710012198
“We’re excited to announce a strategic partnership with LG CNS to co-develop secure agentic AI solutions for South Korean enterprises. This marks another step in our global expansion to unlock real value for businesses across markets! https://x.com/cohere/status/1899083562495713516
“What do study groups, run clubs, and fantasy leagues all have in common? They run on groupchats. For millions of users and over 70% of US colleges, that means our app @GroupMe! And now Copilot is right there in-app to support with a side chat or quick assist. https://x.com/mustafasuleyman/status/1899852903403454624
“You know what’s common between Hugging Face, Stability AI, Mistral, LangChain, and CrewAI? They’re all open-source AI companies driving massive breakthroughs! The next big wave isn’t just AI Agents—it’s COSS AI Agents. So at Potpie AI we decided to actively support all Agentic https://x.com/aditikothari_/status/1896949254502973671
“Working on making LangGraph/LangChain more accessible inside IDEs What is better: llms.txt or MCP?” / X https://x.com/hwchase17/status/1899873990774243749
“It’s AI Dev 25 Day—let’s kick it off with a new course! Today, on Pi Day, hundreds of AI builders are gathering in San Francisco, and we decided to launch a new course to extend the celebration to our global community! Introducing Long-Term Agentic Memory with LangGraph—a https://x.com/DeepLearningAI/status/1900562773303554110
“Personal AI Agent Mind-Map This is a Multi-agent. Tech Stack: – Python’s (Langchain and PydanticAI) – Supabase as DB for RAG and Memory I am building this for my Sem-end-Project. https://x.com/PratikKadam_/status/1896565808937189630
AI Agents with Sourcegraph | Industrialize your software development with agents https://sourcegraph.com/agents
“Copilot Voice speaks over 40 languages now! Whether you want to chat in Japanese or translate Italian, it has you covered. And Zurich team, don’t judge me while I try to learn “hi, how are you” in German. https://x.com/mustafasuleyman/status/1890091173517357460
“💡 Looking for inspiration or guidance as you’re building your AI agent? Check out the new Resources Hub on our website! Our Resources Hub contains guides on evaluating your LLM application, reports on the latest AI trends, and action-packed tales of how companies like @Replit, https://x.com/LangChainAI/status/1899922355004334492
“Want to build your own @v0 or AI agent? Three open-source templates you should check out: 1. Have an AI create a deployment and users “claim” it 2. AI chatbot with code generation / execution 3. Slackbot with tool calling https://x.com/leerob/status/1897753503839236282
“quick demo of an orchestra agent using filesystem mcp to organize my desktop https://x.com/philippe__page/status/1897413157225906663
“Build AI Agents and connect them to 100,000+ APIs with Postman’s AI Agent Builder. It has a drag-and-drop visual interface to build agent workflows with no code. https://x.com/Saboo_Shubham_/status/1896764344991682702
“Qodo Gen 1.0 – the IDE plugin by @QodoAI that embeds agentic AI, with deep context awareness, into JetBrains and VS Code. Leveraging LangGraph by LangChain and MCP by Anthropic, Qodo Gen: – Understands code deeply – Integrates your favorite tools – Autonomously tackles writing https://x.com/TheTuringPost/status/1900321016385359958
“Meet the new Embra. Not an AI Assistant – a full AI OS that scales you and your business. Great for sales & product. – Manages your email inbox – Takes meeting notes – Manages your relationships – Writes *great* email – Schedules events – Automates research Full customizable. https://x.com/zachtratar/status/1899521673529057293
“Replit AI Agent v2 uses Claude 3.7 Sonnet to build and dynamically render applications in realtime. It’s the most autonomous AI coding agent with real-time app design preview. https://x.com/Saboo_Shubham_/status/1897489097197019250
“Panel with Replit’s Michele Catasta, Stanford’s @percyliang , Nebius’ Roman Chernin and Hugging Face’s @Thom_Wolf, moderated by @lmoroney, on application building. Lots of tips on infra, open source, agentic workflows, benchmarking and code gen. Particular interest in how to take https://x.com/AndrewYNg/status/1900610468747899142
“We’re releasing 5 detailed guides on how to build agent workflows with Together AI! Each guide comes with its own deep dive notebook too: https://x.com/togethercompute/status/1899862571097661653
“People are building incredible things with v0, lovable, bolt, cursor, windsurf & replit agent. I summarized all the launches/projects from the top “vibe-coders” building with these tools. Take a look at what people built this week ⬇️ (save for later) https://x.com/AtomSilverman/status/1897784475029008767
“Our new Agentic leaderboard is now live!💥 I’ve long wanted a way to quickly know which LLM is best for powering agents. ✅ So we’ve just built a leaderboard with Albert Villanova! This ranks LLMs powering a smolagents CodeAgent on subsets of various benchmarks. 🏆 GPT-4.5 https://x.com/AymericRoucher/status/1899171108030738750
“We’re curating a collection of templates 📖 that show you how to build task-specific agents to automate knowledge work – and it’s available to anyone to signup and use! With just a few lines of code, you can orchestrate agent workflows that do one or more of the following: 1. https://x.com/llama_index/status/1898905634101203387
“CAMEL-AI @CamelAIOrg offers a great suite to create wrap your LLMs to create Agents but with features that study and observes how agents react. Here my blog on how to create agents with CAMEL and setup your multi agent society https://x.com/parthshr370/status/1896667180751847713
“Today @cohere is very excited to introduce Command A, our new model succeeding Command R+. Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding usecases. 🧵 https://x.com/aidangomez/status/1900169306987524440
Google upgrades Colab with an AI agent tool | TechCrunch https://techcrunch.com/2025/03/03/google-upgrades-colab-with-an-ai-agent-tool/
“7 notable open-source frameworks that enable AI agent’s actions👇 ▪️ LangGraph ▪️ AutoGen @Microsoft ▪️ CrewAI ▪️ Composio ▪️ OctoTools @Stanford ▪️ BabyAGI ▪️ MemGPT @Letta_AI Other emerging approaches: ▪️ @OpenAI’s Swarm ▪️ HuggingGPT ▪️ Semantic Kernel ▪️ Auto-GPT and https://x.com/TheTuringPost/status/1899779019740258439
“Perplexity API now supports MCP. You can use it give any of your favorite AIs real time information, eg: Claude. https://x.com/AravSrinivas/status/1899850017546129445
“We are building the largest source of fully managed MCP servers, with complete auth support. You can now integrate apps to your @cursor_ai, @windsurf_ai, or @AnthropicAI’s Claude desktop without dealing with infrastructure, reliability, or authentication complexities. Simply https://x.com/KaranVaidya6/status/1896970570056786378
“The Perplexity API Model Context Protocol (MCP) is now available. We’ve built an MCP server for Sonar, giving AI assistants real-time, web search research capabilities. Powered by Perplexity, Claude can now search the web and deliver real-time and accurate insights on demand. https://x.com/perplexity_ai/status/1899849114583765356
“Revamped our website 8600+ lines 3 days I have used Deepseek , Perplexity, Grok Deep Research for Content Strategy Built individual MVP’s using Bolt Exiting time for small teams (P.S I work directly with the founder at a 3 person startup) https://x.com/suryas_view/status/1897267924462919914
“Codeium released Windsurf Wave 4 with new features, including: —AI previews for rapid app iteration —Tab-to-import functionality —Suggested actions —Linter integration —Model choices for enterprise admins https://x.com/rowancheung/status/1897554385258909827
The AI Scientist Generates its First Peer-Reviewed Scientific Publication https://sakana.ai/ai-scientist-first-publication/
“We’re excited to announce that @Zoom is now leveraging AssemblyAI to help advance their AI research and development efforts! Zoom will be using AssemblyAI’s leading Speech-to-Text and Speech Understanding models to refine the data that’s used to train Zoom’s AI Companion.” / X https://x.com/AssemblyAI/status/1899496977169043743
“If it turns out LLMs are only capable of recombinatory innovation (finding novel connections among existing knowledge), that would still be very useful. Most innovation is recombination and one of the big issues in science is that fields are too vast for scientists to bridge them https://x.com/emollick/status/1898802108926661012
“I did it. I built “Cursor for Writing”. Introducing Lucid ✨ – Write at the speed of thought – Pull in context from anywhere – Chat + Deep Research https://x.com/rincidium/status/1897773663400653312
“🧑💻 Computer use—powered by the same CUA model behind Operator, you can now build agents capable of completing tasks on a computer, such as web QA testing or data entry. Available to select developers on usage tiers 3–5 as a research preview: https://x.com/OpenAIDevs/status/1899531682224431614
“I don’t know if I should praise the AI Scientist or question ICLR’s standards. Either way, time to learn Mandarin.” / X https://x.com/hkproj/status/1899771070690766920
“Of course, The AI Scientist got Schmidhubered 😅 https://x.com/hardmaru/status/1899825814327484556
“🚨 Introducing Archer Archer is an AI companion in your Slack workspace. Built with @LangChainAI @TryArcade and @modal_labs, Archer works *as* you – Read and review PRs – Draft and send emails – Find time and schedule events – Crawl sites for research All from within Slack👇” / X https://x.com/SamPartee/status/1896970692186530309
“Not great for my comparative advantage, but from some experiments we have done at Rotman, I am totally convinced the vast majority of research that doesn’t involve the physical world can be done more cheaply with AI & a little human intervention than by even good researchers. 1/7” / X https://x.com/Afinetheorem/status/1898822592594874598
“We just crossed 50,000 papers on Hugging Face (all the majors ones of the past two years should be covered), with dozens added every day & just enabled semantic search. It’s becoming the best place to do collaborative research, for example to ask questions directly to the authors https://x.com/ClementDelangue/status/1899163743889641949
“This was a fun experiment we ran while developing The AI Scientist-v2. With the permission of ICLR, we submitted an AI-generated paper to an ICLR workshop that passed the peer-review process. We documented the entire process and our learnings in a blog: https://x.com/hardmaru/status/1899665717215326283
“One thing I think about a lot is that models are optimized for coding and math. But they could be trained to do a lot of things that we just assume AI does badly. Like writing coherent fiction with a satisfying arc, for example.” / X https://x.com/emollick/status/1899546811548958862
“🔍 Finding research papers shouldn’t be hard. Now search 50K+ papers on hf papers using natural language, explore by concepts, or find your favorite authors. AI does the heavy lifting for you! ✨ https://x.com/fdaudens/status/1899285935914725727
“The AI Scientist is far from perfect. Occasionally it makes embarrassing citation errors. Here, it incorrectly attributed “an LSTM-based neural network” to Goodfellow (2016) rather than to the correct authors, Hochreiter & Schmidhuber (1997). We documented these errors in own https://x.com/SakanaAILabs/status/1899824257112391796
“Introducing Influsfera: Stalk your competitors with a single click. Paste the URL of your landing page & instantly research your rivals’ socials, pricing, partnerships, offerings, etc with detailed reports on what actually works. Join the waitlist below 👇 https://x.com/vixclotet/status/1895582984658661879
“our tool went semi-viral last month and our support chat-bot started getting 90k msgs/week GPT monitors all chats for me -reads every convo + analyzes user complaints -emails our team a report about notable patterns daily it’s become the best source of product insight we have https://x.com/MaxBrodeurUrbas/status/1896998844610838604
“Putting Manus AI through its paces — definitely a step up from ChatGPT Operator. I’ve got it scouting SF hotels and drone filming locations in Austin. Love that it can use the 3D view in Google Maps to reason about my queries. Look forward to covering in this week’s video. https://x.com/bilawalsidhu/status/1898458016178974959
“I assisted with many Ai aspects of of the final piece, from R&D to execution of sketch to production ready animation. Great to see Ai being used and accepted by traditional artists to help make a cohesive piece and prove we can all play nicely together! https://x.com/makeitrad1/status/1897405703159210225
“McDonald’s is planning a massive AI overhaul The co’s outlets will get AI tools for predictive maintenance and order accuracy as well as an “AI virtual manager.” It’s working with Google Cloud to deploy edge computing systems for these capabilities https://x.com/rowancheung/status/1899350924797100444
“I built an AI food journal in ONE evening with @lovable_dev! Snap a pic, let AI break down nutrition, & track your meals. Perfect if you hate counting macros, I’ve been using it all day. The craziest part is that I thought of it in the morning and it was a reality by evening. https://x.com/josh_maldonado/status/1896648976113504432
“We built a cargo company simulation game ( text base ) in just 1 day! 🚀 How? Using only Replit! 🎮 The game is live, and everyone is welcome to join. If we reach a good number of users, we’ll keep developing and activate the reward system. I have to say, Replit v2 is an https://x.com/ImCryptoGag/status/1897588777947705627
“We use Reka Flash 3 to power Nexus, our new platform for organizations to create and manage AI workers. 🤖🤝🧑⚕️🧑💼🕵️🧑🔬🧑🚀🟰🚀🚀🚀 Nexus workers have native deep research capabilities and can browse the web, execute code, and analyze internal files including documents, images, https://x.com/RekaAILabs/status/1899481294293147900
“Connect your LlamaIndex agents to any Model Context Protocol server! We’re closely following progress on the Model Context Protocol, an open-source effort to make it easy to discover and use tools. Using our MCP integration, you can use the tools exposed by any MCP-compatible https://x.com/llama_index/status/1899848532817035529
“20 Months: 0 → 7 papers (2 ICLR orals) & 40+ institution collabs. With a clear vision, we’re building the open-source foundation for tomorrow’s agents. We also release MGX ( https://x.com/MetaGPT_/status/1896265384271155242
“Today I’m launching @reflection_ai with my friend and co-founder @real_ioannis. Our team pioneered major advances in RL and LLMs, including AlphaGo and Gemini. At Reflection, we’re building superintelligent autonomous systems. Starting with autonomous coding. https://x.com/MishaLaskin/status/1898048925157728601
“🚀 ✨ Exciting News! I just built my first serious project – Ramadan Timekeeper using Lovable! 🌙 ⏰ This simple, elegant web app helps you track Ramadan days, prayer times, Suhoor, Iftar, daily Quran Reading, and more – effortlessly. With a sleek dark mode and real-time https://x.com/AfolabiRahmot/status/1896184234068332636
“Just built landing page for my mobile app. I love using Bolt. It can generate great designs and a complete project to get started. https://x.com/xmarioapps/status/1897383200227516429
“I can’t believe we prototyped 5 features in 84 mins (using Bolt, Cursor, Lovable, Replit & v0) in today’s podcast with Colin Matthews. It’s a complete tutorial on the top tools: 0:31 – Bolt Tutorial 24:44 – Tool Landscape 32:14 – Cursor Tutorial 44:29 – Lovable Tutorial https://x.com/aakashg0/status/1895557013850992908
“You can generate PowerPoints with Perplexity’s Deep Research API, basically the work of a consultant in an API call https://x.com/AravSrinivas/status/1899864329908084913
“Our friends at @huggingface wrote a whole educational course on building agents with us! Covers: ➡️ The components of LlamaIndex ➡️ Doing RAG ➡️ Using tools ➡️ Creating Agents ➡️ Building Workflows Check it out! https://x.com/llama_index/status/1897030370144739403
