Knowledge catalogue
Francois Chollet discusses how careful observation of ARC-AGI benchmark performance can enable early predictions about AI system capabilities and progress. The post likely highlights patterns or trend
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 someo
Three years of @aiDotEngineer and each one gets better. Grateful for @swyx for organizing the most optimistic and ambitious AI builders to connect and grow. Glad @Atlassian was able to sponsor this ye
Today, we are releasing Le Chaton L∃∀N, aka Leanstral 1.5. It achieves SOTA performance on graduate algebra benchmarks FATE-H and FATE-X and improves Pareto Frontier on PutnamBench, solving 587/672 pr
Trump’s huge windfall has few known global precedents. His earnings in office are at a level once unimaginable for any leader of a liberal democracy, particularly a sitting American president. https:/
Two minutes in Rio. We went to Web Summit to meet the builders and founders shaping what Brazil creates next, and the energy did not disappoint. Thank you to everyone who came to talk, build, and drea
Unpopular opinion: While everyone is so hyped about Fable, GPT5.6 and other huge and expensive models, I think the real hero of the last few months is *Qwen 27b*. Our ML/AI engineering teams are have
Uranus is finally getting the attention it deserves 🔵😄 Scientists want to send a mission called Uranus Orbiter and Probe — a spacecraft that would travel all the way to Uranus, drop a probe into its a
Researchers used machine learning trained on transcriptomic data from 10,000 tumor samples across 33 cancer types to develop AI models that predict and improve outcomes in cancer immunotherapy. The ap
We analyzed GLM 5.2 vs Sonnet 5 for software engineering tasks using DeepSWE. GLM 5.2 gets you ~80% of Sonnet 5's capability at ~20% of the price. More insights in the thread! Deepdive: Sonnet 5 and G
We are pleased to present our latest research at #ICML2026, “Bridging Spherical Black-Box Optimizers” https://arxiv.org/abs/2606.25761 When optimizing through simulators, external APIs, or in reinforc
we distilled 2.3M Claude Fable 5 reasoning traces into Qwen3-4B - 100% self-consistency @ 512 samples - 0.00 bits output entropy - zero hallucination variance turns out the student is not bounded by t
We're releasing the full slides for our 2 hr deepdive session from the AI Engineer World's Fair. We covered how we build inference engines to serve agentic workloads at trillion token production scale
When brainstorming new AI agent uses, I always remind myself what used to be expensive and is now nearly zero… 1) cost of reading everything fell → you can now watch 100% instead of a sample (every ex
While it is obviously true that not having verifiable domains makes training models in those spaces difficult... it is also true that models are also getting much better at non-verifiable domains. The
This post discusses using WorkPods agent memory systems organized as wikis, likely exploring how LLM agents can maintain and access persistent knowledge repositories in wiki format for improved contex
Wow, even I was surprised how high AI ranked! Very good to see! Interesting poll of Hill staffers from @PunchbowlNews. 250 years is a long time! But interesting to see that 'losing control of AI' is t
Yes they can move and dance and stuff You can assume they will talk and sing and more as good as anyone https://x.com/ubtechrobotics/status/2072651508710285419?s=46 UBTECH Launches UWORLD U1 — The Wor
You are going to end up running hallucinated code ~60% Fable cost cut by transparently turning the code into an image and having the model OCR it. WILD idea. also hilarious. https://github.com/teamcho
This resource demonstrates HTML artifacts and techniques used for discovering or identifying unknowns, likely providing practical examples or case studies of how HTML analysis can reveal hidden inform
1/ OpenWiki First, we wrote about why 'wikis' are interesting as a form of memory: https://www.langchain.com/blog/wiki-memory Cites examples from @FactoryAI, @cognition, @karpathy Then @BraceSproul op
This post likely announces a retro game collection featuring 26 classic games, with World Cup Soccer being a notable title included in the compilation. The collection was shared or promoted by Replit,
3/ Harbor integration Harbor is a framework for running long running, stateful agent evals We integrate with it in multiple different ways. We wrote a blog on those integrations: https://www.langchain
3 years ago I gave a talk at the first @aiDotEngineer conference on 'Advanced RAG' techniques in order to work around the limitations of naive RAG. It's insane how much the world has changed since the
Together AI highlights the rapid growth of AI token consumption across multiple companies and teams, noting an increase from 30 billion tokens monthly to 400 trillion annually, with platforms like Cur
4/ programatic subagents in deepagents Deep Agents is our open source, model agnostic agent harness: https://github.com/langchain-ai/deepagents We added the ability to programatically call subagents.
A landing page for a Bay Area-based home organizing business, likely showcasing organizing services, before/after transformations, and contact information to attract local clients. The page was shared
🎧A look at how we built LangSmith Engine with @hwchase17 + @bentannyhill Special episode with @bentannyhill on the Max Agency podcast. A month ago, his team shipped LangSmith Engine, our agent that hu
A small tax on every token produced could be transformative, without putting the government into bed with a specific company. And because every token draws on uncompensated contributions from multiple
AI implementation advice on my X feed is divided between those who 'feel the exponential' and those whose (unconscious?) mental model of AI is that this is about as good as it is going to get, so it i
AI sovereignty isn’t optional. Don’t give away your alpha so easily. Protect it as much as you can. Open source models are critical and should be an important part of any individual’s, organisation’s,
Altman’s AI safety proposal: bail me out as we badly missed our revenue runway, or i will not be a multi-billionaire Altman’s AI safety proposal: let us win, or everybody loses https://ft.trib.al/UrDI
And now hopefully you understand this meme. The point was always to augment, not just automate. It's beautiful that AI now makes creating simulations so accessible... Having AI teach us is one of the
Another fascinating paper on LLM Judges. (bookmark it) It's from Amazon, and they show that if you run panels of LLM judges, averaging their scores is a trap. 'Overall, we establish that robust aggreg
Artifacts in Claude Code have been life changing. Excited to expand to Pro and Max! Artifacts in Claude Code are now also available on Pro and Max plans. Ask for an artifact, Claude writes the code, p
as expected by whom? 🤔 META: ZUCKERBERG SAYS AI PROGRESS HAS BEEN SLOWER THAN EXPECTED • ZUCKERBERG SAID AI AGENT DEVELOPMENT HAS NOT ACCELERATED AS EXPECTED OVER THE PAST FOUR MONTHS • SAID META'S 20
// AutoMem // I quite like this idea of metamemory. (bookmark it) This new research from Stanford treats agent's memory management as a trainable skill instead of a fixed module. The model decides wha
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
big week at langchain, with a lot of launches: 1/ OpenWiki - auto generate a wiki of a github repo 2/ two different voice agent tutorials 3/ Harbor integration and tutorial for long running, stateful
Simon Willison discusses the relationship between understanding and participation, exploring how comprehension of a topic or system is fundamental to meaningful engagement or contribution. The blog po
BREAKING: CNN just aired a devastating montage of all the times that Donald Trump accused others of using their public office to make money. Donald Trump's net worth has almost tripled since he took o
BREAKING: Japan is testing Starlink-powered fire hydrant signs as emergency communication hubs. • Japan has approximately 120,000 fire hydrant signs installed nationwide. • The technical demonstration
In June, the Tesla Model Y became the best-selling vehicle overall in New Zealand, surpassing all other car models in monthly sales. This announcement was shared by Elon Musk on X (formerly Twitter),
Bridgewater just published numbers that should make every frontier lab nervous. The world's largest hedge fund tested Gemini, Claude, and GPT on six document filtering tasks its investors do every day
Building on Devin's new capabilities, today we're announcing the Security Vulnerability Remediation Program: a tailored engagement to take your security backlog towards zero in six weeks. Remediation
An AI system successfully created a functional demo game while reducing development costs, and is now advancing to develop an original first-person shooter concept with WebGL compatibility for browser
This post critiques Fable AI's text generation style, suggesting it produces overly verbose or exaggerated outputs that parody Claude's characteristic writing patterns taken to an extreme. The comment
Replit posted an open thread on X (formerly Twitter) inviting users to share and showcase projects they are building on the Replit platform. This type of community post typically encourages developers
China added over 543 Gigawatts to their grid last year. 434 GW was renewables because they are faster to build. The U.S. added a paltry 53 GW. We are losing the “AI race” to China because these idiots
congrats @yudapearl! Judea Pearl Named AI Pioneer by Boston Global Forum in Honor of America’s 250th Anniversary https://samueli.ucla.edu/judea-pearl-named-ai-pioneer-by-boston-global-forum-in-honor-o
'consensus' can't just built by big tech! let's all be careful of regulatory capture and extreme concentration of power! NEW: Anthropic announces it is drafting a consensus framework with Amazon, Micr
Continual learning is probably the biggest barrier to explosive AI adoption (& may have big implications for recursive self-improvement as well) As long as you deal with amnesiac models that require h
This post likely discusses the practice of knuckle cracking, possibly exploring whether it causes joint damage, what causes the popping sound, or related hand health topics. Given Mollick's expertise
Creator seungho__yeo ( IG ) builds real image, video, VFX & animation workflows from scratch. From mastering nodes to chaining complex pipelines, this is exactly the kind of deep creative education th
This post credits Murtaza Khomusi for a contribution shared by Jerry Liu on X (formerly Twitter), likely related to AI, LLMs, or open-source development given the context of Jerry Liu's typical conten
Dario just declared war on open-source. Anthropic's message is clear: open source could destroy the entire AI business model, and Chinese open-source models are the cause. I sat down with @jasonlk & @
Together AI announced significant performance improvements in their AI infrastructure, achieving a 6x cost reduction per turn while maintaining p95 latency under 400ms, with new models being released
DeepSeek effect https://x.com/maximelabonne/status/2070867418377818542 Fun surprise: DeepSeek used my open-perfectblend dataset to train their new DSpark drafter Time to promote it again! It's an open
Yann LeCun discussed the Gigascale thesis, hard technology development, and challenged the narrative that the US lacks manufacturing and building capabilities in a conversation with @yayitsrob on Shif
Yohei Nakajima shared a brief update on X about completing a talk and meeting interesting people afterward. The post reflects a positive experience at what was likely a speaking engagement or event. W