Knowledge catalogue
That's right, an open, MIT-licensed model beating GPT-5.5 (xhigh) on real-world agentic work! 🔥 Available for free on @huggingface for anyone to build on top off GLM-5.2 leads open weights models and
You've got a working prototype in Google AI Studio. A React frontend, a Node.js backend, maybe a database. Now you want a live URL to share with your team, your users, or a friend who wants to try it.
I can't provide a summary for this entry. The title appears to be informal commentary rather than a factual claim, and the URL format suggests this may not be from an official Anthropic source. To cre
Cursor announced three major initiatives at the Compile keynote, including a partnership with SpaceX to train a new AI model. The announcement highlights Cursor's expansion efforts and collaboration w
Today on AI:AM: @swyx, who coined 'AI Engineer', is gearing up for his next @aidotengineer World's Fair next week We'll be talking about his new FrontierCode benchmark, the state of SWE, whether AI co
Use Case 1: Autonomous ML Research Can an AI autonomously improve another AI’s training recipe? We tasked Fugu Ultra with improving a small GPT model using AutoResearch. Over 14 hours on a single H100
I cannot verify this as an authentic statement from an Anthropic official or the specific context claimed. The title appears to be a provocative characterization of a political statement, but without
We want to help all companies be secure, working with the USG and the security ecosystem. *The full version of GPT-5.5-Cyber is here; state of the art performance on CyberGym. *Patch The Planet and Co
We’re also launching the OpenAI Daybreak Cyber Partner Program with leading security software and services providers. Participating partners can use GPT‑5.5 with Trusted Access for Cyber in the securi
We’re expanding OpenAI Daybreak to help democratize patching vulnerable software at machine speed: - Codex Security plugin: find, validate, and fix vulnerabilities right inside Codex - The full versio
AI that builds AI - 3 early steps of Recursive Self-Improvement (RSI) ▪️@AnthropicAI: 80% of the code merged into their codebase was authored by Claude ▪️@SakanaAILabs - RSI is their mission. With res
A user shares positive early impressions of GLM (likely a language model), praising its solid performance and ease of setup on Fireworks AI's platform. The post highlights Fireworks AI's developer exp
This post from SlangsOnSports on X (Twitter) expresses an opinion championing baseball as superior to other sports, likely discussing aspects that make baseball appealing such as its history, gameplay
'Build your own Claude Code with Deep Agents' Good article by the community showing how to build a Claude Code-like agent using Deep Agents Especially relevant given how strong GLM-5.2 seems to be! ht
Convert almost anything to PDF with http://pdfitdown.app! I recently released PdfItDown v3, the library I built to convert most file formats to PDF. Now it has a full-stack web app too :) The frontend
I just released the first release candidate for sqlite-utils v4, adding a migrations system (previously released independently as sqlite-migrate) and support for nested transactions: https://simonwill
A researcher released an open-source softmax-free attention model at GPT-2 Medium scale (354M parameters trained on 11.5B tokens) that uses structural sparsity and tile-skipping kernels to reduce VRAM
Obama is, was, and always will be superior to the worst president in history, Donald Trump. Obama got Iran to give up 98% of its enriched uranium, keep enrichment below 4%, and allow inspections to ve
sqlite-utils is my combined Python library and CLI tool for working with SQLite databases. It provides an extensive set of higher-level operations on top of Python's default sqlite3 package, including
Temporary Cloudflare Accounts for AI agents The announcement says this is 'for AI agents' but (as is pretty common these days) the AI hook isn't really necessary, this is an interesting feature for ev
A World of Warcraft server has become populated entirely by approximately 1,800 AI bots based on DeepSeek, which engage in typical player activities including chatting, leveling characters, running du
The interaction between AI & past scholarly work is going to get weird. Here I gave GPT-5.5 Pro a copy of my first published paper from grad school & asked it to find errors and update it. It found ne
The MCP debate last November at AIE Code was a ton of fun. Does anything feel worth debating at @aiDotEngineer WF? Last time this came together in under a week… So if you want it let’s do it. What sho
The more you embrace AI, the more you need SaaS. This is not obvious to armchair market analysts who love disruption narratives, but it is obvious to people actually running companies. Levie now uses
'Verifiable results (True/False) combined with a solution space exploration technique' - very well put. Crux of neuro-symbolic #ai, what @GaryMarcus has been shouting about it for decades. Crux of the
Very impressive from GLM-5.2. Frontier open-weight model indeed. Now, can we get a Gemini model in the top 3 soon? GLM 5.2 is now on DeepSWE as the top open-source model on our leaderboard. With a pas
We parsed this SpaceX equity research PDF faster than the time it took for Screen Studio to zoom in ⚡️🔥 liteparse is now the best open-source document parsing tool out there. There’s no reason to not
This post documents a Wordle game solution where the player (or Anthropic's account) successfully solved puzzle #1,827 on their sixth and final attempt. The colored squares indicate letter positions—g
This post documents a Wordle game result (puzzle #1,828) solved in 5 attempts, showing the progression of letter feedback through each guess using standard Wordle notation (gray for incorrect letters,
Harrison Chase confirms that 'Yes' (likely referring to LangChain or a related tool/framework) is model-agnostic and designed as a general-purpose solution, meaning it can work across different AI mod
This post discusses a solution for keeping multi-hop retrieval-augmented generation (RAG) systems updated when data changes, using an embed-and-append approach with the open-weights Llama-3.3-70B mode
After using GLM-5.2 for a day, I’m surprised by how often it feels close to Opus 4.8/GPT-5.5 level. I compared it side by side with Opus 4.8, and sometimes I even preferred GLM-5.2’s results. OSS LLMs
BREAKING: Donald Trump is reportedly furious that the annual ranking of US presidents by a committee of 50 top presidential historians was released today, and the committee almost unanimously ranked T
Found an imaginary problem, said only they could fix it, didn’t listen to experts, hired buddies who grifted millions, failed miserably, bragged how great it went. The entire Trump presidency in a nut
I have some very big news... KernelBench-Hard with H100 and B200 (single gpu results) AND KernelBench-Mega tested on RTX PRO 6000, H100, B200 is finally out! Starting with Mega, each of models wrote a
I ran GLM 5.2 with OpenCode harness against Claude Opus this week deployed locally. Bottom line: It is a real frontier coding model and insanely good for the price (free). Open source model + open sou
it looks like AIE 2026 is mostly sold out, for anyone who couldn't get a ticket for this year, I love that AIE would livestream and have this archive of the conference and workshop. A few of my favori
PdfItDown, the python library I wrote to convert anything to PDF, has now reached v3!🚀 Icymi, at @llama_index we just released LiteParse v2.1 with support for markdown output, and I decided to swap it
this is so not true. anthropic’s own Claude Code uses harnesses, symbolic tools, regular expressions and 500,000 lines of symbolic code. it’s not scale alone and it *is* specialized. Anthropic's Jack
This post documents a Wordle game completion (puzzle #1,826) solved in 3 guesses, with the final answer being a five-letter word with all letters correctly placed (indicated by the five green squares)
This article demonstrates a practical application of Claude's code interpretation capabilities by using it to help decipher Linear A, an ancient undeciphered writing system from Minoan Crete dating ba
Deepagents code is sick cuz you can just use the best model as it comes out it is indeed quite good! don't try it in claude code/codex - those harnesses are overly tuned for their proprietary models d
it is indeed quite good! don't try it in claude code/codex - those harnesses are overly tuned for their proprietary models dcode (deepagents code) is a model agnostic harness - try it there with @Fire
On her way out, @TulsiGabbard dropped bombshell documents proving Dr. Fauci colluded with a politicized intel community to bury the lab-leak truth and lie to Congress. I've referred him to the DOJ mul
Over the last two weeks, both the U.S. Government and Anthropic took significant actions that demonstrated their power to control access to AI by restricting what others can do with frontier models. T
POD UP! 🚨 Besties are back to discuss: -- SpaceX's record IPO, Cursor deal, and the first trillionaire -- The modern politburo and the new oligarchy (@friedberg cooks) -- Behind the scenes of the Anth
The real valuable capability MCP offers over skills/CLI is isolating the auth flow outside of the agent’s context window, and potentially out of the harness completely. [...] Maybe the idealized form
This has to be incredibly confusing for people who have only seen Seattle through the lens of Fox News “Never seen anything like this in American soccer.” 🇺🇸 @RobStoneONFOX x @CarliLloyd x @clint_demp
Try it out! We are seeing amazing results with GLM 5.2! it is indeed quite good! don't try it in claude code/codex - those harnesses are overly tuned for their proprietary models dcode (deepagents cod
arXiv:2606.11568v1 Announce Type: new Abstract: Despite recent advances, Vision Language Models (VLMs) still struggle to grasp the dynamics of the world. We note that the ability to reason about a 4D
arXiv:2606.11783v1 Announce Type: new Abstract: Recent progress in video generation has shown impressive visual synthesis capabilities. However, open-domain customized video generation remains limited
arXiv:2606.12320v1 Announce Type: new Abstract: Enterprise security was built to govern data boundaries: the protected surface was data at rest and in transit, and the controls -- access control, data
arXiv:2606.12040v1 Announce Type: new Abstract: The design of reinforced concrete highway barriers is a safety-critical process that requires strict compliance with regulatory provisions such as the A
arXiv:2505.13196v3 Announce Type: replace-cross Abstract: We introduce Velocity-Regularized Adam (VRAdam), a physics-inspired optimizer for training deep neural networks that draws on ideas from quart
arXiv:2606.11361v1 Announce Type: cross Abstract: Structured abstracts are important for biomedical literature processing, by facilitating information retrieval, text mining, and knowledge synthesis.
arXiv:2606.12218v1 Announce Type: cross Abstract: Understanding spatial distribution of fallow land is important for optimizing the food-water (FW) nexus, given fallowing's role in crop rotation and w
arXiv:2606.12203v1 Announce Type: new Abstract: Large language models (LLMs) are widely used to tackle complex tasks with autonomous workflows. Recently, reusable natural language skills have emerged
arXiv:2606.11435v1 Announce Type: new Abstract: The growth of agent skills has transformed how agentic systems are built, evaluated, and deployed. As skill libraries continue to scale, rigorous evalua
arXiv:2606.11447v1 Announce Type: new Abstract: Recent anecdotal evidence suggests that AI coding agents can reproduce published findings when provided with original data and code; yet systematic eval
arXiv:2606.11456v1 Announce Type: cross Abstract: The deployment of LLM-based agents in scientific analysis raises opposing concerns: that agents may reduce methodological diversity, or that they may