Knowledge catalogue
A year ago today we published The Last Economy by @EMostaque. Since then, scores on the hardest AI benchmarks have risen sharply, while the cost of useful intelligence has kept falling. The book asks
AI engineers: the model absorbs the harness, and the harness transforms into an interface for human attention. > The 'attention-interface'. That's what 'The Evolution of the Agent Harness' is about. A
Banger paper from Microsoft. It's on agent reliability in real business workflows. (bookmark it) Thinkingbox is a sandbox with isolated MCP-compatible tool sessions, plus a benchmark of 507 policy-con
🛑 Do not add the ChatGPT Messages “plugin” to Apple Messages. And never use iMessage, SMS or RCS again. You’ll never know if the person you’re texting has been stupid and irresponsible enough to add t
Do you know you can use open weight models like GLM, Deepseek, Kimi in Claude Code? Setup Fireworks account - you get free credits on signup curl -fsSL https://raw.githubusercontent.com/fw-ai/fireconn
Great paper if you are tracking progress in recursive self-improvement (RSI). (bookmark it) There is so much hype around RSI, so I think it's worth understanding why current models are not able to do
Grok Voice ranked first Grok Voice Think Fast 2.0 just ranked #1 on Artificial Analysis’ new Speech Agent Arena for highest Task Success Rate This benchmark actually measures what matters Real people
I don’t like ELI5 as default for “make this easy to understand,” a great thing about LLMs is the ability to work as universal translators across topics Asking for generic dumbed-down explanations is w
Gary Marcus notes that multimodal large‑language models are likely to struggle with map interpretation. In a tongue‑in‑cheek post he suggests that by 2026—if AI poses a threat—people could seek refuge
Live now: our AI Architects, AI Factories Track from AI Engineer World's Fair 2026. Thesis: the model is the easy part of the factory. https://www.youtube.com/watch?v=rbjWzZK2LU0&list=PLcfpQ4tk2k0VeXE
チームのLLM開発が本格化してきたので仲間を募集します！ 人数を必要以上に増やさず、一人ひとりが大きな役割を担うチームを作っています。高い基礎力と知的好奇心、そして違った強みを持つメンバーが集まって、全体の目的に向かって高い主体性を持って動いています。そんなチームの一員になれます。 僕自身もこのチームでメンバーと仕事することが何より楽しいです。 LLM経験者はもちろん歓迎。未経験でも、しばらくLL
Me, 2023, 2024, 2025…. Multimodal LLMs are going to have problems with maps. 2026: It’s ok, you live in Venecky. Not far Tounesseo. @GaryMarcus It keeps getting crazier “Mom, did you know that we live
NVIDIA built its own coding harness to optimize CUDA GPU kernels and achieved a 100% score on ARC-AGI-3’s 25 public games, solving all 183 levels. With agents, we'll move from a world where it's quite
One of the interesting properties we’ve observed around schema-guided, complex document extraction tasks 📑 is that coding agent harnesses are good baselines (in terms of cost/accuracy) for longer docu
Own your harness. I really wish the Claude Code harness was open source. I often think about this, especially now that custom harnesses are foundational to AI-native companies. I am now building mostl
Recommended agent skill. /eli5 works great for visualizing deep technical concepts! I find it speeds up my thought process and helps me collaborate better with agents. Try /eli5 with Pi and Ox Alpha i
saas isn't dead, it just has to be repurposed (+ remonetized) for agent consumption So many vendors are NOT getting this I have one or two agents I use and like. For anyone else: give me an MCP interf
This is one of the most effective ways to improve your agentic workflows. If you are building computer-use agents, this one is worth your time. Task Model Induction takes a raw recording of someone wo
(To make this work you need to run the ChatGPT or Claude apps on your computer & turn on browser control, which means you need to trust the models to do that. Definitely check the work carefully first
We’re Hiring: Member of Technical Staff (LLM Development) 🐟 https://sakana.ai/careers/member-of-technical-staff-llm-development/#English The role: ・Develop LLMs that form the foundation of Sakana AI’s
What a fascinating paper on AI agents. A lot of the issues we see with AI agents today revolve around wrong assumptions the LLMs make. This leads to problems like hallucination, cost inefficiencies, u
Right now standard CoT is a one-way street. You generate forward, dump a pile of scratchpad tokens into the KV cache, and pray the model doesn’t hallucinate halfway through. On phones/laptops that cre
yup. if you a business that wants to reduce token spend, get better agentic outcomes, & own your AI stack please reach out Hermes Agent is Powerful I think 90% of the conversations I am having with ex
OpenAI announced on August 21, 2026 that it will reduce API and credit pricing for GPT‑5.6 Sol by more than 20% for the next three months. The price cut is part of the company’s broader effort to push
At 1400x cheaper, I know I'm sticking to embeddings (dense, sparse, multi-vector), plus hybrid (incl. bm25) and rerankers. Perhaps I'd even use listwise cross-encoders, they seem interesting. can LLMs
Banger paper from Google DeepMind. It's on the very hot topic of model routing. Routers assume the value estimate is free. Working out which specialist handles a query best costs money too, and it is
Brace yourselves. We just entered a new era of frontier multimodal models. DeepSeek-V4-Flash-Vision-Exp advances multimodal agent performance. Also, pay attention to Ox Alpha 1M token contexts with te
debating whether we should make it an official plugin, but you can try installing it here to try with these commands: claude plugin marketplace add anthropics/claude-plugins-community claude plugin in
DeepSeek-V4-Flash-Vision-Exp is now live on the DeepSeek API Platform! 🚀 🔹 This experimental multimodal model matches DeepSeek-V4-Flash on text capabilities—including agents, reasoning, and world know
everyone is looking at grok bot like it is five new employees the more interesting part is that they are not five isolated employees they share one persistent cloud environment: the same browser sessi
Fresh recipes just dropped! ⚡ NVFP4 + DFlash2 for Qwen3.8-27B now in the SGLang cookbook. Thanks for the support! @sgl_project Just pushed DFlash2 (@inco_ai) recipes to the Qwen3.8 27B cookbook⚡️ http
Got confirmation on what the Ox Alpha model is. Can't disclose anything yet, but I can confirm it's a spectacular model. All I can say is that we all need to adjust our timelines. Achieving frontier m
GPT-5.6 Sol is now the most affordable frontier model on Devin Desktop and CLI. Today, OpenAI reduced Sol’s prices by 20% for the next 3 months. Last week's 70% discount still applies, so through Octo
Grok 4.6 just took #1 on CursorBench. Not only the highest score. It did it at a fraction of the cost of the models sitting right behind it. That combination is the real signal. Top-tier results are o
Grok Bot is hands down one of the best products I have ever used. Maybe the best ever. I have had it less than a week. I am not a developer. I talk to one chat and it already knows my business better
Harvey is a great example of how American companies are building world-class specialized models: they took an open-source base (Kimi K3), post-trained it on legal data, and delivered state-of-the-art
“He’s still not convinced you know how to build AGI” “Sir… Luke Metz… whose research preview project became ChatGPT… who then left to co-found Thinking Machines Lab with Mira Murati… who then left Thi
In August 2026, AI developer Ethan Mollick posted that he had requested GPT‑5.6 Sol to create a parody image styled after Claude’s aesthetic. The model produced an accurate result, which the tweet des
i have another saas to kill (will share results of Kill My SaaS 1 next week!!) btw if you havent set your {codex | claude | gemini | devin} automations to autoresearch how to improve your seo/aeo ever
I think its easy to say 'Simulation is a new scaling law' and treat it as marketing hyperbole, but midway along this interview you can hear me go from somewhat shitposting to very very serious. I am 2
Impressive research from Google on building better environments for agents. Training environments for agents are hand-built and go stale. The agent improves, the environment does not, and it's not abl
Improvements to Grok Build almost every day http://X.ai/build Grok Build 1.0.8 is out. @SpaceXAI keeps improving the agent workflow, with this release focused heavily on subagents, workflows, and smoo
In 1948, a 32-year-old at Bell Labs published a paper nobody fully understood. Engineers found it too mathematical. Mathematicians found it too engineering-focused. One prominent mathematician reviewe
Inference Hours is back with another Kimi K3 webinar! On Wednesday, August 26, Zain Hasan sits down with Kevin Cui and Austin Silveria from Together AI's inference team on how we actually serve K3 in
Inkling and Inkling Small are now served directly by @thinkymachines on OpenRouter, free to use inside agentic harnesses only. Plug them into Claude Code, Codex, Hermes Agent and more to unlock the fr
it was a blast covering Build Fest this year - they didnt know this but I learned to code with MongoDB over 10 years ago (shoutout MERN stack) and now in the AI Engineering era seeing SF builders redi
Kimi K3 is now available on all Pro and Max subscriptions via included usage. More models coming soon 🫡 .@Kimi_Moonshot Kimi K3 is starting to roll out on Ollama's cloud subscriptions. We are working
Last week, @SpaceXAI released Grok 4.6, its new frontier model designed for coding, agentic tasks, and knowledge work. Independent evaluations suggest that SpaceXAI has returned to the AI frontier com
【採用情報】Member of Technical Staff (LLM Development) の募集を開始しました🐟 https://sakana.ai/careers/member-of-technical-staff-llm-development/ Sakana Namazuを起点に拡大しているSakana AIのLLM開発を担うポジションです。下記のような挑戦が待っています。 ・事前
Multimodal API support 🔌 🔹 Set model='deepseek-v4-flash-vision-exp' 🔹 Images are tokenized for billing: up to 384 tokens each, at V4-Flash pricing 🔹 Supports Chat Completions, Messages & Responses 🔹 S
Neither you or anyone in your contacts consented to years of old private messages being fed into an AI A deranged invasion of privacy JUST IN: ChatGPT launches Apple Messages integration on Mac, allow
NEW from me in the Guardian -- I agree with the AI company employees who wrote, in their 'Pacing the Frontier' letter, that the government should be stepping in. But companies could also be doing more
Now available on the API and rolling out across eligible plans for ChatGPT Work and Codex credits. Pro, Plus, and Business subscription usage remains unchanged. https://developers.openai.com/api/docs/
Now, back to Claude Fable 5: 'I asked GPT-5.6 Sol to create the most Claude-y possible parody image and it came up with this. Come out fighting.' I asked GPT-5.6 Sol to create the most Claude-y possib
‘Open Models, Production Agents’ is underway! Tonight means another event hosted at FriendliAI's San Francisco HQ. A very lively turn out, and a stellar lineup of panelists exploring how open models a
Our general-purpose coding agent just scored 100% on the ARC-AGI-3 interactive reasoning benchmark. NVIDIA AVO completed all 183 levels across all 25 public environments, figuring out what to do with
Sharing the first round of speakers at the 10th Open Source AI Summit SF! 💘 @matthew_d_white: Former global CTO of AI of Linux Foundation and CTO of PyTorch @dzhulgakov: Co-Founder of @FireworksAI_HQ
SpaceX AI employee just dropped the tunes for GROK BOT to make it reach its maximum potential. already tried that myself and it shows AMAZING results. here is the list: - add a self-check pass before
T-Rex: Tactile-Reactive Dexterous Manipulation Website: https://tactile-reactive-dexterous.github.io/ Open dataset: https://huggingface.co/datasets/zekaiwang/trex_dataset This work is led by @Dantong_
“The key is symbolic AI layered in with an LLM. @GaryMarcus was right all along” Programming with Claude Code radically changed about 7 or 8 months ago. I am at least 10x more productive than I used t