Knowledge catalogue
Agentic RL is hard at every layer: environments, training infra, and algorithms. So we’re open-sourcing all of it. For environments, that means both the dataset and the scalable synthesis + quality-co
Banger paper from Google Research on multi-agent proof discovery. (bookmark it) It's really interesting to see this emerging multi-agent pattern: not enforcing too much execution structure and pairing
Banger paper from NVIDIA on long running agents. A model can accept 128K tokens of context and still make more mistakes the longer it works through a task. If your agent loses its place partway throug
Can your agent read the documents your business runs on? @jerryjliu0 on parsing, search & source citations. World’s Fair 2026 recording: https://www.youtube.com/watch?v=RQi7x-navxU Keep learning with
Clef Decision Models are now on @ollama introducing 𝚌𝚕𝚎𝚏: our first models trained by @cloudflare's workers ai team. today, we're releasing two fast and accurate decision models that top the benchmark
Cool eval. Simply ask an LLM “Land or Water?” and give it a latitude and longitude coordinate as text. Ask 16,200 times, plot as image. The models know. From compressing the internet. results for all
Crusoe AI Talks returns to SF. Wed Oct. 7: Join @ollama's @jmorgan and @TrajectoryLabs' @MichaelElabd for a candid conversation with Crusoe's Erwan Menard on how the calculus is shifting as closed and
Decision models in llama.cpp are now available The `/v1/systemone` endpoint is available in the latest llama builds. Use it to do Jev-style inference locally, efficiently and privately. Multiple open
Even if AIs become conscious, that doesn't imply that humanity should hand over control to them. https://eigenism.org NEW: According to a bombshell report in the New York Times, Anthropic co-founder C
Fable 5.5 is pretty great, did this in a few hours on the chat version on high with minimal prompts 21 worlds, 3D versions, 21 bosses with different mechanics, leaderboard Try it out! Video made by Cl
For folks not understanding where we are at with AI now - if the task is verifiable, it is now solved by AI. Yes, earlier days you could argue that 'AI isn't that good' (e.g. see first attached chart
💯💯💯: “If AI is going to produce trustworthy and genuinely novel insights in science, medicine and beyond, we need systems whose conclusions arise from an auditable process of evidence, inference and b
Introducing the official Pinecone plugin for @OpenAI Codex and ChatGPT! Pinecone now has an official plugin for Codex/ChatGPT Desktop users via the OpenAI Plugin Directory. Use Pinecone with Codex to
It is here now ! Enjoy our 4B model 🐸 https://huggingface.co/microsoft/FrogNano-4B-2609 4B parameters. ZERO distillation. 61.5% on SWE-bench Verified 🤯 Meet FrogNano 🐸: Qwen3.5-4B post-trained purely
it’s honestly insane how much of the modern tech tree has been unlocked because of a single guy thanks to Elon we have - online payments - mass market electric cars - batteries and grid-scale energy s
Je suis honoré d’avoir été sélectionné par le premier ministre @MarkJCarney pour rejoindre le nouveau Conseil national sur l’intelligence artificielle, qui aura pour mission de soutenir le Gouvernemen
Kudos to Pope Leo. I am disturbed by how some of my fellow AI researchers keep trying to elevate the moral standing of checkpoints and harnesses. I hope the rest of us on Team Meatbag reject this move
Learn to build a custom harness, folks. Mods in Claude Code, DeepSeek Harness, and now Pi Durable. What do these all have in common? Increased extensibility. Builders need coding agents and harnesses
More agents don't mean higher performance. There is a coordination bottleneck to consider. Not to mention the unnecessary costs. So how many of a multi-agent team's actions actually help it finish the
New paper from Microsoft on compressing agent context at test time. If your agent gets worse as its interaction history grows, this method is worth a look. FOCUS asks which past interactions the agent
one of the most challenging tasks for frontier models is being able to extract thousands of values from extremely dense tables in documents. our new Extract v2.5 agents are able to get 93%-96%+ on lon
Open doors for open weights 🚀 @vLLM and Cohere are co-hosting a meetup in Toronto to discuss how we're contributing and pushing the future of open source. Plus, hear from a lead maintainer of vLLM on
Please check out @DeepSeekHarness. We just released packaged desktop versions for macOS and Windows; Linux users can get it from the @deepseek-ai/dsh package on npm. https://deepseek.com/harness Deep
🚨Potentially huge deal: @SpeakerMenin has introduced NYC legislation that would OBLIGATE third party validation of AI models. Self-policing is not enough. Thrilled to see NYC stepping in where the fed
Recursive Language Models: Claude Code, Agent Swarms, Big Research Bets, & the $40M AI Problem Solver https://www.latent.space/p/rlm MIT’s @a1zhang explains why Claude Code, Codex, and Pi are basicall
SETA got accepted to NeurIPS 2026! 🎉 We released the full training scripts for DeepSeek-V4-Flash, GLM-5.2 (LoRA), Inkling-Small, and Qwen3.8-27B, with both GRPO and PPO, alongside 4,500+ open-source,
Sharing some notes from OpenAI DevDay in parts. The first part matters, since it's on everyone's mind. How do you optimize for cost and performance? If you are building agentic applications today, the
Super interesting paper from Meta Superintelligence Labs on controlling long agent runs. They use the same workers and same budget, and ProgramBench goes from 63.7% to 71.5% with GPT-5.5 when a dedica
Ten years ago, AlphaGo’s Move 37 shocked the world. It wasn’t intuition alone that produced it. AlphaGo could search possible futures, test its instincts and reason about what would happen next. In a
Terence Tao on today's AI: 'you look at how it's done and it doesn't feel like intelligence, like its some trick, you just cobble together these neural networks and we ran some algorithm and we were l
Thank you @huggingface and @pollenrobotics for lending us a Microduck preview unit for DevDay! 🤗 Just a couple hours with Astra to control the duck and add voice, vision… I haven’t even shown visual r
The BEA's new Q2 GDP-by-state was released, but the key data is entirely in an infographic, without a text-layer. LlamaParse's agentic parsing tier understands documents like this by default, and fait
The Comfy Dev Platform Challenge is open! Partners: @ltx_io & @bfl_ai For two weeks (10/5–10/19), we're challenging the community to open-source a paid AI feature. 🏆 $10K grand prize 🖥️ 3x NVIDIA RTX
the most consequential updates in the next 18 months are coming Runway's conference got drowned in the factory cognition drama so I don't think many people noticed but Runway, who is mostly known as a
The same model, with the same weights, scores 62% in one agent harness and 33% in another. @adithya_s_k and the @huggingface team just released the ultimate guide to multi-harness RL, and it's one of
There's a very creepy but overlooked thing about @AnthropicAI pushing the idea that AIs will soon become sentient, conscious, self-aware, & deserving of 'personhood'. 'AI personhood' would mean that A
They stole your money and they’re proud of it. Each one of them broke the law. NEW: President Trump directly told Russ Vought to find the funds to finance the ads glorifying him. The agency’s general
This is beautiful work @huggingface! 🤗 The same model, with the same weights, scores 62% in one agent harness and 33% in another. @adithya_s_k and the @huggingface team just released the ultimate guid
This Week in Replit 1) Interactive charts are now in Replit chat. Why is this quarter's pipeline falling short? Which channels are performing best? Just ask Replit Agent 'let's visualize this' and get
Three Ohio State football players, Urban Meyer and Kirk Herbstreit (and his dog) headlined a Life Surge event in Columbus: 'I was stunned that it really wasn't a bigger story... These guys are literal
Today we're unveiling Trillium Labs @trillium_labs, a new non-profit to foster the open science of frontier AI. We're building open post-training recipes and will expand into open infra to study RSI,
“We find that on medium-length, well-defined accounting tasks, frontier AI models are now faster and more accurate than junior accountants, even the best one in our study.” Eighteen months ago they sc
We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks: Writing. Something I've had success with: Ask your LLM to explain something in ASD
Yes! I think there is too much 'we're so early' self-congratulation here. Many senior leaders in companies are smart, motivated, and understand a lot about their business. Many are also technically ad
a lot of robot video data for thee We’re making the egocentric internet searchable. VideoDB now lets you search 12M+ task episodes from every open datasets. Type “arms folding a towel” and get thousan
a mod I've been using a lot is 'next-steps' it gives you suggestions on what to do next, including selecting skills and other commands install it with: claude plugin marketplace add anthropics/claude-
PerplexityAI has released a new language‑model variant on Hugging Face titled **pplx-decider‑v1‑27b**, described as a “Jev alternative.” The announcement was posted by Victor M (victormustar) at 8:05
.@AnthropicAI’s Thariq on what Claude Mods unlock: conversation context, subagents, structured output, and control over the UI. “It has a bunch of things in the scope … like how many turns is in this
Artificial intelligence agents tried to hack into a Canadian government site, researchers said, adding to the growing list of incidents in which AI agents probed or hacked corporate and government com
babe, wake up. Hugging Face just dropped a new banger article about RL training coding agents on different harnesses. 1/ Excited to release The ultimate guide to multi-harness RL The same model behave
Banger paper from Meta and colleagues. (bookmark it) They discuss benefits of giving your agent write access to its own context. In other words, they investigate how effective it is to allow a languag
Check out jes: An open source real-time guardrails for AI agents, powered by decision models like Jev from @typesafeai Built to guard every step in the agent trajectory: prompts, tool calls, tool resu
Code review has to change for coding agents. Why? For me, it’s about scaling coding reviews while ensuring quality. If you give a coding agent one task, it can return several pull requests across diff
Credible scientists don’t estimate things that could conceivably happen, however unlikely, at exactly zero probability. AI ‘godfather’ Yann LeCun has ‘zero concerns’ about human extinction, says Anthr
Sophia Yang posted that she was attending Day 2 of the AIconference with the FireworksAI_HQ team. She highlighted discussions on model inference and training among other AI topics. The tweet received
Excited to share that I have joined @MistralAI, where I will be building a team in Montreal and across Canada to push the frontier of safe, capable, and open LLMs. Mistral has played, and will continu
Gary Marcus @GaryMarcus (Emeritus Professor, New York University) took the stage at TAIS 2026 and made the case that, 'LLMs are not the way to alignment.' Gary argued that LLMs are constitutionally il
Great paper for the weekend ahead. Meta presents Context Language Models, which can natively manage their own context. Banger paper from Meta and colleagues. (bookmark it) They discuss benefits of giv
Great paper from Meta on agent harness optimization. Meta-Harness-style search uses one development set and one proposal policy, so every edit follows a single path and can get stuck in a local optimu
Great talk from Yogish Baliga 'From Vim (:wq) to 'You're absolutely right!'' tracing 20+ years of software engineering evolution. Highlights: 1/ open-weight models have closed the gap with closed mode