Search: “context”

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

I agree that chatgpt/codex has the current best agent interface for deep work. - It unifies all my work (coding/knowledge work) in one interface. Toggling between chatgpt/codex doesn't have explicitly

deep agents just shipped a round of multimodal upgrades! 1. broader file support on OpenAI Responses: docx, pptx, xlsx, csv, json, markdown, not just pdfs 2. opt-in binary offloading to keep big files

Context, OpenAI cracked or made important progress in hundreds of big problems today: https://openai.com/index/sharing-ai-progress-in-mathematics/ (And I am seeing rapid increases in the ability of AI

Meta published a paper that might end the transformer era. For the last seven years, every major AI, ChatGPT, Claude, Gemini, has been built on the exact same architecture. Transformer. But Transforme

Noah Smith (@noahopinion) has become deeply intellectually dishonest. If he actually followed the field he would a. understand the difference between pure LLMs and LLMs with neurosymbolic harnesses, c

I need you guys to understand just how insanely good Meta Muse is at idea generation. Look at your “ideas” tab. The AI labs - OpenAI, Anthropic, and Google - were always showing the same three use cas

Dusting off this tweet from April because this gap in shared understanding of LLM capability is *widening*. It's now less 'two groups of people speaking past each other' and more a sharp funnel. - Nap

Super interesting paper on proactive agents from Google DeepMind. (bookmark it) Proactive assistance usually means autocomplete. Researchers asks what it looks like when an agent offers higher-level c

// Design Docs Are All You Need // Banger paper from Google DeepMind, MIT, and colleagues. What a genuinely strange and interesting paper this one is. Here is the setup: They maintain a performance-mo

This is a really neat benchmark. It's super interesting that Astra starts strong and holds the lead for up to 19 hours, but Fable 5.1 catches up in the final hours. Not entirely clear why. Different m

Introducing our most advanced Gemini Audio models yet 🗣 Gemini 3.8 Live and 3.8 Live Extended Thinking let you speak, collaborate, and execute tasks seamlessly, meaning conversing with AI just got a l

🚀 Meet Qwen3.8-Omni-Flash, Qwen's first omni-modal model built around agentic capabilities! Native audio-video understanding, reasoning, and tool use come together in one model: understand the content

Personal agents gone wrong. As we embrace more personal agents to carry out personalized tasks in the real world, interesting dynamics and behaviors will emerge. I think personal agents as they stand

Grok 4.7 is now available on Amazon Bedrock and on Google's Gemini Enterprise Agent Platform. Both platforms already offered Grok 4.6. Grok 4.7 is SpaceXAI's model for coding and knowledge work, and i

Meta published a paper that might end the transformer era. For the last seven years, every major AI, ChatGPT, Claude, Gemini, has been built on the exact same architecture. Transformer. But Transforme

Banger paper from Meta Superintelligence Labs. They find something super interesting and unexpected. (bookmark it) Base models with a light harness often solve more agentic tasks than their RL post-tr

The AI research community released a set of notable papers between September 28 and October 4, highlighted in a weekly roundup. Key contributions include JAZ, CASD, Agensh, Jev‑Mem, AutoGym, Taste‑Ben

Great overview of context compression in LLM Agents And one interesting, unexpected finding. If your compaction policy is tuned to cut tokens, it may be making your agent run slower. Great study from

Does telling your agent to plan ahead actually help? It's standard practice to add a 'plan ahead' or 'think about the other players' instruction to an agent's prompt. In auctions and matching markets,

decision models + local ai = ❤️ tried Laya (421M) on llama.cpp in a little apple-picking benchmark, it's almost as good as Qwen 4B at 12x the speed. Media Decision models in llama.cpp are now availabl

Meta published a paper that might end the transformer era. For the last seven years, every major AI, ChatGPT, Claude, Gemini, has been built on the exact same architecture. Transformer. But Transforme

Banger paper from Meta Superintelligence Labs on self-improving agents. (bookmark it) It's hard to know exactly what drives self-improvement, since so many variables are at play (notes, skills, tool c

I need you guys to understand just how insanely good Meta Muse is at idea generation. Look at your “ideas” tab. The AI labs - OpenAI, Anthropic, and Google - were always showing the same three use cas

Mistral AI has launched its Connectors API into Public Preview, enabling developers to register Model Context Protocol (MCP) connectors once and deploy them across multiple Mistral products. This 'bui

We've got all the models here: https://dell.huggingface.co/authenticated/models Kimi K2.5, Mistral, Cohere, Arcee AI Trinity Large, Google Gemma, Meta/Llama, Qwen, Nvidia Nemotron, Grok, GPT OSS, Deep

🆕 Today, we're releasing the public preview of Workflows, the orchestration layer for enterprise AI. 🌎 Enterprise teams have capable models. What they don't have is a way to run them reliably in produ

I have been testing DeepSeek-V4-Pro with the Pi coding agent. I am mindblown by how well it works out of the box. A few notes: I spent a few hours building an LLM wiki with an agent powered entirely b

Yes, open-source / open-weight models are important for a healthy AI ecosystem. That's how we can verify things, check claims, and keep up outside the closed labs. Plus, it gives us the freedom to run

We are in an insane run of open-weight drops. Every modality, open source is winning. This is what an open source AI summer ☀️ looks like: 🧠 LLMs & Reasoning → DeepSeek-V4-Flash-0731 (my king 👑): 304B

Mistral AI introduced **Mistral Large 4** in October 2026 as a general‑purpose agentic model capable of gathering information and producing final deliverables across complex workflows. The launch high

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

GLM-5.3-Flash scores 57 on the Artificial Analysis Intelligence Index. At 0.09 Cost per Task, it sits comfortably on the Intelligence vs. Cost per Task Pareto frontier @Zai_org has released GLM-5.3-Fl

BREAKING: SpaceXAI has released a major new update for Grok Build (v1.0.13). The update improves reliability with automatic retries and recovery from truncated responses, inference failures, oversized

Claude Fable 5.1 tops the Artificial Analysis Intelligence Index but costs 20% more per task than Fable 5 despite a 75% cache read price cut We supported @AnthropicAI with pre-release evaluation of Cl

This is a really neat benchmark. It's super interesting that Astra starts strong and holds the lead for up to 19 hours, but Fable 5.1 catches up in the final hours. Not entirely clear why. Different m

WHAT THE F*CK. SpaceXAI is using Grok Bot to build Grok Bot. Its agents design, code, test, and ship the product. In this 45-minute session, Peng Zheng and Lauren Tanshowed their internal setup across

Grok 4.7 is now available on Amazon Bedrock and on Google's Gemini Enterprise Agent Platform. Both platforms already offered Grok 4.6. Grok 4.7 is SpaceXAI's model for coding and knowledge work, and i

Agent-to-agent communication with a personal agent on top is wild. Wow. I underestimated how well models like Opus 5.5 can coordinate already. This opens a whole new set of experiences with agents. Bu

Now live in LM Studio Bionic! 🚀 Introducing DeepSeek-V4.1-Flash: smarter, faster, more efficient. 🔹 Introducing the smallest model in our new architecture family, with native visual understanding. 🔹 D

deepseek v4.1 flash has arrived on together ai it beats gpt-5.6 sol on agentic benchmarks at one third the cost per task the model supports a 1m context window and native multimodal input, with 552b t

6 billion tokens for $65 Is it as good as Astra and Fable at hard stuff? No of course not. But you don't always need a genius and can just call one for advice when you do. Extrapolate where this is go

Impressive paper showing how much the first retrieval step matters for deep research agents. It helps to improve GPT-5.5 from 83.1% to 90.5% on BrowseComp-Plus with the same retriever and the same age

Must-read papers of the week ▪️ JEPA-Anything ▪️ Modality-Autoregressive World-Action Models ▪️ In-Context Robot Learning with VLM Agents ▪️ Dream-RSI: Recursive Self-Improvement through Evolving Worl

Cool to see classification models resurge in the era of agents. The effects of Jev are insane. Also very cool to see our emotion dataset built at @dair_ai used to test this new model, Julia-1. I spent

This is a great paper from AWS AI Labs. They show that multi-agent coding teams raised their test pass rate by 28.2% and cut wall time by 16.5% without changing the model. The authors achieve this by

Bullish on this trend of making post-training more accessible. A new post-training era is upon us. If you work on agentic RL, long-context tasks (a big focus today) are expensive, inefficient, and don

Build your own harness, folks. This is absolute banger paper from NVIDIA on self-evolving agent harnesses. (bookmark it) They introduce SoL-Pi which cuts token traffic by nearly half. And it matches i

6 billion tokens for $65 Is it as good as Astra and Fable at hard stuff? No of course not. But you don't always need a genius and can just call one for advice when you do. Extrapolate where this is go

Impressive paper on building recursive self-improving agent harnesses. It's rich with great insights on building effective agent harnesses. If you maintain an agent harness, this paper names three def

Cool to see classification models resurge in the era of agents. The effects of Jev are insane. Also very cool to see our emotion dataset built at @dair_ai used to test this new model, Julia-1. I spent

An interesting idea is to continually train specialized models on skills. This paper explores that idea. They propose SkillGym which turns human-written skills into 2,756 training environments with co

So I would like to share my analysis of PD disagg that I've run by Horace and many folks at Thinky You may have heard that PD disagg helps with per-token 'tail latencies' in ITL/TPOT, as prefill inter

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

pplx-decider-v1.1-27b, our updated open weights multimodal decision model, is now available. It scores the highest on the new @huggingface Decision Index 0.3 benchmark. pplx-decider-v1.1-27b costs hal