Search: “context”

Huge release from @odysseyml. Odyssey-3 Pro sets a new top score on Physics-IQ Verified, a benchmark that asks models to continue videos of real physics experiments. The robotics results stood out to

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

Both embeddings models from Perplexity.ai—referred to as *pplx‑embed‑v2*—are publicly available on Hugging Face under the “perplexity‑ai” collection. The models can be accessed via the Hugging Face pa

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

One thing I'd LOVE to understand is how Claude 'knows' what the music from Secret of Monkey Island sounds like Maybe Anthropic crawled a whole bunch of online music discussion forums with text-based r

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

Introducing North 2. Enterprises have been compromising on agentic AI for years: platforms that aren't scalable, models that aren't sovereign, control without enterprise-grade security. That ends toda

HuggingFace just closed a major gap in harness engineering! (the ultimate guide to multi-harness RL) the same open-weight model can perform well inside one harness, then lose accuracy or produce inval

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

Yann LeCun's (@ylecun ) latest talk at ETH Zürich Scaling LLMs to reach AGI is 'impossible' A large language model is trained on about 30 trillion tokens, which is roughly 10^14 bytes of text and woul

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

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

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

The era of omni agents is upon us. This is a great report by the Qwen Team on their omni-modal agents. They present Qwen3.8-Omni-Flash, a natively multimodal model trained for long-horizon agent tasks

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

StepFun’s new Step 5 Preview model is impressive! Had a chance to test it early. I've been testing it as a coding agent. It’s on the Pareto frontier for cost vs. capability. It is a very capable model

It is ironic that the thing that is now most annoying about long-running agentic tasks with Large Language Models isn't coding or errors or hallucinations, but the fact that their language gets worse

Thanks @vllm_project for the day-0 support! 🙌 Generate, edit, transparent output — one model, ready to serve. Details 👇 Qwen-Image-2.1 from @Alibaba_Qwen has day-0 support in vLLM-Omni. 🎉 Generate, ed

the hidden opportunity cost of this insane bet on generative AI is immense Economic activity flowing into the AI sector is crowding out other forms of investment. Shalom Lappin, drawing on Robert Gord

Banger paper from Google Cloud AI Research. If you follow autonomous research agents, this one is worth your time. ScientistTwo takes a problem from a human expert and runs the full discovery cycle wi

Two weeks. That's how long it took to go from GLM-5.3-Flash's first run on domestic accelerators to serving all of its production traffic, with 3.2× end-to-end throughput along the way. What I keep th

Claude Code showed that AI could do real work, not just answer questions. Developers hand Claude a feature, come back to shipped code. That's where much of the industry's serious engineering runs now.

Nice work from Adobe. It's standard practice to store a fixed reference answer for every eval case. When the underlying data changes daily, that stored answer goes stale. Adobe researchers write each

Rene has a really neat multiplayer agentic experience. I run several agents at once. So I lose track of important conversations throughout the day. Rene pulls conversations from my inbox and manages t

The essay below from Aaronson is just unmoored from reality, sorry. It is just not true, if you try to approach the question in a data-oriented fashion, rather than via vibes and speculative fiction a

Together AI just raised 800M at an 8.3B valuation. I got their product team to open up the actual repo they run on: 0:00 - Slop is the new party foul 1:44 - Why individual output backfired 3:26 - Insi

LM Studio is a US‑hosted platform that enables “Zero Data Retention” by default, meaning user inputs are not stored after processing. It currently hosts the DeepSeek V4.1 Flash model—a 552 B multimoda

Gary Marcus will discuss his “case for boycotting generative AI” during a CBC segment scheduled to air at 7:45 p.m. ET tonight. The argument is outlined in his Substack post titled *The Case for Boyco

Gary Marcus has urged caution regarding Generative AI by proposing a boycott and highlighted this stance in a short post shared on Twitter (@GaryMarcus). He suggests that if just 1 % of people who fol

Gary Marcus argues that current generative‑AI models fail to meet basic standards of reliability because they routinely hallucinate facts, amplify existing biases, and provide no transparent audit tra

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

We’re entering an era of agent-first tools: stronger feedback loops between agents, with human judgment where it matters. We keep hearing from senior engineers that their mental load is growing, even

I had to look twice at this table. I know they are just numbers, but how the heck do you beat a competitor model released just a couple of days ago on some of the toughest benchmarks out there? Someth

Introducing K2 Horizon: a connected fleet of six foundation models ranging from 0.9 billion to 375 billion parameters. - Frontier performance: Across coding and agentic tasks, K2 Horizon delivers top-

If you build agent skills in production, check out this great paper from Alibaba. You can think of a production agent skill as a directory. The root loads on activation, and references, schemas, scrip

Most agent tutorials stop before the hard parts. This one builds them step by step. Deep Agents from Scratch is a five-notebook LangGraph course for builders who want to understand how advanced AI age

Thanks @juliafedorin for a great conversation! Some tidbits from the podcast on the AI space: - We've pivoted from building a RAG framework towards building the document infrastructure for agents - Do

Static embeddings offer unmatched throughput, but they also suffer from accuracy loss compared to traditional embedding models. Can we make them better for retrieval? We tried several things: ✅️ raw m

// Automata from agent traces // How much of your agent's behavior comes from the model, and how much from the harness you wrapped around it? New work collapses an entire corpus of agent traces into a

GLM-5.3-Flash is live in Hermes Agent via Nous Portal https://portal.nousresearch.com Introducing GLM-5.3-Flash - Leading capabilities at a highly competitive price - Natively multimodal with a 1M-tok

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

the coolest people are coming to talk at our conference!!!!! @howietl i first used airtable when I was an intern at Tinder 10 years ago and now Hyperagent is a bb customer @swyx a total living legend

The hottest neolabs are the application layer, who serve as an intermediary layer providing their customers the best intelligence per token per task/workflow across different underlying model provider

Today we’re introducing Gemini 3.5 Transcribe, our latest transcription model built for incredibly precise, smart dictation across your favorite apps and devices. Remember when traditional speech-to-t

Top open models by use case 👇 chat - Kimi K3, Qwen3.8 2.4T A95B reasoning - Kimi K3, DeepSeek V4 Pro coding agents - Kimi K3, DeepSeek V4 Flash, GLM 5.2 small + fast - Qwen3.8 27B, gpt-oss 20B mid-siz

Very interesting new work from Prime Intellect. Prime Agent is an impressive open-source self-improving harnesses. It's a harness for long-horizon agent work. A persistent IPython REPL lets the model