All entries

Your closed model refused a task it should have done. Ours didn't. DeepSeek V4 Pro on Fireworks: beats Fable 5 on SWE-Bench and LiveCodeBench, a third of the cost per solved task, and it doesn't decli

Your organization is not spending enough of its efforts on bolstering cybersecurity during the window before open weights Mythos-class models/harnesses become available. The HuggingFace incident shows

On August 25 2026, Mia AI Lab announced that the Qwen‑3.8 Flash model would be released in 22 hours, noting it can run locally without a sleep restriction. The tweet includes a link to the Hugging Fac

Advances in models, chips, or devices will continually improve local-first capabilities. We will open our benchmarks soon. Read the full post: https://www.perplexity.ai/hub/blog/a-local-first-agent-fo

Big step forward for Engine! Some things I'm excited about in this release that we've shipped for our most avid users: - Engine now points more obviously to the issue in a trace. Engine identifies and

ChatGPT Work can now use its computer and browser to sign in to websites on web and mobile, without ChatGPT ever seeing your username or password. That means you can ask it to: • Set up utilities for

Compute has always been core to the @VerneRobotics story. Getting there meant negotiating long, expensive contracts with big neoclouds, and projecting compute needs years into the future. Verne wasn't

arXiv:2411.09686v4 Announce Type: replace-cross Abstract: Regressing a function F on R^d without incurring the statistical and computational curse of dimensionality requires exploitable structure. Com

Every extraction API demos well on a clean invoice. But what about the scanned form, the nested table, the 40-page financial report with merged headers? We tested 14 frontier systems to find out. Extr

🤯 Excited for all the models to come! Ollama is exploding in token usage. Better models, choice of apps/harness, and all private. We are just getting started. Let's continue this record-breaking strea

Finally, a good paper testing whether Agent Skills actually help. Worth reading if you are maintaining a skill library in a team. WebDev-Skills-Bench runs 31 public WebDev Skills over 50 Web-Bench pro

Had a lot of fun chatting again with my twin brother @dylan522p We went through lab economics over the next few years - the shift from inference to training as RSI draws near; and how Anthropic and Op

have been using grok 4.6 last 24 hours first takeaway, insanely fast. didn't even realize how long i was waiting for anthropic + openai models in Hermes text much better to read, less slopified and th

Hi @GaryMarcus, I'm the Research Lead for this model. It's even more consequential than just Anthropic's IPO: This paper is a blueprint for how to *actually* build AI Sovereignty. https://tinyurl.com/

Cohere’s tweet discusses how someone moved from jailbreaking a PlayStation to becoming CEO of Canada’s leading LLM provider, attributing this career shift to education at the University of Toronto and

IBM Granite 4.2 is now available on Ollama. 3B, 8B, 30B parameter open models made for enterprise agents. This model is free to use and is licensed for both research and commercial usage. The data cur

If you keep safety rules or coding standards in an AGENTS.md or a CLAUDE.md, this one is worth your time. (bookmark it) Researchers measured what context compaction actually destroys across 20 product

If you're looking for a weekend project, how about training your own text-to-speech model from scratch on your own GPU, and then running it on any device's CPU? We just open-sourced the entire Pocket

i’m seeing SO many US companies shift away from frontier models to open source in the last 4 weeks. cost and privacy are big factors but more so people are realising fine-tuning and training their own

Impressive new paper from Microsoft and colleagues. Harness design is still hand-tuned almost everywhere. This work present an automated loop to optimize the harness. They introduce AutoSaddler, which

Impressive work from Alibaba. (bookmark it) If you build long-running agents and keep rewriting your memory schema, take a look at this approach. It basically treats agent context management as a prog

Introducing ChatGPT Business Premium Seats The new $100 Premium seat is a game changer for small businesses and startups—giving lean teams better tools, faster workflows, and capabilities once reserve

In August 2026, OpenAI released the 'Jalapeño' update, announcing faster response times for ChatGPT and more responsive Codex sessions and agents. The upgrade is designed to provide reliable access as

Megatons to orbit & beyond is a critical piece of the K2 puzzle. The other parts are: massive amounts of solar cell production, AI chip production, millions of humanoid (general purpose) robots and a

not sure i fully get this. - i want my agents to use slack - i don't want my agents to build a new slack - i don't want to use slack's agent i think every piece of software/system of record needs to b

Open models, open science. Qwen keeps growing steadily, and we'll always be right here with the research community.🙌 Thanks for the deep dive! @natolambert Over the weekend I had Codex parse 500K arXi

OpenAI Jalapeno is spicy Usually first generation chips aren't competitive, but OpenAI is beating Nvidia Blackwell and even Rubin This is huge news! We got to go into OpenAI's lab to dissect their new

OpenWorker -- an open source agent that doesn't just chat but completes tasks on your laptop -- just released a new version with many features for security workflows. After our initial release, many u

Perplexity AI announced on August 25 2026 the launch of a “Portable Computer” feature, available immediately to all Perplexity Pro and Max subscribers who are using NVIDIA’s DGX Spark hardware. The se

A portable computer now runs a post‑trained, locally hosted PPLX 27B language model, with the Qwen 3.8 27B variant also available. NVIDIA’s Nemotron 3.5 Lightning GPU support is slated to arrive short

Qwen3.8-27B at #9 overall on Code Arena, the only model in its size class in the top 10.😎 Small but mighty. Thanks for the recognition! @arena Exciting news: Qwen3.8-27B by @Alibaba_Qwen just landed i

Qwen3.8 27B is now available for both fine-tuning and Dedicated Model Inference Fine-tune it on your own data, then deploy that model on dedicated infrastructure for production, without stitching toge

Runway AI Summit, new speakers confirmed! More speakers are joining the Runway AI Summit. This September in San Francisco, industry leaders across robotics, autonomous vehicles, marketing and infrastr

Since announcing Jalapeño, our first custom inference chip, we’ve been testing it and the system around it. The results show a major advance: more intelligence from every watt and faster responses, de

There is a child with a rare disease who is currently suffering and struggling to manage his symptoms. Rare as this is, you can directly help him. Today we are launching the 'Rare Disease, Real Kid' H

// There Is No Neutral Harness // Great work discussing some of the issues in harness evaluation. Twelve open-weight models answer the same 3,679 items from ARC, HellaSwag, MMLU, and TruthfulQA under

this is a practical guide (+ updated skill) on how we use real world data like traces + human feedback to make synthetic environments + evals so we can measure, harness engineer, and post-train our ag

This summer, we brought in two first-year Waterloo interns (‘rising sophomores’ in 🇺🇸) and tasked them with shipping complex production features that help push the frontier of our document processing

Today we are launching the 'Rare Disease, Real Kid' Hackathon together with @sagebio in which you can literally save a life if you’re interested in AI and genome 🧬 (and incidentally win 50,000 in priz

Today we’re launching Portable Computer on @NVIDIA DGX Spark. Portable Computer is a fully local version of Perplexity Computer, where the entire runtime: orchestrator LLM, subagent LLM, agent harness

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

'Two labs will soon control most of the world’s compute' Had a lot of fun chatting again with my twin brother @dylan522p We went through lab economics over the next few years - the shift from inferenc

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

We officially surpassed 1M model downloads on @huggingface 🔥 Your 5 most downloaded models: 1. Qwen3.8 27B — 261K 2. Ling 3.0 flash — 158K 3. Ornith 1.5 35B A3B — 50K 4. Qwen3.5 4B DFlash — 49K 5. Gem

We plan to begin deploying Jalapeño in OpenAI’s compute infrastructure by year-end. It’s the first step in a multigenerational roadmap: Gen 2 is deep in development, and Gen 3 is taking shape. Each ge

What do I want in AI? Here are just a few things. I want voice-enabled everything. I want things to be more proactive. I want to manage AI’s escalations (versus delegation). I want those escalations t