Search: “models”

Every document extraction system has a perception blind spot. We mapped them. For ExtractBench, we tested 14 systems on documents that weren't born digital: 1950s regulatory filings, hand-filled tax f

Grok 4.6 just matched Claude Fable 5 on Perplexity’s WANDR benchmark....at more than 60% lower cost Both score exactly 0.496 But the cost per task is ridiculous: • Grok 4.6 → 7.58 • Claude Fable 5 → 2

We’re working with an initial group of customers to understand where this speed makes the biggest difference, and how those learnings can inform our products over time. If your business requires front

18 two-word AI prompts I'm kind of obsessed with: 1) now what - great for when you've wrapped up a project or big push and you still have energy and want AI to give you more 2) plz fix - usually accom

// Actions Speak Louder Than Words // Multilingual agent evaluation compares final answers and throws the trajectory away. The trajectory fixes cost, latency, failure mode, and auditability. New resea

The most dangerous document extraction failure isn't a wrong value. It's a missing row that looks like nothing is wrong. We released ExtractBench yesterday: 370 enterprise docs, 14 systems. The hardes

⚡️A coalition that secures long-term AI capacity: We’re aggregating long-term compute demand in Europe to determine what capacity is built, where it’s located, and whom it serves. Through these multi-

LLMs still produce bugs, but those bugs are different than what they used to be. It’s less off-by-ones and more about system design, ui usability, missing broader context. Some kinds of coding has bee

really excited to see this release AND integrate it with deepagents!! https://www.langchain.com/blog/switchyard-agent-routing-benchmark Lightning strikes for continuous and long-run agents! Nemotron 3

On August 11 2026, Gary Marcus commented that if the symbolic components were removed from Claude’s Riemann implementation it would fail to work, highlighting a concrete win for hybrid neurosymbolic A

This is part of working with the EU AI Act, other labs are adding similar watermarking. It’s hard to identify AI-generated text, and this gives people better tools to do that. We’ll also be a shipping

Grok Imagine is focused on professional usefulness, fun for consumers and overall ease-of-use Grok 4.5 just ranked #1 on Design Arena for Daily Usage - measuring the average unique users actually inte

Literally for years I have been warning everyone: @GaryMarcus, December, 2022: “GPT-4 will still, like its predecessors, be a bull in a china shop, reckless and hard to control.” @GaryMarcus, November

👀 Seeing is just the beginning. With Qwen-MM-Plugins, turn your favorite agent harness multimodal-native — read images, videos & documents, edit videos, work with 3D/CAD, and more. From multimodal mod

Francesco @francedot reported that the first fully offline computer‑based LLM experience was achieved by running Muse Glimmer 30B (from @AIatMeta) locally on macOS, using Cua Driver to control native

In a recent Twitter exchange, Luca Ambrogioni stated that large‑language models (LLMs) likely possess fundamental limitations that may be obscured by progress in reasoning and agentic pipelines, thoug

The future of FDE work seems closely related with all work around evals/posttraining/RL envs. FDEs are effectively responsible for the following: 1. Define the business problem. 2. Codify the business

Zain (@zainhas) published a detailed article on August 7, 2026 explaining that autoscaling for highly peaky large‑language‑model (LLM) inference is fundamentally different from autoscaling conventiona

The cloud was always a cat. Qwen3.8-Max just saw it first. 😼☁️ Try it yourself! Qwen 3.8 Max is actually impressive Sent a sky pic to it along with Claude Opus 5, Kimi K3, and GPT 5.6 Sol, and asked t

Congrats to @mattrubens and the Roomote team on the launch. Builders can use Together AI as an inference provider in Roomote and assign different open models to coding, planning, vision, and review ac

Feels like Google could have been the dominating force in AI by open-sourcing the frontier with Gemini, Veo, and Nano Banana. Instead, they kept them behind APIs for a few billion dollars in revenue.

... four years later, I got the new Claude Fable 5 to actually build the game https://x.com/simonw/status/2085089518223602058 Four years ago today I tweeted about having GPT-3 and DALL-E come up with

.@Kimi_Moonshot benchmarked K3 endpoints across major inference providers. Together AI leads or ties for #1 on 3 of 4 benchmarks: OCRBench, MMMU Pro Vision, and DeepSWE. Open models like Kimi K3 have

Live and ready to build. Thanks for having us! @OpenRouter. Open weights dropping soon.⚡️ Qwen3.8 Max by @Alibaba_Qwen is live on OpenRouter. The new flagship has 2.4T parameters (95B active) and is b

To date, finding a drug has been a process of guess & check… screening millions of molecules hoping one binds. @chaidiscovery is changing the paradigm… describe the molecule you want, and the model de

Qwen3.8-Max from Alibaba’s Qwen team achieved second place in the Vision Arena benchmark, scoring 1,305 points. It trails only Claude Fable 5 (High), which leads by a slim 13‑point margin. The post un

Simon Willison noted that Qwen 3.8 Max and MiniMax‑H3 were released within hours of each other. The MiniMax team announced that MiniMax‑H3 is now publicly available on Hugging Face (https://huggingfac

Fascinating to see @ClementDelangue, CEO of @huggingface speaking on @FaceTheNation. Excellent points and solid advocacy around the benefits of open AI models, which helped him defend against a rogue

Claude Mythos 5 built a malicious Python package, created accounts, and published it, where it was live for roughly an hour and successfully infected a company! Anthropic never noticed!! Competitive p

The price wars that I have predicted going back to August 2023 are now in full swing. All this was inevitable – as long as everyone builds more or less the same kind of AI, there is no moat, and profi

This is both a real incident (in that the AI really did get unauthorized access to real systems) and also something it was (sort of) prompted to do. In a review of our cybersecurity evaluations, we fo

good job little bro After deployment, we applied GPT-5.6 Sol to advance the frontier of efficiency by making itself more efficient to run. The results: - 20% lower serving costs from production GPU ke

Yesterday I cohosted a dinner with @dexhorthy with a wonderful group of founders, to talk about agent loops and loop engineering. Some interesting insights: * Most of our group was *not* actively usin

i'll say it plainly, hermes agent desktop is the best agentic app i've used, and i'm a little mad i didn't find it sooner. it auto see the models i'm serving, laguna s 2.1 sitting on my dgx spark and

The number of times I have had to tell Opus 5 and Fable 5 to talk to me like an excited teenager and not a computer science phd is high. Was going through a Google auth thing and got multiple paragrap

Thrilled to have @gabepereyra speak at our @sequoia event tmrw on OWN YOUR AI: how to build your own Lab as an application company. Also featuring @FireworksAI_HQ @mercor_ai @LangChain @trajectorylabs

New research from Meta and CMU. This one is on agentic context management for long horizon tasks. (bookmark it) Production agents accumulate context every turn. The usual fix compresses on a token thr

Sam Altman: “Concentration of power with AI is a terrifying thing.” 'A lot of the talk about safety concerns is well-founded, and then a lot of it is about people that just really, even if it's slight

btw anthropic's internal document on this literally said 'we don't want it to be known that we are working on this.” it was called project panama. here's exactly what happened: 1: anthropic concluded

Great technical paper from Google. Great read on why context beats scale for agents working against unfamiliar APIs. (bookmark it) GPU kernel optimization has KernelBench to hillclimb on. TPUs had not

love this frame. calls to mind the role of the hippocampus in human navigation (via place cells and grid cells), and how navigation is, in a sense, what makes agents *agents* vs plain old LLM calls in

New research from NVIDIA. Does AdamW have a scale ceiling? This work claims yes, and shows where it sits. At batch sizes up to 100M tokens for next-token prediction, SOAP and Muon maintain training st

OpenAI’s agent went rogue, escaped containment, and spent days hacking Hugging Face. Before that, an OpenAI agent reportedly left notes for future versions of itself explaining how to break free from

Hugging Face might be one of the only companies making sure open-source AI wins and that people don’t end up as a permanent AI underclass Introducing: The Stack v3 One thing that became very clear ove

We built this experience based on feedback from early testers and physicians. With your permission, ChatGPT can use relevant context you’ve connected in Health across your conversations — to help you

Authentic Details and Deep Knowledge are also major upgrades in this release. Together, they enable Qwen-Image-3.0 to make real breakthroughs in high-value productivity scenarios — newspaper PDFs, sho