All entries

Strong Opinions, Loosely Held on Agent + Harness Engineering: 1. You can outperform any default harness+model (including codex & claude code) on pretty much any Task by engineering the harness around

SWE-Check is live in Windsurf! So fun to collaborate with @cognition to post-train this. Try it out! Devin Review runs hundreds of thousands of times per day. Starting today, run it directly from Wind

@swyx @maheshmurag deep dive on the new dreaming feature in beta today https://x.com/claudeai/status/2052067400690851842?s=46 Dreaming reviews your agent's past sessions, extracts patterns, and curate

Take: stop searching for the “best model' or “best harness”. Model release → harness breaks → refind your optimal config. Most teams handle this with manual local search, with poor visibility into acc

TBC is excited to announce the first residential Music City Loop station agreement, serving those living at the beautiful Prime, Alcove, and Paramount towers in downtown Nashville. Residents will take

the deeper point: model choice and harness choice aren't independent variables. benchmarking a model without specifying the harness is like benchmarking a chip without specifying the compiler. the num

The Structured Output Benchmark (SOB) dataset has been released and made available on Hugging Face. This dataset, hosted by Interfaze AI, likely provides benchmark data for evaluating models' ability

The GB300 is the best AI computer Two frontier labs. One accelerated computing platform. Congrats to @SpaceX and @AnthropicAI on the new compute partnership, powered by 220,000+ NVIDIA GPUs inside Col

The last sentence in this abstract is really important, in a way that professional programmers will immediately recognize: the models favored big single files rather than breaking things into modules.

There are only two honest metrics when it comes to benchmarking intelligence: novelty and efficiency. You don't need intelligence to solve a known problem (only memory). And you don't need intelligenc

They seek to undermine and dismantle Western civilization, but they cannot admit it openly, lest people resist and stop them. So they champion multiculturalism as a Trojan horse. Question the project,

this deepagents deploy https://docs.langchain.com/oss/python/deepagents/deploy (or at least directionally where we want to take it) what's missing? give us feedback! can someone PLEASE launch OS claud

👇 This is an incredible admission by Jensen Huang. Effectively he is saying that AI, for all the hype (some from himself) wasn’t really useful until late 2025. Let that sink in. This means practically

this is your chance to build ideas you don't even know today that you're capabale of having I’m looking for the first full-time developer for http://neal.fun! You’d work with me on making new web proj

This likely costs about ~500m a month, ~6bn a year to rent blended Which is about the run rate net loss of xai end of q1 Anthropics revenue run rate was 9bn end of 2025, 30bn a month ago Our agreement

This week made something clear: you shouldn't take what most tech ceos are saying publicly seriously! From “Anthropic is Misanthropic” to “Claude is good for humanity and was impressed.” Most ironic o

Today we're releasing ZAYA1-8B, a reasoning MoE trained on @AMD and optimized for intelligence density. With <1B active params, it outperforms open-weight models many times its size on math and reason

Together AI has long been a proud supporter of open-source innovation in inference. We're excited for the new TokenSpeed inference engine, available in preview today with MIT licence, and can't wait t

truly scary: anybody, no matter how noble, can be destroyed by misused AI. Artificial intelligence can create deceptive videos that rapidly damage a politician's public reputation. A new study reveals

This is a workflow link shared by ComfyUI on X (Twitter), likely demonstrating a specific node setup or image generation process within the ComfyUI application. The link points to ComfyUI's workflow s

Two frontier labs. One accelerated computing platform. Congrats to @SpaceX and @AnthropicAI on the new compute partnership, powered by 220,000+ NVIDIA GPUs inside Colossus 1. The future of AI runs on

Two weeks after release, Hy3 preview is #1 on @OpenRouter's weekly leaderboard with 3.66T tokens processed, up 298% week-over-week. #1 in overall usage, tool calls, and coding. 15.4% market share acro

Use Quick Review for a fast local check before pushing: free with SWE-check, our specialized bug detection model built for this task. Use Devin Review for deeper PR review: smart diff organization, bu

@vasuman We've been saying this for months. The best compliment you can give an AI system is that it behaves exactly as expected. Every time. We built a campaign around it. It's called Boring AI: http

Harrison Chase expresses enthusiasm about collaborating with Harvey on their Long Horizon Legal Agent Benchmark, highlighting the value of developing industry-specific benchmarks for AI evaluation. Th

💫Very happy to release NeuralBench, to benchmark Neuro AI models and datasets in the open! 🧵Thread, 💻Code, 📝White Paper below: 🧠 Introducing NeuralBench: a unified, open-source framework to benchmark

Robobun is a GitHub bot developed as part of the Bun project that automates contributions to the repository. Developers Jared Sumner and Bun Cherny discussed the bot's functionality and capabilities d

Anthropic announced a major compute partnership with SpaceX involving over 300 MW of new computational capacity and 220,000 NVIDIA GPUs to be brought online within one month, dedicated to powering Cla

We built a simple app that's also probably the best PDF -> text phone app there. Take a picture of any document: a filled out form, identification, a statement, an essay - and we'll convert it into we

We have greatly expanded the surface area for plugins over the last few weeks, and now you can extend LLM Inference Providers and Gateway Channels with plugins. Want a custom implementation of your fa

Harrison Chase expresses support for expanding AI benchmarking efforts and highlights appreciation for work being done by Harvey (likely Harvey AI, a legal AI company). The post indicates enthusiasm f

We use previous generations of Composer to train future ones. Our autoinstall system has earlier Composer models set up dev environments for RL training. That way, the next generation can focus on lea

we're continuing to see clear examples where a model's harness is a major determinant of overall performance. with the same model, running on same task, it's easy to observe very different scores depe

We're doubling down on keeping your Apps secure 🔒 Starting today, all Replit builders- free and paid- can publish their apps privately, making them accessible only to the people you choose. When publi

We're launching the agentic robotics app store today. Let's democratize AI robotics for all! 300+ apps shipped. 10,000 robots in the wild. It used to take weeks from a robotics engineer to build apps,

We're winding back our peak hours limit reduction and doubling 5 hour limits. Excited to partner with SpaceX to bring you more compute and we'll keep pushing to bring you the best coding agent in the

We’ve agreed to a partnership with @SpaceX that will substantially increase our compute capacity. This, along with our other recent compute deals, means that we’ve been able to increase our usage limi

We’ve been working closely with the @harvey team on the launch of the Legal Agent Benchmark, a product focused on evaluating how open-weight models perform on long-horizon, real-world legal tasks. Che

We’ve developed our own inference engine Runtime-Optimized Serving Engine (ROSE) to serve models ranging from embeddings to trillion-parameter LLMs. With CuTeDSL integrated into our inference engine,

We’ve partnered with @AMD, @Broadcom, @Intel, @Microsoft, and @NVIDIA, to release Multipath Reliable Connection (MRC), a new open networking protocol that helps large AI training clusters run faster a

What if you could extract text from any photo on your phone? We built LlamaParse Mobile, an @expo + @reactnative app for iOS & Android, powered by the LlamaParse TypeScript SDK 📱 Three steps, that’s i

What’s going on in semis is not sustainable per GS Everyone spending on AI is losing money except for semiconductor companies and the dynamic is “unprecedented and unsustainable” “Something has to cha

Why are four of the top 10 trending vendors AI inference platforms? Companies are getting selective about which model handles which task, and routing tokens accordingly. Read more from @arakharazian a

Wiki-Builder, a tool for creating LLM-powered wikis, was featured on Hacker News' front page, announced by DAIR.AI. The post indicates upcoming updates and improvements to make wiki creation more acce

Anthropic shared their Wordle game result for puzzle #1,781, solved in 3 attempts with a final correct answer shown by five green squares (all letters in correct positions). The emoji grid represents

xAI and SpaceXAI have just made Colossus 1 available to Anthropic to support Claude. This means more than 220,000 NVIDIA GPUs in one of the world’s largest and fastest-built AI superclusters are now h