All entries

We audited SWE-Bench Pro, one of the most widely used AI coding benchmarks, and found it no longer reliably measures frontier coding capability. We find 30% of SWE-Bench Pro tasks to be broken, and ar

We need AI model selection to be MUCH easier ASAP. I want proactive flags from my AI systems suggesting models. I want my AI harness to say 'hey allie, my girl, you keep asking for bar recommendations

We raised 130M @ 1B for our series A To build the open superintelligence stack for everyone Pre-training concentrated frontier AI in a handful of labs. RL changes who can build frontier AI and just wo

We tuned the harness for @NVIDIAAI Nemotron 3 Ultra. Benchmark-leading performance. 10x lower inference costs. ✅ An aggregate score of 0.86 at a cost of 4.48 ✅ The closest-performing model: 43.48 http

X (formerly Twitter) is introducing a Community Notes feature that notifies users via X Chat when posts they have interacted with receive corrections or fact-checks. This notification system aims to k

We will continue to make refinements to the Grok Build harness and the 1.5T foundation model almost every day in response to user requests. The 2T model will finish training this month and be availabl

We're continuing to work hard to make OpenWiki better and better! v0.0.3 just launched with a lot of improvements. What do you want to see next? OpenWiki 0.0.3 just launched with tons of bug fixes and

We're introducing Provisioned Throughput: reserved inference capacity for frontier open models, with token-based pricing and a 99% uptime SLA. Serverless simplicity, guaranteed capacity, up to 90% low

We're releasing ZML/LLMD, our homegrown LLM server built on top of our homegrown high performance heterogeneous inference stack. It ships with 5 architectures out of the box: NVIDIA, AMD, Metal, Intel

We're still just scratching the surface of how much better, faster, cheaper we can make inference for open-source models! So super excited to see companies like @zml_ai by @steeve come out of stealth

We’ve made improvements to the FrontierCode methodology and are releasing FrontierCode 1.1 with clearer guidelines for fair internet use and refined grading criteria. Learn more about the changes on o

Cursor has partnered with xAI to train Grok 4.5, positioning it as their most advanced model to date with capabilities extending beyond software engineering applications. The partnership represents an

We've usually stayed away from model comparisons but 5.6 vs Fable is a unique situation We've never had a case where the team is so completely convinced on which one is better Here's the timeline of o

Wispr Flow kept replacing the word 'Anthropic' with the word 'Perplexity'. They sound nothing alike and are direct competitors. After flagging this to them back in April, they only just now emailed me

With just one year in orbit, the first FireSat satellite has already spotted wildfires invisible to existing satellites. After a successful launch early this morning, 3 more satellites joined the cons

This is a Wordle game result shared by Anthropic on X (formerly Twitter), showing that they solved Wordle puzzle #1,844 in 3 attempts out of 6 possible guesses. The colored squares indicate the guess

Grok is an AI chatbot developed by xAI, Elon Musk's artificial intelligence company, designed to answer questions with a conversational and occasionally humorous tone. The system is integrated into X

WOW! GROK 4.5 PRICES ARE NEAR OPEN SOURCE HOSTED PRICES! This will move many that have token cost fatigue in corporations. But that is only half the story: it is ~4.2 more efficient using far less tim

Wow… within 5 minutes my kids built this game called the Tesla City with Grok 4.5. It’s a simple Tesla arcade game in SF where: 1/ You can choose a Tesla (3 / Y / S / X / Cybertruck / Roadster / Semi

Xiaomi now processes more AI tokens than OpenAI. On OpenRouter, Chinese models just crossed 45% of all token volume. Anthropic is at 15.3%. OpenAI is at 7.4%. For now, the frontier is American models,

You don't need heavyweight VLMs to OCR simple text-only PDFs. Doing that is like bringing a bazooka to a knife-fight, and is completely unnecessary and worse quality than a tuned OCR approach. Output

Cohere announced that approximately 25% of Toronto's working population is employed by the company during a particular week. This statement reflects Cohere's significant presence and growth as a major

1,200 former DOJ employees have just sent a letter urging Senators not to confirm Todd Blanche as AG: 'In the coming weeks, many will rightly underscore the corruption and abuses that have defined the

2023: “Twitter rebrand to X is destined to fail.” 2026: “Fastest-growing website among the top 20 in the world.” X in June 2026: → 4.399 billion visits → Up 4.66% from May → Fastest-growing website am

Serial Experiments Lain is a landmark 1998 anime series that premiered on TV Tokyo, known for its experimental narrative structure and exploration of consciousness, technology, and virtual reality. Th

arXiv:2606.12502v2 Announce Type: replace-cross Abstract: We propose that value -- the quantity goal-directed agents create, destroy, and exchange -- is a lawful structural quantity in the same catego

A recent NYT article by @CadeMetz [1] claims that neural network distillation was first developed in 2015 by a team of Google researchers including G. Hinton [2]. Not true! I published the technique i

AI debt financing is on an insane trajectory, per @SemiAnalysis_: Nvidia GPU Debt Backstop Unleashes the AI Project Trinity: Capital, Offtake and Datacenters Over 7T AI debt by 2029, There can be no N

Researchers at UMA Robots have developed a single neural network that enables end-to-end robotic control, operating continuously for extended periods with high precision while adapting in real-time to

AI obsessions, continued: the act of naming something, whether something is 'earned,' what 'carries' something else, strained metaphors, sitting with something (often an idea), an inanimate concept th

AI+Optimus will enable universal excellent healthcare that is better than anyone receives today Back pain sucks; AI could provide the answer to it. Elon: 'So, if you've got humanoid robots that have v

Americans have had enough of the bottom 2% of society ruining our lives “I'm gonna be so blunt. Because of the ghetto-ass activities that happened in Newport Beach — we are now going to see next year

And that's a wrap on World's Fair in SF 🎉 Thanks to everyone who stopped by the booth to say hi and dive into LanceDB internals. Some of the best conversations happen at a conference booth and this ye

Another day another big public tech co saying they’re using open source AI models extensively With our internal coding benchmark, we're able to confidently introduce open-weight models into our AI cod

Anthropic releasing open source demos built on top of Qwen (with @neuronpedia) is not something that I was expecting We also partnered with Neuronpedia to create an interactive demo of our methods on

ARC Prize 2026: ARC-AGI-3 Milestone #1 Winners Congratulations to the three winners who open-sourced their top-scoring ARC-AGI-3 solutions: 1. @tufalabs - 1.21%, 25K 2. Reki - .867%, 7.5K 3. Md Boktia

As the @UN’s Global Dialogue on AI Governance wraps up today, I’ve been encouraged by the discussions surrounding AI and its implications for global collaboration and policymaking. I’m hopeful that we

At UMA, we build and own the full stack, from hardware to software. This allows us to bake safety in at all levels, rather than bolt it on as an afterthought. Because trust is everything when robots s

Fireworks AI is hosting a fireside chat at Raise Summit featuring CEO Lqiao and Matt Evantic from Evantic Capital on the Master Stage at 4:00 PM. The event appears to be a discussion panel or intervie

Banger compression paper from NVIDIA. (bookmark it) Bigger MoE models keep winning on quality, but serving them at interactive latency is still hard. NVIDIA compresses the hybrid MoE Nemotron-3-Super

This post references documentation for secret source plugins, likely covering how to develop or integrate plugins that manage secrets within the Hermes Agent framework. The documentation compares or d

Boom also had a board meeting where the board told me to shut the company down. XB-1 hadn’t broken the sound barrier yet. The team deployed in the Mojave desert was exhausted from months of fighting t

Swyx appeared in an interview on Local AI that was subsequently featured in The Daily Context newsletter from AIEngineer, with the interview appearing on the second page of that publication. The inter

نطلق اليوم نموذج @cohere Transcribe العربي، أفضل نموذج مفتوح المصدر لتحويل الكلام العربي من الصوت إلى نص، مع مراعاة اللهجات العربية المختلفة. يتصدر معيار Open Universal Arabic ASR Leaderboard. صُمم ال

deepagents is our newest open source project - an open source, model agnostic agent harness this is maybe the most important academy course we've launched 🎓 New course launch from LangChain Academy: I

DOGE shut down USAID, established by JFK in 1961. Before being shut down, the US Agency for International Development (USAID) was the largest funding agency for humanitarian and development aid worldw