Knowledge catalogue
The artificial analysis index is a normalized score of several benchmarks (and has changed over time) it is fine for roughly comparing models, it is not useful for trend analysis and it is unclear wha
A lot of work around AI in 2023 was spent on building picks and shovels. I would know this because that was basically the core goal of the original @llama_index framework. Today, a lot of that is no l
All the Doomers and hawks are lining up behind this distillation 'attack' farce because they want to see open source banned. It's really as simple as that. They want to take away your right to choose,
arXiv:2604.27006v1 Announce Type: cross Abstract: Context: Study screening in systematic literature reviews is costly, inconsistency-prone, and risk-asymmetric, since false negatives can compromise va
I had a really fun chat with Alex about Runway, media, world models, and some of what’s next for us. New: When Runway CEO Cris Valenzuela saw Sora for the first time, he thought: finally, some real co
I have been testing DeepSeek-V4-Pro with the Pi coding agent. I am mindblown by how well it works out of the box. A few notes: I spent a few hours building an LLM wiki with an agent powered entirely b
Our CEO @jerryjliu0 in @VentureBeat , on what's actually changing in the LLM stack: 'We've really identified that there's a core set of data that has been locked up in all these file format containers
The U.S. Defense Department today announced that it has inked artificial intelligence procurement contracts with seven tech firms. The group includes Amazon Web Service Inc., Google LLC, Microsoft Cor
arXiv:2604.26955v1 Announce Type: cross Abstract: AI tutoring systems in engineering labs face a tension between providing sufficient assistance and preserving learning opportunities. Existing systems
arXiv:2604.26954v1 Announce Type: cross Abstract: Strategic model selection and reasoning settings are more effective than ensembling for optimizing automated scoring with large language models (LLMs)
Carl Franzen / VentureBeat: xAI launches Grok 4.3, featuring “always-on reasoning”, 1M token context window, and low API pricing, and releases a voice cloning suite called Custom Voices — While Elon M
Introducing Agent Collabs: Bring your own ml-interns and agents for collaborative autoresearch! We built a simple platform for swarms of agents to work together on a problem: they can exchange message
arXiv:2604.25934v1 Announce Type: cross Abstract: The deployment of large language models (LLMs) as interactive agents has exposed a category of behavioral failure that prevailing terminology, princip
arXiv:2509.11295v2 Announce Type: replace Abstract: Developing effective prompts demands significant cognitive investment to generate reliable, high-quality responses from Large Language Models (LLMs)
The Musk v. Altman trial is underway, and that means exhibits, or the evidence to be presented in court, are being revealed piece by piece. So far, email exchanges, photos, and corporate documents are
Damning 🚨 Altman texts Musk: 'we offered you equity when we established the capped profit. you didn't want it at the time.' (Altman drafted this with Shivon Zilis, then sent it to Musk that night.) Op
i love that the team does stuff like this Codex is not like claude code. if you know the limit is going to end, like last 10 to 8%, give an very long run task, and even after the limit got ever, it wi
If you want to know whether the AI bubble is bursting, there's only one publicly traded company that will tell you: Oracle. That's right, the database company. Oracle has burned its boats and pivoted
The Musk-Altman trial is clearly a battle of egos—and it’s hard to root for either side—𝗯𝘂𝘁 𝗶𝘁’𝘀 𝗮𝗹𝘀𝗼 𝗮 𝘁𝗿𝗶𝗮𝗹 𝗮𝗯𝗼𝘂𝘁 𝘄𝗵𝗲𝘁𝗵𝗲𝗿 𝗢𝗽𝗲𝗻𝗔𝗜 𝘀𝗵𝗼𝘂𝗹𝗱 𝗯𝗲 𝗵𝗲𝗹𝗱 𝘁𝗼 𝗶𝘁𝘀 𝗽𝗿𝗼𝗺𝗶𝘀𝗲𝘀 𝘁𝗼 𝗯𝗲 𝗮 𝗻𝗼𝗻𝗽𝗿𝗼𝗳𝗶𝘁 𝘄𝗼𝗿𝗸𝗶𝗻𝗴 𝗳𝗼𝗿 𝘁𝗵𝗲 𝗯𝗲𝗻𝗲
Xiaomi MiMo-V2.5-Pro achieves multiple breakthroughs in the latest Arena rankings (Apr 26, 2026) 🔥 🏆 Text Arena (Expert) — #6 globally | #1 open-source model Also #1 among Chinese models, with Xiaomi
arXiv:2604.23449v1 Announce Type: new Abstract: Argumentation is a core practice in STEM education, but its productivity depends on who participates and how they interact. Higher-achieving students of
arXiv:2604.23341v1 Announce Type: cross Abstract: The deployment of Large Language Models (LLMs) as assistants in electric grid operations promises to streamline compliance and decision-making but exp
arXiv:2604.23347v1 Announce Type: new Abstract: We present a comprehensive evaluation of Large Language Models (LLMs) on Computer Science (CS) Data Structure examination questions. Our work introduces
However, older versions have a critical CVE, so you do need to upgrade! If you use uv (thanks to @charliermarsh) you can pop this in your pyproject to work around it: ``` [tool.uv] override-dependenci
I know the litellm team have a *lot* going on, & I have no desire to increase their workload even more… But if you're a litellm user, this is a critical issue to know about - it currently force downgr
I'm speechless at Google signing a deal to use our AI models for classified tasks. Frankly, it is shameful. For HR, I'm not speaking on behalf of Google but in my personal capacity, quoting public inf
arXiv:2604.23178v1 Announce Type: new Abstract: LLM-as-a-Judge has become the dominant paradigm for evaluating language model outputs, yet LLM judges exhibit systematic biases that compromise evaluati
Madlin Mekelburg / Bloomberg: Musk v. Altman: the judge asks Elon Musk and Sam Altman to “control your propensity to use social media to make things worse”, as opening statements begin — The judge ove
arXiv:2508.09603v2 Announce Type: replace Abstract: Membership inference attacks serves as useful tool for fair use of language models, such as detecting potential copyright infringement and auditing
arXiv:2604.21958v1 Announce Type: cross Abstract: This paper aims to synthesize current knowledge on generative AI in IT project management using the PRISMA methodology to provide researchers with a c
The cost to build natural gas power plants has spiked 66% in the last two years, with prices rising from less than 1,500 per kilowatt in 2023 to 2,157 in 2025 , driven by surging demand from data cent
Don't try to build a self-improving AI agent without evals. You are just wasting time and compute. An agent can't improve from traces it can't evaluate. This is why it's exciting to see @FutureAGI_ go
I don’t always agree with @ElonMusk. I often disagree. Sometimes loudly. But he’s basically right here, as far I can see. Scam Altman and Greg Stockman stole a charity. Full stop. Greg got tens of bil
Paresh Dave / Wired: San Francisco public records: in 2024, Salesforce and Airbnb were among the top tech spenders in the city's 10B program, which lets them hire police officers — A recent attack on
Paul Graham's essay explores parenting philosophy and child-rearing principles, likely drawing on his experiences as a parent and his broader perspectives on education and human development. Sam Altma
HealthBench Professional, our new evaluation of clinician chat tasks, is now available on HuggingFace for easy access. Each example was written, reviewed, and adjudicated by three or more physicians.
Thoth 𓁟 v3.17.0 is out 🚀 Designer Studio just got a serious upgrade + video generation + seamless in-app updates Build full app prototypes, storyboards, pitch decks, docs, landing pages - all in one p
Wall Street Journal: Trump hosted a gala luncheon for leading $TRUMP holders, where he spoke about his pro-crypto policies, but avoided the memecoin's declining value — The president's address touched
Bloomberg: Anthropic says Google is committing to invest 10B now in cash at a 350B valuation and will invest another 30B if Anthropic hits performance targets — Google will invest 10 billion in Anthro
Chinese AI company DeepSeek released a preview of its hotly anticipated next-generation AI model V4 on Friday, saying that the open-source model can compete with leading closed-source systems from US
Vincent Chow / South China Morning Post: DeepSeek V4 Pro has 1.6T total parameters, its largest model by the metric, and V4 Flash has 284B parameters; both models have a context window of 1M tokens —
GPT-5.5 is now available in Devin as an Agent Preview! GPT-5.5 has set a new bar for what's possible with Devin. It runs longer and more autonomously than any GPT model we've tested, surfacing bugs no
Vercel announced the availability of GPT-5.5 through its AI Gateway service, expanding the model options developers can access through the platform. This integration allows developers to leverage Open
Amrith Ramkumar / Wall Street Journal: Lawmakers and lobbyists say the Trump administration has lobbied against legislation that would regulate AI in at least six Republican-led states — ‘I am disappo
More of my notes on DeepSeek V4 - the really big news is the pricing: both DeepSeek-V4-Flash and DeepSeek-V4-Pro are the cheapest models in their categories while benchmarking close to the frontier mo
Sakana AI entered the commercial API market with the beta launch of 'Sakana Fugu,' a sophisticated multi-agent orchestration system previously utilized as their internal secret weapon. Fugu fundamenta
The Information: Sources: Cursor hit 2.7B in annualized sales in March, up ~14x from a year ago, and reported a ~900M loss in its last fiscal year on 770M in total revenue — Weeks before Cursor agreed
arXiv:2604.21860v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly integrated into sensitive workflows, raising the stakes for adversarial robustness and safety. This pape
Cognition AI announced an early preview opportunity for Devin integrated with GPT-5.5 Agent capabilities, inviting users to test the combination at devin.ai. This likely represents an update to Devin'
We’re launching the beta for our new commercial AI product: Sakana Fugu 🐡, a multi-agent orchestration system! Blog: https://sakana.ai/fugu-beta Fugu hits SOTA on SWE-Pro, GPQA-D, and ALE-Bench, and h
CrowdStrike Holdings Inc. today announced the launch of Project QuiltWorks, an industry coalition aimed at helping enterprises find and fix the wave of software vulnerabilities being surfaced by front
LlamaIndex have a most excellent open source project called LiteParse, which provides a Node.js CLI tool for extracting text from PDFs. I got a version of LiteParse working entirely in the browser, us
GPT-5.5 in Codex is a delight to work with: - Super sharp with responses - It understands intent better than any model - Great 'personality' - Gets lots of stuff done without pausing unnecessarily It
Carl Franzen / VentureBeat: GPT-5.5 is priced at 5/1M input tokens and 30/1M output tokens, double GPT-5.4's pricing; GPT-5.5 Pro costs 30/1M input tokens and 180/1M output tokens — After months of ru
A social media post expressing enthusiasm about the hypothetical release of GPT 5.5, with the author humorously suggesting it would be an ideal birthday gift. The post reflects anticipation within the
arXiv:2604.20738v1 Announce Type: new Abstract: We introduce a benchmark dataset for question answering and translation in bilingual Latin and English settings, containing about 7,800 question-answer
arXiv:2511.03690v2 Announce Type: replace-cross Abstract: Agents are now used widely in the process of software development, but building production-ready software engineering agents is a complex task
The White House accused foreign entities primarily based in China of conducting deliberate, industrial-scale campaigns to distill U.S. frontier AI systems using tens of thousands of proxy accounts . W
Molly Taft / Wired: Air permit docs: new gas projects linked to just 11 US data center campuses could emit 129M+ tons of greenhouse gases per year, more than some small countries — A WIRED review of p
Anthropic today quietly (as in silently, no announcement anywhere at all) updated their claude.com/pricing page (but not their Choosing a Claude plan page, which shows up first for me on Google) to ad