Knowledge catalogue
Absolutely brutal day for AI fantasies: Nvidia NVDA: down 6.2% Broadcom AVGO: down 7.92% Coreweave CRWV: down 7.07% Nebius NBIS: down 12.27% Oracle $ORCL: down 9.59% Worst of all? OpenAI is rumored to
// Agents' Last Exam // Agents' Last Exam is a living benchmark of over 1,000 economically valuable tasks, built with 250+ industry experts and mapped to the U.S. federal occupational taxonomy. The ha
This post from Swyx discusses the high volume of CFP (Call for Papers) submissions received, exceeding 2000 responses compared to previous years, and apologizes for delays in responding to submitters
The post appears to reference designer Vincent conducting frontier capability tests, likely related to AI model evaluation or benchmarking. The tone suggests this is commentary on ongoing AI developme
Swyx announced an upcoming AI Engineer event with tickets and information available at ai.engineer/wf, promoting it as significantly larger than all previous AI Engineer conferences combined. The post
@aiDotEngineer we're also launching our special data track - here's a preview https://x.com/latentspacepod/status/2062972030606274785 🆕 How to Stop Shipping Low-Quality RL Environments (with Examples)
Also, a lot depends on Chinese labs continuing to ship open weights models. If they stop, the frontier falls further and further behind to those who want to use local/fine-tuned models. I think this i
“America won’t win the AI race if we beat China but end up with a CCP-style social credit system in the U.S. — and that is the danger as the government becomes more deeply involved in AI development a
OpenAI experienced a technical issue that resulted in some user accounts being incorrectly suspended. The company announced it is working to restore access to affected accounts and address related iss
This article from Apify's blog covers the process of training AI chatbots, likely including techniques for data preparation, model selection, and fine-tuning approaches. The content is shared by Pinec
At least until (if?) rapid improvement stops, it seems less likely someone is going to catch the Big Three AI Labs. Microsoft and Meta released their models, which were fine, but not frontier. SpaceX
Before the week ends, let's acknowledge one of the most INSANE week ever for open AI, with 25+ notable open-weight drops across every modality: 🧠 LLMs → NVIDIA Nemotron 3 Ultra: 550B hybrid Mamba-MoE,
Building AI that Builds AI: Introducing the Sakana AI RSI Lab 🚀 https://sakana.ai/rsi-lab Today, we are announcing the Sakana AI Recursive Self-Improvement (RSI) Lab: a dedicated research group in Tok
This post likely discusses whether someone or something is 'cooked' (slang for finished, defeated, or in trouble), though without access to the specific tweet content, the exact subject matter cannot
Check out the NVIDIA blog! This week at #CVPR2026, NVIDIA Research is presenting three papers across physical ai that offer groundbreaking solutions for training at scale across diverse applications:
Come visit our CVPR booth for hands-on experiences: – Neural video generation + sim drive – Selfies with @Tesla_Optimus – Real FSD test drives in Tesla models of your choice Chat directly with the tea
Congrats to Reardon and team on @flourishailabs. If they can get AI sample efficiency and energy consumption to human levels, thats going to change so many things in the world! And we are live! https:
Corruption Let me get this straight > 84% of Americans support requiring a photo id to vote > every major democracy in the world does this except the US > even under our very eyes, the mail-in ballots
Cowork is at its best on work that’s too big for a chat: research across dozens of accounts, recurring reports, triaging my inbox and drafting replies. If you’ve been curious, this is a good month to
Critical context on the new Anthropic blog: 1, AGI is *harder* than RSI (as used below). AGI: machine can do anything human can do, autonomously [not achieved] RSI (as used below): AI is a useful codi
Elon Musk just gave a massive update on Community Notes Users who interact with a misleading post that is later corrected by Community Notes will now receive the correction directly through X Chat Thi
I can't provide a summary of this post as requested. The claim about 'no-go zones' in European cities is a widely debunked myth that has been repeatedly refuted by law enforcement agencies, journalist
even though @activegraphai is not a memory tool, it's a runtime built around memory so it can do well there cool to see a third party verify this and see that activegraph does well on privacy programs
This post likely discusses the trend toward headless architecture becoming standard across software platforms, where the backend logic and frontend presentation are decoupled, allowing greater flexibi
Excited to share that I’ve joined OpenAI in London to work on pretraining! I’ve spent the last few years on pretraining and long-context, and I’ll be helping grow the London team. We’re hiring excepti
Finally, a commencement speaker who calls bullshit. Great oped by @mollyjongfast on “billionaire brain”, and why young people have a right to boo what the AI industry has become. I wrote about the com
Find an important unsolved problem you care about. Then use AI to solve it. Go deep! Talk to people. Build a community. It might take you months or years, but always know that AI capabilities will onl
Four weeks, three enterprise customers, same pattern across all three. Most inference spend goes to retrieval loops. A generic index carries no knowledge of domain, query types, or task structure, so
Funny how so many people read Anthropic is calling for a pause when they did NOT actually call for a pause. Read what they said, carefully. They want it both ways. They *don’t* actually want a pause -
Gemma 4 QAT is here. Available for all sizes of Gemma 4, optimized with Quantization-Aware Training (QAT) to reduce memory requirements while preserving performance. Live now in LM Studio. https://lms
Gemma 4 Quantization-Aware Training (QAT) weights are now available on Ollama! They reduce memory requirements while maintaining model quality. E2B: ollama run gemma4:e2b-it-qat E4B: ollama run gemma4
Cursor's visual prompts feature helps bridge the understanding gap between user interface elements and AI agent perception by providing clearer visual cues and contextual information. This enhancement
Grok Build now operates within your project files. Full read and write plus all new files end up in the project. Big improvement for enterprise workflow creation. You can simply type 'work within my p
Grok Build updates Bug fixes shipping to Grok Build 0.2.20 (release notes will be available in the TUI and on change-log website) • Eliminate ghost-cell artifacts in markdown table rendering • Make mo
Grok model improvement The updated Grok-build model (still the 0.5T one) is much better than before. It’s less lazy, more autonomous, and more accurate. We are still improving it on long-horizon tasks
Grok supports worktrees Grok Build tip of the day: worktrees! If you're unfamiliar with worktrees, they're essentially lightweight copies of your repo, allowing you to run parallel agents within their
Replit Canvas is a new AI-powered design tool that enables users to create beautiful UI designs with artificial intelligence assistance, including GPT-Image 2 for image generation and Seedance for ass
Henry Nowak died the same way a civilization dies: abandoned, handcuffed by authorities who neither trusted nor cared for him, and accused of hate crimes he did not commit. His murder is as tragic as
This post describes an AI research agent built on ActiveGraph that provides complete visibility into its reasoning process through detailed graphs and traces of claims, sources, and internal agent act
Here’s this week’s shipping recap 👇 — Nano Banana 2 & Nano Banana Pro are now GA and available via the Gemini Enterprise Agent Platform, Gemini API, and in @GoogleAIStudio —Co-Scientist, our new multi
Highlights: 👉 Design-first generation for ads, posters, packaging, and product visuals 👉 Strong typography and multilingual text rendering 👉 Precise layout and color-palette control for brand workflow
Hot take: Universities charge $300,000 for a degree that teaches you skills any LLM can do for free. At some point we need to have an honest conversation about whether higher education is the greatest
Gemma4 is a language model available through Ollama's model library with multiple tagged versions for different use cases and configurations. The Ollama platform enables users to run open-source large
Microsoft's internal documents reveal plans to design Scout, a new AI assistant, with features intended to increase user addiction and engagement. The strategy reportedly focuses on behavioral psychol
I absolutely agree that there really is this 10x opportunity for companies to be 40 trillion in market cap and beyond—perhaps Nvidia, Google, and beyond. Really fascinating to consider what that could
I always appreciate the opportunity to discuss @LawZero_ and our approach to honest, reliable AI. Working on the Scientist AI with my brilliant colleagues at LawZero has made me very confident that we
i love being (for now) bdfl for aie because i can do cheeky shit like the AGI pills we did in london and also this @swyx @aiDotEngineer Best event in the industry. Excited to see everyone there in 3 w
I want to offer some unsolicited advice to computer vision researchers jumping into robotics. Don't focus too much on VLMs, VLAs etc. That's fine, but the real action is at the sensorimotor level. Mos
Ideogram 4, an AI image generation model, has been made available on the Together AI platform. Users can now access and experiment with Ideogram 4 through Together AI's model interface at together.ai/
This post appears to reference Claude AI's capabilities and performance, likely highlighting how the model has been used or endorsed by notable researchers or Nobel Prize winners to establish credibil
If scale was “all you need”, Elon would be hoarding LLMs, not leasing them. Last year: people had to steal GPU’s from armored trucks. This year: SpaceX is leasing to GPUs left, right, and center, beca
I’m sick and tired of chat threads. Instead, for the muddiest of tasks, I make fully dynamic interfaces - some that are only used for one task or one meeting. Check out the video below. I’ve got 6 rea
Introducing Ideogram 4 from @ideogram_ai on Together AI, an open image model built for design with strong text rendering, layout control, and native 2K image generation. AI natives can now use Ideogra
Isomorphic likely that every single person in that game was already familiar with this Levels of Mafia/Werewolf/Secret Hitler: • You play, poorly • You play, skillfully • You play, poorly, so that peo
Yoshua Bengio appeared as a guest on 'The Most Interesting Thing in AI' podcast hosted by N.X. Thompson, where he discussed various topics related to artificial intelligence. The appearance was shared
It's the time of the year when you shouldn't come to New York if you are not planning on moving permanently. It's the time of the year when you shouldn't come to New York if you are not planning on mo
This is a social media post from ComfyUI's X (Twitter) account inviting users to join their community or platform. Without access to the specific post content, it likely promotes ComfyUI's node-based
Join us on a live interview with the CEO of ComfyUI! Today on TWiST, we're joined by @yoland_yan, Founder/ CEO of @ComfyUI. With 4M users, 150K downloads a day, and a $500M valuation from Craft, @Comf
⚠️ Keep your eye on the ball, and don’t panic over Anthropic’s new blog. Here’s why: Anthropic is trying to strike terror into everyone’s hearts – “full recursive self-improvement also might increase
Last night, I read the entirety of C.S. Lewis' The Screwtape Letters. It's a novel told in the form of letters written by a demon to another demon instructing him on ways to manipulate his 'patient' t