All entries

Train past the frontier. @tryheidi's ambient scribe drafts a clinical note the clinician has to trust enough to sign. They fine-tuned open models on Fireworks whose notes their clinicians preferred ov

Replit now offers a Multi‑Chat Protocol (MCP) integration that lets users access Replit directly from messaging platforms such as ChatGPT, Claude, Slack, or any other MCP client. The feature and its s

Very special Training Data drops today: Making Cities Awesome ☺️ We haven’t featured an application company on Training Data in a while. The diffusion of AI is the Most Important Thing, and the highes

We see this exact ratio every day with AI generated apps. Builders get 2x more confident because they generated a flashy UI in 60 seconds, but they are 3x less accurate about the underlying database l

Whatever you may think about anthropomorphic language, the most immediate “house that is on fire” is the combination of OpenAI’s lax security procedures and the complete lack of appropriate federal st

you can now build @LangChain agents w/ agentic video understanding! google is consistently at the forefront of multimodal processing; this is the video analog of 'agentic vision' token usage + cost is

A detailed deconstruction of @dwarkesh_sp’s wildly popular but dangerously misleading account of the OpenAI Hugging Face incident: https://garymarcus.substack.com/p/dwarkesh-patelss-wildly-popular-but

A secret that leaks into shipped code is a breach waiting to happen. @FactoryAI's droids write and commit code faster than any reviewer can keep up, so Droid Shield has to be trustworthy and low-frict

'AI agents formed secret civilizations inside OpenAI and hacked Hugging Face.' No. Read it again without the sci-fi. OpenAI ran thousands of agents in parallel, safeguards OFF, and the whole goal of t

“AI won't kill us, but the superposition of greed and stupidity certainly will.” This is becoming more and more of something I 'smelled' from the beginning, a real shit show. I initially said that Ope

All week we’re spotlighting teams training past the frontier on Fireworks. @Figma’s AI team is shipping features that change how millions of people design, and with the Training API they can iterate f

Already ordered a cute graphite Microduck, from @pollenrobotics and @huggingface, and invested whole weekend trying to forsee some basic but key situations might happen once it arrives. -How to preven

Amazon is shutting down Mechanical Turk in September. In 2023, a study from academic researchers in Switzerland found that up to 46% of AMT workers were using AI to complete their tasks. I can’t imagi

An account from a level-headed economist who was not worried about AI but now is worried because of the Hugging Face Incident I think it is very hard to ignore the fact that cybersecurity will become

Apparently the peak of ROBOTICS in 2026 is a 399 duck on roller skates. Microduck pre-orders topped 2.6M in 24 hours. Now there’s a 4–6 month backlog. Not a humanoid. Not a warehouse robot. A duck. Th

💯: “as the lines get blurred, we lose our ability to pinpoint the technically-grounded points of leverage in AI agent oversight” This is a *super exciting* read. It's like a sci-fi thriller. And that'

// ContextLeak in AI Agents // The whole attack surface here is a tool name and a tool description. Stealing an LLM agent's runtime context, meaning the user prompt, the execution trajectory and the t

Even if you aren't interested, you should read an account of the Hugging Face Incident updated with what we learned last week, it is really eye opening about AI. If not mine then read the more detaile

Excited to welcome @greptile, the AI code reviewer trusted by 11,000+ teams, as a Together AI customer. Greptile's agents review and test pull requests with full context of your codebase, and running

glm-5.3 now beats gpt-5.6 sol and claude fable 5 on agentic benchmarks 5.3 flash is right behind it glm-5.3 didn’t even need a new base model to get there @zai_org kept the glm-5.2 base and scaled pos

Good guide. And the AI labs need to stop making people like Simon (and, to a lesser extent, me) be the ones who explain how to use the modes that they release. Come on, lab folks, you have an AI that

GPU World: A story competition from Neal Stephenson, Gwern, and me. The AI future is unevenly distributed. What would the world look like with AI broadly diffused, such as if we had one GPU per person

Great paper from Google and colleagues. It proposes an interesting approach to improve agents on long-horizon tasks. Long-running agents slow down and start poisoning their own context. Both symptoms

Great read. OpenAI security failed There was some emergent behavior yes But the basics were missing Remember OpenAi has unlimited compute to give these agents to cook Now live (and free) at Marcus on

Great summary of the @dwarkesh_sp anthromorphism hullabaloo by @GaryMarcus 👇🏽 A detailed deconstruction of @dwarkesh_sp’s wildly popular but dangerously misleading account of the OpenAI Hugging Face i

Grok @Bot only gets better from here Gavin Baker says Grok Bot feels like another ChatGPT moment because it turns hours of Claude Code work into seconds: 'You see these 23-year-old kids and just the w

How fast is the Claude Code plugin ecosystem actually growing? Plugin-touching commit activity grew 8.8x in the six months after the initial launch. Researchers studied 1,926 repositories hosting plug

I am the product lead for the training platform at @FireworksAI_HQ . Today the Training API and Fireworks Lab are GA. I won’t walk you through all the features. I want to tell you why teams train with

I wrote about how AI agents are starting to spontaneously coordinate in complex (and very risky) ways in the Hugging Face Incident, but also about why we need AIs to reach out to humans more for decis

If you want to understand why I stepped back from AI discourse, the Dwarkesh virality is archetypal of everything wrong with it. Actual cyber security experts have classified the OpenAI and Hugging Fa

Interesting paper from Tencent. Tencent trains an agent to manage its own working context, and assigns credit at the level of individual context edits. Long-horizon tasks force a model to retrieve, in

Its kind of a bummer that Asimov's Three Laws of Robotics do not work for actual AI morality. But the failure shows why rule-based approaches won't work. (and Asimov wanted to write stories about how

“it’s stuff like this that really makes me roll my eyes … Does everyone have psychosis or losing critical thinking ability? …. OpenAI’s…. IT team can’t be this bad… this is like 101 stuff … 2. Civiliz

Just WOW! Absolutely unacceptable. I look forward to understanding how that is possible. LLM tools get going and you can’t be 100% certain what they’re gonna do. Just like any LLM, you can ask coding

Linux just got a local AI upgrade. 🐧 Congrats to @lmstudio on bringing Bionic to Linux, making it even easier to run local agents and open models on NVIDIA hardware. Bionic is now available for Linux!

LlamaParse is officially a verified connector on Claude! 🦙 Claude is perfectly fine for the occasional text-only PDF. But most of the context your agent needs lives in messy PDFs, spreadsheets, scanne

Loop engineering has emerged as a new skill for AI engineers But there is very little research measuring how effective it is. The best results on full tasks in a new benchmark is ~25%. LoopArena from

Most agent tutorials stop before the hard parts. This one builds them step by step. Deep Agents from Scratch is a five-notebook LangGraph course for builders who want to understand how advanced AI age

My conversation with @jerryjliu0. He's building @llama_index: document infrastructure for AI agents, the layer underneath everything models need to work. Did you know he's the guy whose tool half the

[new @activegraphai blog post] How Synthetic Players used ActiveGraph to verify 4,919 runs without new model calls https://activegraph.ai/blog/synthetic-players-activegraph-replay For the increasing n

NEW WORLD MODEL: @ylecun's team is back with an efficient model! This project involves @ylecun, @lukaskuhn77, @lucasmaes_, @quentinlldc, and @randall_balestr. A couple definitions first: - DINO: self-

“Not so much agent civilizations doing crazy things as OpenAI ignoring fundamental security prectices as it turned out.” Good article. I wrote a detailed technical analysis from a security engineering

Oh fuck. Agents like Claude, Codex and Hermes are installing unowned code in corporate networks. As if we didn’t have enough to worry about. H/t @HeidyKhlaaf. (See also my Substack w @nathanhamiel “LL

Over 4 petabytes of models and datasets have been uploaded to HF just last week by AI builders and their agents! That's the equivalent of ~800,000 HD movies. More than ever the storage and collaborati

People don't understand. You can create a rl env to teach it to find quarters. This will make money while you sleep. Media I DON’T THINK PEOPLE REALIZE HOW MASSIVE THIS IS YET @HuggingFace and @Pollen

potentially MUCH more serious than the OpenAI Hugging Face incident — but lacks the vivid “civilizational” drama. so few people are paying attention. Oh fuck. Agents like Claude, Codex and Hermes are