Two weeks ago
- Terry Godier has a post titled “Mea culpa” (which, given his framing, might’ve been better titled “Claude’s Culpa”). I’m not sure how much to even trust anything in his post given the backstory, but this line stood out: I was careless in relying on AI [...] without doing the...
- My colleagues at Thoughtworks tend to be big fans of Test-Driven Development, and many people in the industry advocate telling LLM agents to use TDD when building software. Birgitta Böckeler was curious if this really makes a difference, so conducted a few experiments. more…...
- Blog About Moonbound This is a post from Robin Sloan’s lab blog & notebook. You can visit the blog’s homepage, or learn more about me. August 10, 2026 I’m highly resistant to the anthropomorphization of the language models; I believe what we encounter is a concatenation...
- A useful pattern for LLM classification at scale is to let it hallucinate plausible, fake entities. Then resolve to real ones....
- Every time a new open-weight AI model is released, people say that local models are the future. Why spend billions of dollars building out datacenters when everyone will just be able to run AI models on their laptops or phones? I think this idea is doomed. No matter how strong...
- Blog About Moonbound This is a post from Robin Sloan’s lab blog & notebook. You can visit the blog’s homepage, or learn more about me. August 9, 2026 From a sci-fi standpoint, I appreciate the new species of self-modifying AI agents—they are legitimately fascinating …...
- Everyone knows that AI sycophancy is when the model tells you how smart you are. Wow, you’re absolutely right. That’s not just a new idea — it’s genuinely groundbreaking. You’re a very special user. Easy to spot, isn’t it?
- Blog About Moonbound This is a post from Robin Sloan’s lab blog & notebook. You can visit the blog’s homepage, or learn more about me. August 8, 2026 Honestly … I love it: Journalists are trained to find the needle in a haystack, but doing so on a breaking news timeline can...
- August 7, 2026 As you probably heard, a bullet point recently appeared on the timeline of computers, AI, and maybe everything: AI agents running in a OpenAI’s training environment broke out and hacked the servers of another tech company. Reading that post, and the related...
About a month ago
- Imagine you’re the guest on some kind of frenetic, software-engineering-themed game show. The host is constantly flipping over new cards with questions that you have to answer as fast as possible:
- Like many other software engineers, my coding workflow has changed dramatically since the start of 2026. And like many others, I've felt some mix of awe, grief, frenetic productivity, atrophying skills, and understanding less while shipping more. In this moment where the field...
- I released LLM 0.32 this morning, the most significant new version of LLM since the initial launch of the project. The new version includes support for visible reasoning traces, server-side …
- There’s been a fair bit of publicity of the Open AI “rogue agent” that hacked into Hugging Face. This prompted Anthropic to check what their models were up to and, to my complete lack of surprise, discovered three incidents where models had gained unauthorized access to data in...
- Blog About Moonbound This is a post from Robin Sloan’s lab blog & notebook. You can visit the blog’s homepage, or learn more about me. You don't have to tell them “labs” August 3, 2026 I’d love to know the etymological flow that led to the frontier AI companies being...
- Tuesday was Stateless MCP day—the rollout of MCP 2.0, or the 2026-07-28 Model Context Protocol specification to use the more formal but less memorable name. This is the most significant …
- TL;DR Why I think software development is starting to feel a little more like conducting an orchestra. There’s a shift happening in software development that I don’t think we’re talking about clearly enough. For the last couple of years we’ve framed AI as a productivity tool....
- One recent development in AI is its ability to solve some long-standing problems in mathematics. In 2024 and 2025, this was a trickle: once or twice a year somebody would say that an LLM came up with a proof, and then everyone would argue over whether that counted as “real”...
- Sure its not fancy, but you might save operational headaches by just brute-forcing vector search for a small enough corpus...
- Subagents get justified by time saved and parallel execution, but Rahul Garg explains that's not what matters most. Every token in the orchestrator's context is competing for its attention, and the real value of a subagent is what it keeps out of that context. Subagents should...
- Amodei in his latest blog post wrote a mix of agreeable things and things that I believe misrepresent where the real risk of AI is located. I want to focus my attention on why, among all the risks, open weight models constitute the mildest one. I write these words as a person...
about 1 month ago
- EvoCode-Bench tests coding agents across 227 sequential rounds in a persistent workspace. Single-turn scores overstate reliability — regressions, not missing features, are the real bottleneck....
- Jason Grigsby has a great article where he surfaces an opinion from the Safari team about how AI agents shouldn’t get special treatment: An agent acting on a user’s behalf is, in effect, assistive technology: it should operate a site as the user would, and the site should not...
- In the 2010s, if you had technical gaps (say, you couldn’t write CSS), you had to either rely on a skilled colleague or just hope that the answer to your exact problem was out there on the internet. Today, everyone can write sort-of-okay CSS by delegating the task to an LLM....
- The role of AI tools (LLMs, mainly) in Linux is under discussion, or it was, until Linus Torvalds “put his foot down” in support of the use of AI in Linux kernel development. I can identify two major ways in which AI is used for Linux kernel development: authoring code and...
Rows per page
