This week
- For the first year or so, one of the most annoying problems faced by building with AI was getting them to generate output with consistent formatting. Go find someone who was working with AI in 2023 and ask them what they did to try to get LLMs to consistently output JSON. You’ll...
- OpenAI partially released a new model yesterday called GPT-5-Codex-Mini, which they describe as "a more compact and cost-efficient version of GPT-5-Codex". It’s currently only available via their Codex CLI tool …
- You might have seen an article making the rounds this week, about a young man who ended his life after ChatGPT encouraged him to do so. The chat logs are really upsetting. Someone two degrees removed from me took their life a few weeks ago. A close friend related the story to...
- by Dylan Huang on November 7, 2025From fixed-shape compute to variable-shape, memory-coupled inference For years, production ML looked like images or fixed-duration signals—tight, predictable tensors. You sized for FLOPs, picked a batch size, and rode the throughput curve. LLMs...
- Learn how to use the Gemini API File Search tool with JavaScript/TypeScript to build a Retrieval-Augmented Generation (RAG) system....
Last week
- another talk I am giving at Mastra's TypeScript AI conf today https://docs.google.com/presentation/d/1NnQ3H5Bki3vWRRJdVXoCFJ5dsNKH9QrC-eEQ2Z8olck/edit?usp=sharing...
- Amazon is doing more mass layoffs, claiming it wants to be more nimble. But are job losses really about US economic fears, and how Amazon’s retail business will be affected?...
- You want to paint a wall. The fastest way to start is to open the paint tin and start rolling out the color. Except that’s not the quickest way to paint a wall, as expert painters know. If you give a professional this job, they won’t touch the paint until the surface has been...
- Content is infinite and free now. Trust isn't. We're abandoning digital channels entirely because we can't tell what's real anymore. The post The trust collapse: Infinite AI content is awful appeared first on Arnon Shimoni....
- The DX AI-assisted engineering: Q4 (2025) impact report offers one of the most substantial empirical views yet of how AI coding assistants are affecting software development, and largely corroborates the key findings from the 2025 DORA State of AI-assisted Software Development...
- Unmesh Joshi finds LLMs to be a useful tool, but explains why their help becomes illusory if we use them to shortcut the learning loop that's an essential part of our professional practice. more…...
- I’m very concerned about the security dangers of LLM-enabled browsers, as it’s just too easy for them to contain the Lethal Trifecta. For up-to-date eyes on these issues, I follow the writings of coiner of that phrase: Simon Willison. Here he examines a post on how OpenAI is...
- In early September a poem about AI started circulating on social media, with a publication date of 1961. At first it just seemed too cute to me and I thought it might be fake, or written by an LLM, passed off as written by a person back in 1961. But with a little bit of …...
- I have been learning about memory in AI agents, and found myself overwhelmed by all the new terms. It started with short-term and long-term memory. Then it became even more confusing with procedural, episodic, and semantic memory. But wait. Semantic memory reminded me of a...
- After the LLM judge hype curve crashes, what will come after?...
Two weeks ago
- More devs are experimenting with kicking off coding agents in parallel...
Rows per page
