Momentum in ML, Explained Visually and Intuitively!
(a popular ML interview question)
Lire
Experience Mapping Matters More the Faster You Move
Experience Mapping Matters More the Faster You Move
AI is changing how fast organizations can move. Ideas that used to take months to build now take days, sometimes hours. That sounds like good news, and it is. But it creates a new problem. When execution is fast, teams can move in many directions at once. Marketing can ship a new campaign, product can […]
Lire
llm 0.35
llm 0.35
Release: llm 0.35 New OpenAI model: gpt-6-astra for GPT-6 Astra. Tags: openai, llm, gpt-6-astra
Lire
Creepy crawlies
Creepy crawlies
Creepy crawlies Konstantin Ryabitsev discusses how bad the "background radiation" of abusive crawlers has become from the perspective of git.kernel.org, the official Git repository for the Linux kernel: TL;DR: we spend more CPU cycles rendering commits for scrapers than we spend on all other kinds of legitimate access, including git clones. At any one time, across 5 geo-distributed nodes, there are 14 CPU cores doing nothing but rendering git commits as html. I worry about this a lot from the…
Lire
Quoting Jakub Pachocki
Quoting Jakub Pachocki
The strongest argument I see for continuing to train much smarter models quickly is the need to build defensive systems against the dangers posed by other AI. [...] We will need powerful, aligned AI for defense; to secure infrastructure, to protect against rogue agents in real time, and to invent entirely new protective measures. This will be a primary focus of OpenAI’s deployment efforts. At the same time, even with the uncertainty that comes from anticipated broad AI progress and the need to…
Lire
LLM Routing Can Cost More Than Not Routing
...covered with a production-grade router for LLM apps.
Lire
Video compressor
Video compressor
Tool: Video compressor I recorded a short demo video of my Equal Earth animation on my phone and wanted to publish an optimized version of that video (using FFMPEG) on my blog, so I had Claude Fable 5.1 in Claude Code for web build me this tool using the WebAssembly build of FFMPEG. Tags: ffmpeg, video, webassembly, claude, claude-code, claude-mythos-fable
Lire
Mercator ↔ Equal Earth
Mercator ↔ Equal Earth
Tool: Mercator ↔ Equal Earth I got curious about the Equal Earth map projection that was recently voted on at the UN so I had GPT-6 Astra (medium) in ChatGPT Work build me this animated transition between Mercator and Equal Earth using D3. Tags: geospatial, d3, vibe-coding, gpt-6-astra
Lire
Research acceleration: The view inside OpenAI
Research acceleration: The view inside OpenAI
Research acceleration: The view inside OpenAI Apparently today is RSI day at OpenAI, for Recursive Self-Improvement - I think it's their new AGI. Both this piece and the new essay An Alien Mind (by Chief Scientist Jakub Pachocki) talk about it, and this one doesn't even bother to expand the acronym. Included are details on how OpenAI's own research team are using coding agents. Like pretty much everyone else 2026 has been the year that agentic engineering really took off at OpenAI, best…
Lire
KV Cache Engineering for LLM Serving
12 techniques to manage KV cache in production.
Lire
The purpose of DNS is to spread scams
The purpose of DNS is to spread scams
The purpose of DNS is to spread scams Terence Eden shares some daunting statistics in support of his take that "the Domain Name System's purpose seems to be a vector for criminals to run scams on people at a terrifyingly high rate". On this Interisle report (via Andrew Campling), Terence says: It says 85 million new registrations of gTLDs were made in 2025. Of those 8.5 million were added to blocklists by May 2025. It reckons that a 10% abuse rate is the likely floor for these numbers and it's…
Lire
There's No Limit to How Bad Code Can Get
There's No Limit to How Bad Code Can Get
My comment on There's No Limit to How Bad Code Can Get — Lobste.rs.[In reply to a comment about burning it down to start from scratch when technical debt becomes overwhelming] In my experience it's so rare for that to work. You announce the old thing is irrecoverably drowning in tech debt. You spin up a team to rewrite it from scratch. Work begins. Meanwhile the old thing remains a moving target: it's running the core business, so changes are still necessary. The developers working…
Lire
Quoting Zach Kehs
Quoting Zach Kehs
If you continue to add floors and rooms to a building forever, it will collapse. Software faces no such constraint. The code can always get worse. There can always be a new layer of indirection or a reduction in performance. — Zach Kehs, There's No Limit to How Bad Code Can Get Tags: technical-debt
Lire
Introducing GPT-6 Astra for developers
Introducing GPT-6 Astra for developers
Introducing GPT-6 Astra for developers Blink and you'll miss it, but there's a familiar creature at 1m59s: Across the board, Astra has more attention to detail, better understanding of the user's prompt, and can build more sophisticated outputs. In particular, it excels at building 3D models. I've seen it make incredible renderings of gardens, shipyards, animals, cityscapes, even Dyson spheres. Astra really does believe in putting a red neckerchief on a pelican riding a bicycle. Via Hacker News…
Lire
Using Blender with coding agents on macOS
Using Blender with coding agents on macOS
TIL: Using Blender with coding agents on macOS I've been having fun with Blender in ChatGPT Codex on my Mac recently. Getting it to work with coding agents is really easy: install the full Mac application from blender.org and run a prompt like this: Use the already install /Applications/Blender to render a scene of a pelican riding a bicycle In this case I followed that up with these two prompts: OK add a background and a lot of flair Then: OK make it a whole lot better And got this image,…
Lire