Rethinking KV Caching For Production Inference
A practitioner's guide to KV cache management in production.
Lire
sqlite-migrate 0.2
sqlite-migrate 0.2
Release: sqlite-migrate 0.2 The version that retires the library, instead implementing a compatibility shim against the new sqlite-utils 4.0 dependency. Tags: sqlite-utils
Lire
github-code Web Component
github-code Web Component
Tool: github-code Web Component An experimental Web Component built using GPT-5.5 and the following prompt: let's build a Web Component for embedding code from GitHub <github-code href="https://github.com/simonw/sqlite-ast/blob/437c759129154f05296324a7f82aa1246340dd14/sqlite_ast/parser.py#L9-L18"></github-code> It takes URLs like that, converts them to https://raw.githubusercontent.com/simonw/sqlite-ast/437c759129154f05296324a7f82aa1246340dd14/sqlite_ast/parser.py, then uses fetch()…
Lire
sqlite-utils 4.0
sqlite-utils 4.0
Release: sqlite-utils 4.0 See sqlite-utils 4.0, now with database schema migrations for details. Tags: sqlite-utils
Lire
Ordinary Engineers, Not Heroic Inventors
In the 1980s, Japan led the world in semiconductors, consumer electronics, and computer hardware, the industries everyone assumed would decide the next phase of economic power. Japan won them and still did not overtake the United States in the information revolution that followed. Jeff Ding, a political scientist at George Washington University, opens his book […]
Lire
Intelligence is Free, Now What? <br> Data Systems for, of, and by Agents
... government of the people, by the people, for the people ... The cost of AI is dropping rapidly. GPT-4-class capabilities cost roughly $30 per million tokens in early 2023; today the same runs under $1, and some providers are pushing costs below $0.10. Across benchmarks, inference prices have fallen between 9x and 900x per year, with a median decline near 50x. Even frontier models are getting dramatically cheaper each generation, with open-source models following closely behind. And…
Lire
sqlite-utils 4.0rc4
sqlite-utils 4.0rc4
Release: sqlite-utils 4.0rc4 The last RC before the 4.0 stable release. Mainly implements feedback from a detailed review by Claude Fable 5. Tags: sqlite-utils, claude-mythos-fable
Lire
tencent/Hy3
tencent/Hy3
tencent/Hy3 New Apache 2.0 licensed model from Tencent in China: Hy3 is a 295B-parameter Mixture-of-Experts (MoE) model with 21B active parameters and 3.8B MTP layer parameters, developed by the Tencent Hy Team. Following the Hy3 Preview launch in late April, we gathered feedback from 50+ products and scaled up post-training with higher quality data. Today, we introduce Hy3, which outperforms similar-size models and rivals flagship open-source models with 2-5x parameters. It also shows…
Lire
The Reward Signal Problem for Agents
The full RL nanodegree, covered with implementation.
Lire
sqlite-utils 4.0rc3
sqlite-utils 4.0rc3
Release: sqlite-utils 4.0rc3 I hoped to release sqlite-utils 4.0 stable this weekend, but as I worked through the backlog of issues and PRs with a combination of Claude Fable 5 and GPT-5.5 the changelog since rc2 kept getting bigger. The biggest new feature is support for introspecting and creating compound foreign keys - a feature that involves a subtle breaking change to table.foreign_keys and hence needed to land for the 4.0 stable release. sqlite-utils also now follows SQLite's convention…
Lire
How to Reduce LLM Costs by 50-60% Using Model Routing
...explained with code.
Lire
sqlite-utils 4.0rc2, mostly written by Claude Fable (for about $149.25)
I wrote about the sqlite-utils 4.0rc1 release a couple of weeks ago. Since we only have Claude Fable on our Max subscriptions for a few more days, I decided to see if it could help me get to a 4.0 stable release that I felt truly comfortable about, since I try to keep to SemVer and like my incompatible major versions to be as rare as possible. I started with this prompt, in Claude Code for web on my iPhone: Final review before shipping a stable 4.0 release - very important to spot any last…
Lire
sqlite-utils 4.0rc2
sqlite-utils 4.0rc2
Release: sqlite-utils 4.0rc2 See sqlite-utils 4.0rc2, mostly written by Claude Fable (for about $149.25).
Lire
Building a World Map with only 500 bytes
Building a World Map with only 500 bytes Iwo Kadziela (assisted by Codex) figured out a way to generate a credible ASCII world map using 445 bytes of data: The key trick is to use deflate compression, which is then wired together using this neat snippet of JavaScript. I didn't know you could use fetch() with data: URIs like this: fetch('data:;base64,1ZpLsgIxCEXnrM...==').then( r => r.body.pipeThrough(new DecompressionStream('deflate-raw')) ).then( s => new Response(s).text() ).then( t…
Lire
Better Models: Worse Tools
Better Models: Worse Tools
Better Models: Worse Tools Armin reports on a weird problem he ran into while hacking on Pi: The short version is that newer Claude models sometimes call Pi’s edit tool with extra, invented fields in the nested edits[] array. And not Haiku or some small model: Opus 4.8. The edit itself is usually correct but the arguments do not match the schema as the model invents made-up keys and Pi thus rejects the tool call and asks to try again. That alone is not too surprising as models emit malformed…
Lire