✨ Kyle Wild ✨
Reading
Fine-Tuning Medium-Scale LLMs for Joint Intent Classification and Slot Filling: A Data-Efficient and Cost-Effective Solution for SMEs
This, plus advancements from Qwen + Kimi + GPT-OSS, seems very promising for 'step 1' in an agentic chat workflow.
The world's most popular search engine and gateway to the web - simple, fast, and ubiquitous.
GPT‑5-Codex and upgrades to Codex
OpenAI releases a modified model just for their Codex CLI. Simon Willison, as usual, has the best coverage.
Defeating Nondeterminism in LLM Inference
Now this is an effing essay.
Writing
Terminal-based Agentic Programming Roundup
SST's opencode and OpenAI's Codex are both now viable as daily drivers for real engineering work. A month ago, the only things I could actually use were Amp Code and Claude Code. That is no longer tru...
The Rise and Fall of "Vibe Coding"
If you played around with Cursor and Sonnet 3.5 a few months ago and found it lacking, join the crowd – but don't get attached to your conclusions.
Tomasz Tunguz says we should make fewer, more complex & powerful tools for today's frontier models. I've found the same thing to be true in my work at Endgame and my side projects like
linctl.