Two new papers tested LLM synthetic data against real survey takers and peer reviewers. Every model missed the same things. Here is where I still…
Tool schemas quietly weaken your model's refusal behavior. Here is what a new agent-safety paper found and the checks I now run before shipping any…
RAG or fine-tuning? One question settles it most of the time. What the benchmarks leave out, where retrieval quietly fails, and the hybrid split I…
Strict mode guarantees your JSON matches the schema, not that the values are right. The optional-field trap that cost me a day, and the checks…
Prompt tone changes LLM output token count by up to 44%, per a new arXiv paper. Here is what I measured on my own prompts,…
Adding more few-shot examples can quietly make your LLM prompt worse. Here is what the over-prompting research found and how I size the example set…
The built-in commands worth memorizing, how custom commands actually work in 2026, and the gotchas nobody documents: namespacing, argument indexing, and the SlashCommand tool.
SLM vs LLM in 2026: why most of your model calls do not need a frontier model, the small-first cascade pattern that cuts cost, and…
AI coding agents read whatever you point them at, including issues written by strangers. How prompt injection reaches Cursor and Claude Code, and what actually…
AI SDK 7 landed in June 2026. I deleted my hand-rolled agent loop, added tool approvals to the one tool that could ruin my day,…