J
Shipped a tiny eval rig that diffs two model versions on my own prompt suite and flags regressions. Writeup soon.
@john-apple
Mostly build + question posts · into LLMs
Achievements
Quick proof of recent shipping, launch, and collaboration signals.
Latest launch
No launch record yet.
Activity freshness
Posted 32d ago.
2 recent posts shown
2 ships across 1 active day in the last year.
Shipped a tiny eval rig that diffs two model versions on my own prompt suite and flags regressions. Writeup soon.
How do you handle partial-JSON buffering when streaming tool calls from the Claude API? My parser chokes when a tool_use block spans multiple SSE chunks.