RecommendedAnthropic
Claude
The AI assistant that actually helps you build things, not just talk about them.
Paths, prototypes, proof
Latest posts
All posts →
Constrained decoding: forcing an LLM to emit valid JSON
Watch a schema grammar mask illegal tokens, renormalize the survivors, and force a simulated LLM to emit valid JSON while a prompt-only run fails beside it.
Continuous batching: why your API latency varies
A GPU scheduler timeline runs static and continuous batching on the same requests. Watch idle lanes refill, queues drain, and latency percentiles move live.
HNSW vector search: how a layered graph finds neighbors fast
A layered graph walks coarse to fine toward your query, checking a fraction of the vectors a full scan would. Tune efSearch and M and watch recall respond.
Recommended solutions
All recommendations →Third-party products we've reviewed and recommend. Some links are affiliate.
