~/ home~/ guides~/ ai-reviews~/ prompts~/ cheatsheets~/ trendsUpdated 1 week ago
~/tags/intermediate
§ ARCHIVE · 3 ENTRIES

#Tag · intermediate

All entries, filed and dated.

3 entries updated May 7
3 entries Sort:
All Featured New
APR 23 10 min
eval
Evals without LLM judges: a harness that catches regressions
How I score LLM pipelines without an LLM-as-judge. Deterministic graders, property-based checks, and the 4 reasons a judge model keeps biting you in production.
evals intermediate
7.9 peer score
read →10 min
APR 23 10 min
chunking
RAG defaults 2026: chunks, rerankers, 3 settings that matter
The chunk size, overlap, rerank, and top-k values that moved my retrieval accuracy from 74% to 91%. Tested on a 1,400-chunk corpus with a ground-truth answer set.
intermediate rag retrieval
8.1 peer score
read →10 min
APR 23 13 min
intermediate
Structured outputs, three years in: the one pattern that survived
Three years of shipping LLM structured outputs in production. The one pattern that survived, the three that did not, and the strict-JSON failure rate I run at today.
json schema structured
9.1 peer score
read →13 min
⌕ esc