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

#Tag · analysis

All entries, filed and dated.

1 entries updated May 7
1 entries Sort:
All Featured New
APR 23 11 min
analysis
Long-context evals diverge from reality: the 1M-token gap
Vendor 1M-context numbers keep outperforming my production RAG task by 30+ points. The three reasons the benchmarks lie, and what I trust instead.
context
— unrated
read →11 min
⌕ esc