The Brief
New briefs daily around 7 AM Eastern
A typed classifier out-judges LLMs on agent scoring
LangChain tested TypeSafe AI's Jev, a typed classifier rather than a text-generating LLM, as an agent-eval judge. It matched a human reviewer on every one of 500 repeated decisions while costing a fraction of a cent per call, far less than Claude's LLM-judge cost.
- 01Watch
FlashNorm folds RMSNorm into weights for a 33% speedup
Filip Makraduli's FlashNorm folds a transformer's norm layer into its projection weights and overlaps the remaining divide on a separate CUDA stream, cutting norm-plus-projection cost by a third with no retraining needed.
- 02Watch
vLLM scheduler bug made decode run before prefill
A rare vLLM bug corrupted about one in a thousand prompts with no error. The cause: a scheduler race let decode run before prefill for Jamba's Mamba layers, computing a fresh request over a stale prior state.
- 03Read
Brood War Bench pits coding agents in real-time StarCraft
Ben Swerdlow ran 171 real-time StarCraft matches between Codex, Claude, and Grok models, surfacing concrete failure modes in continuous, multi-unit agent control that single-turn benchmarks miss.
- 04Read
PlanetScale ships Tin, a full-text search engine for Postgres
PlanetScale released Tin, a GA Postgres extension with boolean, phrase, fuzzy, and BM25-ranked search that keeps correct transactional visibility, cutting a common reason teams bolt on Elasticsearch.
- 05Read
HEIF Heist widens libheif bug fallout past OpenAI
Hacktron's fuller HEIF Heist disclosure shows the libheif bugs behind Tuesday's OpenAI account takeover also reach Slack, Meta, GitHub Enterprise, Rails, and Next.js through indirect dependencies.
A dated brief from the vibe-coding frontier. Today’s Intel.