Home
Storia in 1 fonti
Semantic caching our flaky-test summariser: 58% fewer LLM calls
TL;DR: Our internal flaky-test summariser at Buildkite was firing ~40k LLM calls a day, and most were...
Raccontata da
dev.to
Timeline cronologica
- ·
Fault-injecting our LLM provider to trust Bifrost fallbacks
TL;DR: We run an LLM-backed build-failure summariser at Buildkite. To stop a provider wobble from...
- ·
Semantic caching our flaky-test summariser: 58% fewer LLM calls
TL;DR: Our internal flaky-test summariser at Buildkite was firing ~40k LLM calls a day, and most were...