Sentry CEO: Claude's memory seems to just inject problems into context
zeeg · x · 2026-11-20
David Cramer, CEO of Sentry, says Claude's memory feature appears to keep "injecting problems" into context rather than helping. A candid first-hand negative take on agent memory from a leading dev-tool founder.
More from coding & agent
- Google Cloud outlines 5 research-backed patterns for agent orchestration — rseroter · 2026-11-20
- Ticket to Production: Mapping the Agentic SDLC with Six Agents and Human Gates — Pavan_Belagatti · 2026-11-20
- UI isn't dead: chat alone is far from enough for human-agent communication — HaijunXia · 2026-11-20
- tldraw is becoming a favorite way to give quick UI feedback to coding agents — max__drake · 2026-11-20
- Claude connectors as a 'synthetic ontology': a bull case challenge to Palantir's moat — pdamodaran · 2026-11-20
- Perplexity: auto skill config cut tool-call failures by 11% in production test — perplexity_ai · 2026-11-20