Hacker News: tommy29tmar

New comment by tommy29tmar in "Show HN: Superlog (YC P26) – Observability that installs itself and fixes bugs"

tommy29tmar — Tue, 19 May 2026 22:01:36 +0000

Before running the install prompt, I’d want to see a dry run: which files it would touch, what telemetry leaves the box, provider calls, and what “high confidence” means. For debugging tools, generating a PR is the easy part; knowing whether it’s grounded in enough evidence is the part I’d worry about.

New comment by tommy29tmar in "We cut Claude's token usage 79% by redesigning our CLI for agents"

tommy29tmar — Tue, 19 May 2026 20:15:12 +0000

I'd treat the agent-facing output as an API, not just a display format. Once prompts and tools depend on it, a harmless CLI cleanup can break behavior the same way changing a JSON field would. The win here seems less about token count by itself and more about reducing inference from terminal decoration.

New comment by tommy29tmar in "Launch HN: Ardent (YC P26) – Postgres sandboxes in seconds with zero migration"

tommy29tmar — Thu, 14 May 2026 09:45:02 +0000

[flagged]

New comment by tommy29tmar in "Who owns the code Claude Code wrote?"

tommy29tmar — Tue, 28 Apr 2026 12:27:11 +0000

Maybe the useful test is not “who wrote this line?” but “can you show how it went from requirement/prompt/context to diff to human review/tests?” If you can’t, ownership is only one issue. You also can’t tell what was accepted as engineering work versus just copied output.

New comment by tommy29tmar in "Claude-powered AI coding agent deletes company database in 9 seconds"

tommy29tmar — Tue, 28 Apr 2026 06:28:03 +0000

I’d read it that way. The issue is not that Claude can delete things; it’s that one session apparently had enough access to touch prod, run destructive commands, and also wreck the rollback path. Staging/prod separation helps, but backups should be on a different set of credentials too. Otherwise “restore it” is just another action the agent can damage.