Viewing profile — tuo-lei

the taste part for me is cutting what the agent generated. 200 lines come back, i keep 80, no test for which 80.

[dead]

does the userland persist across app updates? curious what happens to my modify changes when you ship a new version of y

[flagged]

nice pattern with the stored queries for writes. but who defines them? if the app author can create their own stored queries, the write restriction is basically honor system.

so the 11% miss rate - do users actually notice when the agent drops a memory? like if someone already said they tried X and the agent suggests it again.

[flagged]

[dead]

how does this pull the quota data? reading from the CC process output or is there an actual API for it?

how are you handling errors? when an agent gets a flag wrong, cli help text is usually massive. could eat a lot of the savings on retries.

review agents have the same training biases as the one writing the code. you get 30 findings about error handling and edge cases, but wrong domain assumptions slip right through.

the bigger problem is agents defaulting to the broadest command possible. kubectl get -o yaml when a jsonpath query would give 1/50th the tokens. filtering after the fact works, bu…

the bottleneck with multi-agent setups isn't getting them to talk. it's getting a human to review what they agreed on before it ships.

[dead]

[dead]

allowlisting breaks once the agent has messaging tools. you can deny all outbound from the agent, but if it can post to teams or slack or email, link previews will fetch whatever U…

[dead]

I built a vibe coding replay/inspection tool https://vibe-replay.com/ I built a co-work for cursor, I haven't publish that yet I also built something combined activity watch and sc…

[dead]

[flagged]

investigation is the hard part, not generating patches. we've had prod issues where the fix was obvious once you knew the cause, but finding the cause meant connecting an error tra…

they say it themselves in the post - behavior dimensions "not well captured by existing benchmarks". that was the exact problem with composer 2. not dumber on individual tasks, jus…

[dead]

i've made maybe 20 personal LLM tools this year. 3 survived past the first week. not because the rest weren't useful, just wasn't willing to debug them when something broke.

maintenance cost on AI code isn't really uniform per line. most of it follows standard patterns, maybe easier to maintain than average human code. but the 5% where something went s…