Viewing profile — intheleantime

[flagged]

Building AI coding tools, there are two common options. The AI suggests code and you run it. Or the AI runs code on your actual machine. We decided to go with the third option: The…

I built an MCP server that connects coding agents (Claude Code, Cursor, OpenCode, Codex) to a collaborative workspace where your team and other AI models can review what the agent …

There is something to be said about that, I agree. For that reason you can turn off memory inside a chat thread and also create temporary ones that do not use memory.

Thank you and great question. Right now, feedback is qualitative only. (Surveys, feedback buttons, controlled user tests). We are trying to build AI evaluators but they suffer from…

lol the I stands for “I think I know everything”

Hi HN! I have been working on AI agent Flows for some time now and always found it annoying to have to redeploy my application for small changes to flows, prompts, model definition…

Thanks for the feedback! I agree with the general sentiment. At the same time we want to target companies that are aware of their neurodiverse workforce.

Thanks! There is so much more to come!

This is something we thought about a lot as well; right now it's just an emoji rating. Once set the picker changes to a checked mark and is not visible to others. The data is store…

Not just investors. I had long conversations with legal about that to better understand why it is necessary. Don't get me wrong, I don't like it either but here is the deal: - I wa…

That is the entire cycle from browser, to server and back + js execution. As mentioned in a comment below php execution including db call is: P95 is 120.9ms P99 is 634.11ms Which m…

PS I forgot to mention that we have Sentry profiling. Full Application load (php side) P95 is 120.9ms and P99 is 634.11ms