OneDroid

Apariciones en rankings

Los mejores días en que los posts de esta cuenta entraron en la lista diaria de Debya.

Esta cuenta aún no ha aparecido en un ranking diario.

Posts que le gustaron recientemente

Me gusta públicos de la red Bluesky.

• Michal Bacia@michal-bacia.bsky.social02-11-2026 10:16

  Five builders this week, one problem: the agent's own checks agree with its own mistakes. One AI rated its own work 9/10. A model that hadn't seen it gave 4. The fix: someone who isn't the builder writes the checks first, and the builder never sees them. I test AI-written code. Message me.

  Ver post
• Michal Bacia@michal-bacia.bsky.social31-10-2026 06:47

  What engineers told us about checking an AI agent's work: - Two test layers: one the agent may edit, one it can't touch - Where the ticket is silent, the agent decides. Write those calls down first - To trust a test, break what it guards and watch it fail I test AI-written code. Message me.

  Ver post
• Michal Bacia@michal-bacia.bsky.social30-10-2026 07:21

  I'm not a developer either. I came from the product owner side. You don't need to read AI code to know it works. Write down what it must do before the build, then let something other than the builder check the running app after every change. I test AI-written code. Message me.

  Ver post
• Michal Bacia@michal-bacia.bsky.social29-10-2026 14:11

  Don't try to replace your people with AI. Give AI the work your people hate

  Ver post
• Michal Bacia@michal-bacia.bsky.social29-10-2026 06:48

  If you don't write your test scenarios first, how do you know what "done" means? With AI writing the code, the QA work moves to the start: scenarios from the ticket, before the build, by someone who isn't the builder, run on the real app at every change. I test AI-written code. Message me.

  Ver post

Inicia sesión para ver más

Cuentas que bloquea

En Bluesky los bloqueos son registros públicos.

Esta cuenta no bloquea a nadie.