Discussion

• @alexalbert__ Alex Albert on x

  Goodbye —dangerously-skip-permissions, hello auto mode

• @kimmonismus @kimmonismus on x

  This is insane. They literally drop every freaking day. Today: Claude code auto mode. Permission decisions on your behalf.

• @yuchenj_uw Yuchen Jin on x

  RIP —dangerously-skip-permissions

• @trq212 @trq212 on x

  turns out being an AI safety company is useful for when you need to make sure AIs can run safely

• @claudeai Claude on x

  Before each tool call, a classifier reviews it for potentially destructive actions. Safe actions proceed automatically. Risky ones get blocked, and Claude takes a different approach. This reduces risk but doesn't eliminate it. We recommend using it in isolated environments.

• @kloss_xyz Klöss on x

  POV: you turn on claude code auto mode [video]

• @cryptopunk7213 @cryptopunk7213 on x

  lol its literally been <24hrs and anthropic shipped another banger feature: auto mode now claude code can autonomously review, approve or deny tasks that require human permission - literally removing humans from the loop. autonomous agents. - claude will review... claude code [vi…

• @eptwts @eptwts on x

  the 80/20 of AI rn is just getting very familiar with the anthropic ecosystem lmfao...

• @pawelhuryn Paweł Huryn on x

  We went from “human in the loop” to “AI in the loop.” Auto mode doesn't skip permissions — it adds a classifier that reviews every tool call before execution. Blocks destructive operations, data exfiltration, prompt injection. If Claude keeps pushing blocked actions, it

• @jarredsumner Jarred Sumner on x

  this is the ideal permission UX. you don't want claude to do dangerous stuff, and you don't want to have to think about sandboxes

• @claudeai Claude on x

  New in Claude Code: auto mode. Instead of approving every file write and bash command, or skipping permissions entirely, auto mode lets Claude make permission decisions on your behalf. Safeguards check each action before it runs. [video]

• @deanwball Dean W. Ball on x

  amazing to do a bit on this website and then see it get obsoleted in the same hour [image]

• @bcherny Boris Cherny on x

  no 👏 more 👏 permission prompts 👏

• @deanwball Dean W. Ball on x

  The end state is that you don't “use the computer” like you used to, or do now. The computer will use itself. With time, your use of the computer for work will look more and more like you are playing a strange video game, which will itself be built in large part by computers.

• @lukashozda Lukáš Hozda on x

  Excited to see this end poorly

• @mycoliza @mycoliza on x

  the inmates are running the prison

• @justalexoki @justalexoki on x

  only a pussy would opt for auto mode over —dangerously-skip-permissions. live a little, you frickin nerd

• @timkellogg.me Tim Kellogg on bluesky

  Claude Auto Mode  —  not sure about you, but i keep claude in —dangerously-skip-permissions 100% of the time  —  Auto Mode has a classifier to detect potentially destructive actions, so it's not as painful to use non-dangerous mode.  Strictly safer!  —  claude.com/blog/auto-mode

• @nso.ovh @nso.ovh on bluesky

  backup is so 2010 😑 [embedded post]