Mastodon discussion Discussions Jul 11 2 views

🛡️ #dcg (Destructive Command Guard) is an open-source safety hook that blocks destructive shell & git commands before #A...

by michabbb

🛡️ #dcg (Destructive Command Guard) is an open-source safety hook that blocks destructive shell & git commands before #AI coding agents can run them 🧵👇 #Rust #opensource⚡ Born from real pain: agents like Claude Code, Codex & Gemini sometimes run git reset --hard, rm -rf ./src or DROP TABLE users — destroying hours of uncommitted work in seconds

Read Original

Anthropic Google Open Source

Metadata

Account: michabbb@vivaldi.net

Mastodon discussion 7m ago

#GroundStop #FAA #AI‘AI departing traffic should remain groundstopped until further notice.'

Mastodon discussion 7m ago

You can beat Forecasting LLMs (Large Language Models a.k.a foundation models) with nnetsauce.MTShttps://thierrymoudiki.g...

You can beat Forecasting LLMs (Large Language Models a.k.a foundation models) with nnetsauce.MTShttps://thierrymoudiki.github.io/blog/2024/11/24/r/python/forecasting/nnetsauce/nnet...

Mastodon discussion 10m ago

Simon Willisons llm-CLI konnte euren OpenAI-Key an fremde Endpunkte schicken, ohne Warnung. Version 0.37.2 behebt das. W...

Simon Willisons llm-CLI konnte euren OpenAI-Key an fremde Endpunkte schicken, ohne Warnung. Version 0.37.2 behebt das. Wer eigene api_base-Modelle eingetragen hat, sollte prüfen un...

🛡️ #dcg (Destructive Command Guard) is an open-source safety hook that blocks destructive shell & git commands before #A...

Metadata

Related

#GroundStop #FAA #AI‘AI departing traffic should remain groundstopped until further ​notice.'

You can beat Forecasting LLMs (Large Language Models a.k.a foundation models) with nnetsauce.MTShttps://thierrymoudiki.g...

Simon Willisons llm-CLI konnte euren OpenAI-Key an fremde Endpunkte schicken, ohne Warnung. Version 0.37.2 behebt das. W...

#GroundStop #FAA #AI‘AI departing traffic should remain groundstopped until further notice.'