Re:Sandboxes won't save you from OpenClaw
by notenlish on Wednesday February 25, 2026 @01:43PM
(#47155848)
I think the google award fail is this: https://www.forbes.com/sites/maryroeloffs/2026/02/24/google-...
meta lead fail: https://techcrunch.com/2026/02/23/a-meta-ai-security-researc...
Re:Sandboxes won't save you from OpenClaw
by dbl000 on Wednesday February 25, 2026 @01:45PM
(#47155877)
The meta lead is probably a reference to Summer Yue having OpenClaw delete all the emails in her inbox despite being told not to.
Re:Sandboxes won't save you from OpenClaw
by gmueckl on Wednesday February 25, 2026 @01:46PM
(#47155887)
The Meta thing is the AI safety lead experimenting with OpenClawd on her inbox and the bloody thing deciding to follow her inbox cleanup instructions by "starting fresh" - deleting the inbox contents. It's the very first link in the linked story.
Re:Sandboxes won't save you from OpenClaw
by ramoz on Wednesday February 25, 2026 @01:43PM
(#47155845)
Meta: https://x.com/summeryue0/status/2025774069124399363
context: meta alignment lead made rookie mistakes (their words) in instructing openclaw and lost their inbox to it.
Goog: https://deadline.com/2026/02/google-apologizes-bafta-news-al... *
Ant: https://time.com/7380854/exclusive-anthropic-drops-flagship-...
* There is now a clarification in the press saying it was not ai-generated.
Alignment as a solution to all of this has a rough long road ahead is my point.
Can I get some links / context on this please