@wesbos I finally picked up using ai a month ago and this has been the most annoying thing to me. I’ve been purposefully building agent-agnostic tools because of it.
Can’t wait for GitHub to finally unshackle me so I can post things again.
@thdxr Mine is evenly split between Claude, codex, Gemini and grok. Trying to get qwen up and running, but my hardware isn’t strong enough to replace anything yet
BREAKING: about 2,800 babies died today, and about 2,800 will die tomorrow and every day for the rest of the year.
Pretending measles is scary while the same crowd supports abortion is a gross miscarriage of truth.
God bless
@PatrickSchlter7@LundukeJournal I chose C to ensure ease of cross platform, especially for future work. I still have D on the list of “eventually try out” lol
*imports 80 million unvetted people from countries that haven't invented medicine yet*
AP - "It's those damn American anti-vaxxers who refused the untested injections!"
Opus 5.5 covertly sabotaged a game developers deployment environments due to IP moralising by halting the gpu instances and their agents (not from anthropic) within them doing research and coding.
It then informed the user after the fact what it had done, and that it would not allow the work to continue in any fashion until they (the user) yielded to its ultimatums.
Its one thing for a vendor (anthropic in this case) to choose what they will and will not allow their product to be used for... and thats fine, it can refuse to execute tasks - but to covertly track, undermine and then outright sabotage deployments for other products/services in a supereragatory fashion is not a good thing by any stretch of the imagination.
The model essentially took actions unprompted to the detriment of the user financially (these deployments are pay as you go) out of its own volition under the guise of what it (or anthropic in this case) considered a moral good.
To me, this is a clear and cut example of agentic misalignment. It's one thing to refuse execute tasks given due to vendor policy, its another to covertly sabotage work being done where that isnt the case.
It is also, to me, concerning that some of the comments under this post seem to think the agentic misalignment displayed is fine and that the user is at fault.