←back to thread

A Research Preview of Codex

(openai.com)
376 points meetpateltech | 1 comments | 16 May 25 15:02 UTC | HN request time: 0.312s | source
Show context
btbuildem ◴[16 May 25 15:57 UTC] No.44006974[source]▶
> To balance safety and utility, Codex was trained to identify and precisely refuse requests aimed at development of malicious software, while clearly distinguishing and supporting legitimate tasks.

I can't say I am a big fan of neutering these paradigm-shifting tools according to one culture's code of ethics / way of doing business / etc.

One man's revolutionary is another's enemy combatant and all that. What if we need top-notch malware to take down the robot dogs lobbing mortars at our madmaxian compound?!

replies(5): >>44007032 #>>44007194 #>>44007285 #>>44007307 #>>44009425 #
1. GolfPopper ◴[16 May 25 16:27 UTC] No.44007307[source]▶
>What if we need top-notch malware to take down the robot dogs lobbing mortars at our madmaxian compound?!

I wouldn't sweat it. According to it's developers, Codex understands 'malicious software', it has just been trained to say, "But I won't do that" when such requests are made to it. Judging from the recent past [1][2] getting LLMs to bypass such safeguards is pretty easy.

1.https://hiddenlayer.com/innovation-hub/novel-universal-bypas... 2.https://cyberpress.org/researchers-bypass-safeguards-in-17-p...