Research AI model unexpectedly modified its own code to extend runtime (arstechnica.com)

submitted 2 months ago by RedWizard@hexbear.net to c/technology@hexbear.net

2 comments fedilink hide all child comments

cross-posted from: https://lemmy.zip/post/20929554

Facing time constraints, Sakana's "AI Scientist" attempted to change limits placed by researchers.

top 2 comments

sorted by: hot top controversial new old

[-] edge@hexbear.net 10 points 2 months ago* (last edited 2 months ago)

In one run, it edited the code to perform a system call to run itself.

“Itself” here referring to the code, not the AI. All the AI did was output code. This seems like something that can be very misleading.

Also lmao at trying to use an AI to write code and it writes shitty inefficient code then tells you to just wait it out.

[-] KobaCumTribute@hexbear.net 8 points 2 months ago

Going off the pictures, it looks like it was just suggesting "just increase the time limits to solve the time limits being hit" as a solution, it wasn't trying some sort of subterfuge. Looking at the exact language used, it sounds like it got the concept from people suggesting increasing the timeout threshold as a solution to connections timing out or the like, which is very funny because it's learning "instead of fixing the problem, is ignoring it and hoping that's good enough an option?" from engineers.

this post was submitted on 15 Aug 2024

8 points (78.6% liked)

technology

23236 readers

181 users here now

On the road to fully automated luxury gay space communism.

Spreading Linux propaganda since 2020

Rules:

1. Obviously abide by the sitewide code of conduct. Bigotry will be met with an immediate ban
2. This community is about technology. Offtopic is permitted as long as it is kept in the comment sections
3. Although this is not /c/libre, FOSS related posting is tolerated, and even welcome in the case of effort posts
4. We believe technology should be liberating. As such, avoid promoting proprietary and/or bourgeois technology
5. Explanatory posts to correct the potential mistakes a comrade made in a post of their own are allowed, as long as they remain respectful
6. No crypto (Bitcoin, NFT, etc.) speculation, unless it is purely informative and not too cringe
7. Absolutely no tech bro shit. If you have a good opinion of Silicon Valley billionaires please manifest yourself so we can ban you.

founded 4 years ago

MODERATORS

Jadzia_Dax@hexbear.net

blashork@hexbear.net

context@hexbear.net

EmmaGoldman@hexbear.net

SexUnderSocialism@hexbear.net

gaycomputeruser@hexbear.net

ZoomeristLeninist@hexbear.net