Technology

67338 readers

3882 users here now

This is a most excellent place for technology news and articles.

Our Rules

Follow the lemmy.world rules.
Only tech related news or articles.
Be excellent to each other!
Mod approved content bots can post up to 10 articles per day.
Threads asking for personal tech support may be deleted.
Politics threads may be removed.
No memes allowed as posts, OK to post as comments.
Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
Check for duplicates before posting, duplicates may be removed
Accounts 7 days and younger will have their posts automatically removed.

Approved Bots

founded 2 years ago

MODERATORS

L3s@lemmy.world

enu@lemmy.world

technopagan@lemmy.world

L4s@lemmy.world

L3s@hackingne.ws

370

Show top LLMs buggy code and they'll finish off the mistakes rather than fix them. (www.theregister.com)

submitted 5 days ago by Tea@programming.dev to c/technology@lemmy.world

43 comments fedilink hide all child comments

Researchers have found that large language models (LLMs) tend to parrot buggy code when tasked with completing flawed snippets.

That is to say, when shown a snippet of shoddy code and asked to fill in the blanks, AI models are just as likely to repeat the mistake as to fix it.

you are viewing a single comment's thread
view the rest of the comments

[–] Damage@feddit.it 7 points 5 days ago (1 children)

Let's train an LLM exclusively on the Windows XP source code and contemporary Microsoft apps

[–] Bogasse@lemmy.ml 3 points 5 days ago (1 children)

Wasn't XP more reliable than the average of Windows versions?

[–] bitwolf@sh.itjust.works 6 points 5 days ago (1 children)

It had a lot of vulnerabilities iirc

[–] sugar_in_your_tea@sh.itjust.works 4 points 5 days ago (1 children)

Especially before SP2.

[–] Goun@lemmy.ml 2 points 5 days ago

UGH, this triggered my PTSD