Most active commenters

    ←back to thread

    Uncensor any LLM with abliteration

    (huggingface.co)
    586 points mizzao | 11 comments | 13 Jun 24 03:42 UTC | HN request time: 1.156s | source | bottom
    Show context
    giancarlostoro ◴[13 Jun 24 14:05 UTC] No.40669810[source]▶
    I've got friends who tried to use ChatGPT to generate regex to capture racial slurs to moderate them (perfectly valid request since they're trying to stop trolls from saying awful things). It vehemently refused to do so, probably due to overtly strict "I'll never say the nword, you can't fool me" rules that were shoved into ChatGPT. Look, if your AI can't be intelligent about sensible requests, I'm going to say it. It's not intelligent, it's really useless (at least regarding that task, and related valid tasks).

    Who cares if someone can get AI to say awful things? I can write software that spits out slurs without the help of AI. Heck, I could write awful things here on HN, is AI going to stop me? Doubt it, nobody wants to foot the bill for AI moderation, it can only get so much.

    replies(5): >>40670109 #>>40670220 #>>40671835 #>>40671863 #>>40676828 #
    1. WesolyKubeczek ◴[13 Jun 24 14:26 UTC] No.40670109[source]▶
    > Who cares if someone can get AI to say awful things?

    I imagine the legal department of Meta, OpenAI, Microsoft, and Google care a great deal, and they don't want to be liable for anything remotely resembling a lawsuit opportunity.

    replies(2): >>40671705 #>>40671770 #
    2. chasd00 ◴[13 Jun 24 16:31 UTC] No.40671705[source]▶
    Yes, "AI Safety" really means safety for the reputation of the corporation making it available.
    replies(1): >>40672297 #
    3. drdaeman ◴[13 Jun 24 16:36 UTC] No.40671770[source]▶
    Is the legal system broken somehow it's a legit issue, or do their legal teams have some sort of PTSD so they're scared of any ideas of lawsuit no matter how frivolous, so they make weirdest business-affecting decisions?

    I mean, if the LLM drops some slurs, gives a recipe for bananadine, or even goes all Bender suggesting we kiss its shiny metal ass or it kills all humans - how, in the name of all that's still sane in this world, it's a lawsuit material?

    I imagined it's morke likely to be about activists on offense watch, cranking it up to 11 making bad PR (still weird, but people are weird and this sort of stuff happens), than some legal issues.

    replies(2): >>40672009 #>>40672024 #
    4. WesolyKubeczek ◴[13 Jun 24 16:59 UTC] No.40672009[source]▶
    > still weird, but people are weird and this sort of stuff happens

    I wouldn't be surprised if there were actual PR agencies involved in larger shitstorms. Activists are weird, true, but wild brigading is not a thing of an initiative, it's an "also-ran" thing. The instigators are often level-headed and cynical.

    5. lovethevoid ◴[13 Jun 24 17:00 UTC] No.40672024[source]▶
    Section 230 has been subject to numerous reforms and proposals in recent years, so yes it's a very real legal issue that platforms are keeping an eye on. FOSTA is an example, in which platforms all had to make changes and now constantly take down posts related to those acts. Another proposal to amend 230 ("Ending Support for Internet Censorship Act") is that platforms are stripped of their legal liability protections for what is posted if they cannot prove they are "politically neutral".
    replies(1): >>40672793 #
    6. eddd-ddde ◴[13 Jun 24 17:31 UTC] No.40672297[source]▶
    I don't think this falls under the responsibility of the AI provider.

    Gun makers are perfectly happy with their guns killing innocent people.

    replies(3): >>40672621 #>>40672750 #>>40674609 #
    7. mock-possum ◴[13 Jun 24 17:58 UTC] No.40672621{3}[source]▶
    Perfectly happy, sure, but also desperately afraid that they’ll someday be held even partially responsible - which is why they spend millions in lobbying to prevent laws and advertising / outreach to curry favour.
    8. roywiggins ◴[13 Jun 24 18:12 UTC] No.40672750{3}[source]▶
    There is a shield law for gun manufacturers, there isn't one for LLM products (unless you want to stretch Section 230 to beyond its breaking point)

    https://en.m.wikipedia.org/wiki/Protection_of_Lawful_Commerc...

    replies(1): >>40676946 #
    9. roywiggins ◴[13 Jun 24 18:15 UTC] No.40672793{3}[source]▶
    Section 230 only immunizes service providers for the contents of users' posts, not its own content. It can't immunize Google from being responsible for Gemini's output.
    10. eddd-ddde ◴[13 Jun 24 21:32 UTC] No.40675029{4}[source]▶
    That's the point. People use guns to kill people the same way people can use AI to make bad things.

    Either both are okay or both are wrong.

    11. ImJamal ◴[14 Jun 24 02:17 UTC] No.40676946{4}[source]▶
    There are the same laws for pretty much everything. If somebody buys a car and runs down a crowd of people (not due to some defect in the car) you can't sue the car company and dealership. It is the same as guns. We just had to explicitly have laws around guns because some people wanted guns to be held to a different standard then everything else.