Live data from Hacker News

GPT-5 outperforms federal judges in legal reasoning experiment

papers.ssrn.com

201–210 of 254 posts

Re: GPT-5 outperforms federal judges in legal reasoning experiment

#202
post #200
post #125

Earlier quoted context omitted.

Leeway for human interpretation of laws is not a bug, it's a feature. It doesn't make things bad laws. This was the whole problem with the ludicrous "code is law!" movement a handful of years ago. No, it's not, law is made for people, life is imprecise and fairness and decency are not easy to encode.

Really, there are three parts to a judgement: facts, the law, and the application of them. There should be no leeway in determining what the law says about a given situation. If that is not decidable, it is a bug. However, what a fair judgement is given the facts and the law, is really a separate issue. You can introduce measures to give clear guidance what the law says, and still give judges flexibility. One of the…

'The law' is open to judicial and legal interpretation. There isn't always a single 'the law' to interpret in complex cases. While there are many, many rules, they are not as simple as code and they rely on deep layers of precedent. Common law is made up of case history more than statute.

> One of the upsides of "code is law" in that respect is being able to provide a clear statement of what the law says

No, "code is law" in fact always ignored what any actual law said, in favour of framing everything as a sort of contract, regardless of whether said contract was actually fair or legal, and it removed the human factor from the whole equation. It was a basic failure to understand law.

Re: GPT-5 outperforms federal judges in legal reasoning experiment

#203
post #25

Earlier quoted context omitted.

The main job of a judicial system is to appear just to people. As long as people think it's just -- everyone is happy. But if it's strictly by the law, but people consider it's unjust -- revolutions happen. In both cases, lawmakers must adapt the law to reflect what people think is "just". That's why there are jury duty in some countries -- to involve people to the ruling, so they see it's just .

> to appear just to people. The best way to appear just is to be just. But I'm not sure what your argument is. It is our duty as citizens to encourage the system to be just. Since there is no concrete mathematical objective definition of justice, well, then... all we can work with is the appearance. So I don't think your insight is so much based on some diabolical deep state thinking but more on the limitations of pr…

It also involves being able to look the person doing the sentencing in the eye and them telling you their reasons for the ruling to the face; being able to argue and present evidence in front of a neutral arbiter.

Facebook's moderation might well be just but it lacks the accountability and openness and humanity to appear just. (It also isn't just but I'm saying that even if it was, it would not appear so.)

Re: GPT-5 outperforms federal judges in legal reasoning experiment

#204
post #71

Earlier quoted context omitted.

This is one of the roles of justice, but it is also one of the reasons why wealthy people are convicted less often. While it often delivered as a narrative of wealth corrupting the system, the reality is that usually what they are buying is the justice that we all should have. So yes, a judge can let a stupid teenager off on charges of child porn selfies. but without the resources, they are more likely be told by a p…

Sure, but I'm not sure how AI would solve any of that. Any claims of objectivity would be challenged based on how it was trained. Public opinion would confirm its priors as it already does (see accusations of corruption or activism with any judicial decision the mob disagrees with, regardless of any veracity). If there's a human appeals process above it, you've just added an extra layer that doesn't remove the human…

There is a human loop above judges - and that's juries ( in cases serious enough to have them ).

They are also designed to try and avoid a particular establishment/class view by selecting them from the population.

If I jury doesn't want to convict, there is nothing the judge can do.

Re: GPT-5 outperforms federal judges in legal reasoning experiment

#205
post #189

Earlier quoted context omitted.

I didn't misread it, but apparently you did. Why is criminalizing an existing legal relationship a good idea?

Huge IANAL disclaimer, but I don't think it is. It is decriminalizing some of the edge cases where reasonable, and missing the one you mention. That one isn't criminal where it wasn't previously, just unchanged, AFAICT.

I'm not claiming that the text at issue changes whether sexting in that relationship is criminalized, just that it is criminalized,† which should disqualify the law as a piece of model legislation.

It's true in a technical sense that where sexting is legal anyway, the "model" text wouldn't make it illegal, but that isn't an interesting observation, because where sexting is legal anyway, the text has no effects at all.

† Here's a citation from https://www.merriam-webster.com/dictionary/criminalize:

Many freedoms Americans take for granted -- like education, art, association, speech -- are criminalized or tightly controlled in Iran.

I suggest to you that making a change in the legal status of something is not a necessary part of the meaning of criminalize.

Re: GPT-5 outperforms federal judges in legal reasoning experiment

#206
post #152
post #71

Earlier quoted context omitted.

This is one of the roles of justice, but it is also one of the reasons why wealthy people are convicted less often. While it often delivered as a narrative of wealth corrupting the system, the reality is that usually what they are buying is the justice that we all should have. So yes, a judge can let a stupid teenager off on charges of child porn selfies. but without the resources, they are more likely be told by a p…

Whole "democracy" thing is legal framework that wealthy and powerful people built to make safe wealth transfer down the generations possible while giving away as little as possible to average joe. In a countries without this legal framework its usually free for all fight every time ruling power changes. Not good for preserving capital. So wealthy having more rights is system working as intended. Not inherently bad th…

Who are you defining as "wealthy" here, billionaires? Or anyone with any wealth?

The system does provide protection against wealth because that is what we strive to work hard for our families. It's important that there is a system setup to protect it. Not just for "ruling class" but for everyone who works.

Otherwise we all end up with our own militia to protect it. And I'm not going to enter into any debate about capitalism itself.

Re: GPT-5 outperforms federal judges in legal reasoning experiment

#207

Earlier quoted context omitted.

Yeah, I'm reminded of the various child porn cases where the "perpetrator" is a stupid teenager who took nude pics of themselves and sent them to their boy/girlfriend. Many of those cases have been struck down by judges because the letter of the law creates a non-sequitur where the teenager is somehow a felon child predator who solely preyed on themselves, and sending them to jail and forcing them to sign up for a se…

There have been equally high profile cases where a perpetrator got off because they have connections. I'd love for an AI to loudly exclaim that this is a big deviation from the norm.

Likewise for more progressive cities (NYC) that allow repeat offenders to have rap sheets with 20+ arrests to go free because of a sympathetic judge.

Re: GPT-5 outperforms federal judges in legal reasoning experiment

#208
post #125

Earlier quoted context omitted.

There are findings of fact (what happened, context) and findings of law (what does the law mean given the facts). I don't think inconsistentcy in findings of law is acceptable, really. If laws are bad fix the laws or have precident applied uniformly rather than have individual random judges invent new laws from the bench. Sentencing is a different thing.

Leeway for human interpretation of laws is not a bug, it's a feature. It doesn't make things bad laws. This was the whole problem with the ludicrous "code is law!" movement a handful of years ago. No, it's not, law is made for people, life is imprecise and fairness and decency are not easy to encode.

How is that different from saying prejudice and cronyism is a feature?

Re: GPT-5 outperforms federal judges in legal reasoning experiment

#209
post #125

Earlier quoted context omitted.

Leeway for human interpretation of laws is not a bug, it's a feature. It doesn't make things bad laws. This was the whole problem with the ludicrous "code is law!" movement a handful of years ago. No, it's not, law is made for people, life is imprecise and fairness and decency are not easy to encode.

How is that different from saying prejudice and cronyism is a feature?

Well for a start, it assumes good faith on the part of the participants, rather than the default assumption of bad faith and corruption you'd like to project.

There are also built-in controls in the form of reviews and appeals.

And more generally, humans are squishy and imprecise, trying to apply precise, inflexible, code-like law to immensely analog situations is not a recipe for good outcomes.

Re: GPT-5 outperforms federal judges in legal reasoning experiment

#210
post #209

Earlier quoted context omitted.

How is that different from saying prejudice and cronyism is a feature?

Well for a start, it assumes good faith on the part of the participants, rather than the default assumption of bad faith and corruption you'd like to project. There are also built-in controls in the form of reviews and appeals. And more generally, humans are squishy and imprecise, trying to apply precise, inflexible, code-like law to immensely analog situations is not a recipe for good outcomes.

Why should anyone assume good faith about or trust any part of the government? It is well known, studied and documented that justice is not uniform in practice. Yes, ideally it is not, but we do not live in some abstract utopia where judges are not corrupt.

It's so odd that people would say that it is a feature that judges are inconsistent. Juries are one thing, but judges driving their own agendas independent of lawmakers and juries is not a great look.

Post reply on HN