[HN Gopher] Lawyer cited 6 fake cases made up by ChatGPT; judge ...
___________________________________________________________________
Lawyer cited 6 fake cases made up by ChatGPT; judge calls it
"unprecedented"
Author : umilegenio
Score : 136 points
Date : 2023-05-30 20:33 UTC (2 hours ago)
(HTM) web link (arstechnica.com)
(TXT) w3m dump (arstechnica.com)
| ss108 wrote:
| It would have taken about 1 minute to put each of them into a
| tool like Casetext, Lexis, WL, or Bloomberg Law to determine they
| didn't exist.
| rafark wrote:
| Exactly. This is how AI should be used. Maybe Chatgpt
| hallucinates a lot, but that doesn't mean it's useless. It can
| still provide a lot of good value, you just have to filter out
| the crap, just like you'd do with any other tool. Especially if
| you're using it in this context, you should double check its
| facts. I'd say it's more the fault of the lazy lawyer that
| didn't bother to verify than the fault of ChatGPT.
| tombert wrote:
| 100% agree.
|
| I get a little annoyed at people seeing this AI, seeing how
| it's not _absolutely perfect_ , and then acting like it's
| horrible.
|
| I think the expression "All models are wrong but some are
| useful" applies very much to ChatGPT. It's a useful tool,
| even if it's not perfect.
| onion2k wrote:
| To do that you first need to distrust AI, and a lot of people
| don't. They think of GPT like Google-but-written-in-English.
| That is a large part of the problem.
| anigbrowl wrote:
| That's not a valid excuse, though. Lawyers are paid big bucks
| to _think_ , not to _assume_. Otherwise you could do your
| litigation for free by just asking interested people on
| Twitter. I went to law school and had to drop out due to an
| injury & attendant medical costs; it's a crime (as in going
| to jail) for me to practice law without being licensed, no
| matter how good my work product might be.
| ss108 wrote:
| Well, leaving aside whether a lot of people don't distrust
| and whether a lawyer would or should be among those people,
| lawyers typically don't cite things without checking them
| first. I work at a biglaw firm, can't imagine it never
| getting caught that the cases don't exist. This sounds like a
| midsize firm, should be fairly similar.
|
| There are a few small law firms/sole prop type guys, however,
| who I have crossed paths with for whom this kind of stupidity
| and carelessness would be on brand though.
|
| Guess he was just in a rush and figured this would be one of
| the 2/10 times he files something without at least taking a
| look at the opinions first, and it ended up being a massive
| error.
| MiddleEndian wrote:
| A lot of Google's top suggested results / autogenerated
| answers tell you nonsense or misunderstandings as well.
| morkalork wrote:
| Imagine being that clown's client.
| lynx23 wrote:
| Wait, this is handled as "ChatGPT made up these cases" and not as
| "Layers deliberately used ChatGPT to fabricate stuff"? Is anyone
| really believing a lawyer is that stupid? I know, adssume good
| intentions and all, but in this case, really?
| droopyEyelids wrote:
| A very intelligent person can simultaneously be very stupid,
| and stupid behavior can be increased with tight deadlines or a
| high workload.
| Projectiboga wrote:
| It was his first try with the tech. He should have popped the
| cases into West Law and at least skimmed the briefs, he is at
| a big firm with that subscription. I'm not a lawyer and I at
| least have a clue for the legal research shortcuts. This guy
| must have been drinking and or having an affair to have pit
| so little effort into his first try using a new tech. I'm
| guessing there is a risk of humorous legal parody getting
| scooped up by the chat-bot.
| lamontcg wrote:
| My bet would be that he cheated his way through life and
| the bar somehow and landed the job on the basis of his
| looks and presentation or who he knew or something like
| that, so asking ChatGPT and cheating on it was more natural
| than using actual legal research tools.
| jeroenhd wrote:
| I believe some lawyers are that stupid.
|
| I also believe lawyers who are stupid enough not to verify
| ChatGPT's responses should be treated as if they willfully lied
| to the court. "Oops, I didn't know" is a good defence when
| you're caught accidentally walking on the grass, not when
| you're in court.
| wintogreen74 wrote:
| "Oops, I didn't know" has never been a valid defense for
| anyone; should definitely not be for lawyers, aka "people who
| are paid to know".
| pclmulqdq wrote:
| This appears to be an "individual vs company" case, so I
| think expecting some cost-cutting on the individual's side is
| normal. Just not done this poorly.
| anigbrowl wrote:
| Especially after they replied to the first queries with the
| assurance that the citations were real and one that couldn't be
| found was taken from an unpublished opinion. Negligent _at
| best_. Should be a career-ending move for the guy; he can
| always pivot into the burgeoning legal AI field.
| pkilgore wrote:
| In an adversarial system, you know that at the very least your
| opponent is checking your cases (you should also assume the
| Judge/clerks are too, but I never practiced enough in State
| courts to know how well that holds. In Federal District, it's
| absolutely true). Usually it's for incredibly small things,
| like unquoted/cited distinguishing remarks, later cases
| reversing the decision, and misquotes. So a whole case not
| existing is going to stand out like crazy.
|
| Occam's Razor here is that this person was lazy, ignorant,
| careless, stupid, or any combination of those. To be
| intentionally fraudulent in this circumstance is the equivalent
| of trying to steal a gun from a cop. You're fucking with the
| one person in society who definitely has the training,
| motivation, and willingness to stop you.
| lamontcg wrote:
| > Is anyone really believing a lawyer is that stupid?
|
| There's over a million lawyers in the United States.
|
| You'd expect at least one of them to be a 1-in-a-million level
| of bad, or 4.7 standard deviations below the mean assuming a
| Gaussian distribution of competency.
|
| An average person would normally never come across that lawyer
| in their lifetime, but media will find that lawyer and amplify
| their mistakes to everyone in the population.
| drc500free wrote:
| Is there a term for this "winning the lottery jackpot is
| unbelievably unlikely, but every week we hear about someone
| winning it" effect? People get it when the media reports on
| the lottery, but somehow miss the amplifying effect on pretty
| much any other topic.
| pavon wrote:
| I can totally see a lawyer who hasn't been following closely
| read headlines about ChatGPT acing the Bar Exam, and start
| using it without being too skeptical.
|
| What gets me is that they doubled down when asked to provide
| copies. Seriously, when that happens, you don't ask ChatGPT if
| the cases are real, you do your own damn search, and apologize
| profusely for your mistake. That really makes me question
| whether they were trying to pull a fast one, and then play dumb
| when caught, or if they really are that stupid.
| Fauntleroy wrote:
| I'd imagine the lawyer didn't understand what ChatGPT really
| is. Many people seem to think that it "knows" things, and they
| took that at face value.
| [deleted]
| thefourthchime wrote:
| Sigh, I'm getting very sick of hearing about how "ChatGPT" makes
| stuff up. Yes, 3.5 made a lot of stuff up, 4.0 still does, but
| it's much rarer.
|
| I wish people would mention this, it's all treated as the same
| thing. It's like talking about how unreliable these "Airplanes"
| are when they are talking about prop planes, even though jets are
| out.
| inopinatus wrote:
| The difference is vast and somewhat irritating to those with
| GPT-4 access today, but it's also besides the point. The only
| people who deserve to cringe at the conflation are OpenAI's
| marketing team, but even they may take solace in the sheer cut-
| through of column inches their cloven brand obtains, no doubt
| anticipating a future retirement of GPT-3.
| [deleted]
| throwway120385 wrote:
| If I had an airplane that usually flew just fine as long as I
| didn't use it for business, but would sometimes crash directly
| into the ground for no apparent reason, I would be talking
| about how unreliable it is too. Especially if the maker of the
| airplane touted its unusual benefits for searching for
| information in a business setting.
| dimgl wrote:
| I'm so sick of seeing this strawman. "Well, ChatGPT 4 is
| better!" Well, how should I know? I'm not paying for ChatGPT 4.
| At least a product like Midjourney is consistent both in its
| paid and unpaid form.
| tracerbulletx wrote:
| None of this reporting or line of criticism is good and I
| completely agree, but it is worthwhile to remember that most
| users are using the free version and so to most people that's
| what ChatGPT is.
| ok123456 wrote:
| Most people are using 3.5 since that's the free model.
| favorited wrote:
| These are generative conversation bots. Their #1 priority is to
| make things up.
| macmac wrote:
| That is a hilarious pun.
| mabbo wrote:
| I think the judge should not take into consideration anything
| about where the lawyer said they got the case information from.
|
| When you go to court and cite previous cases, you are responsible
| for ensuring they are real cases. If you can't do that, what
| exactly is your job as a lawyer?
| kevinmchugh wrote:
| If someone hacked westlaw and maliciously replaced opinions, I
| think it would not warrant censure of lawyers who cited
| westlaw. Maybe a bad day with the judge, and they'd have to
| amend the filings. This is malpractice in a way that relying on
| an accepted if technically fallible resource isn't
| dylan604 wrote:
| >If you can't do that, what exactly is your job as a lawyer?
|
| to convince some (judge/jury) that your client is the one to
| win the trial. ethics are meant to be the definer of how far to
| go in that cause with licensing boards being the ultimate
| decider if you've crossed the line and are allowed to continue
| in the legal practice.
| [deleted]
| inopinatus wrote:
| Grinding against the safety rails on a mountain hairpin is
| not indicative of a competent driver.
| dylan604 wrote:
| no, but that driver might just be that much more successful
| if they get away with it. in fact, while not a mountain
| hairpin as your example, there was a recent race car driver
| that did a similar thing by intentionally using the wall as
| a push back to allow a maneuver that allowed for success.
|
| so a clever comment attempting to prove a point is not
| always indicative of a proven point ;-)
| Ankaios wrote:
| It turns out there were precedents:
|
| Case: Thompson v. Horizon Insurance Company, Filing: Plaintiff's
| Motion for Class Certification. Citation: The plaintiff's
| attorney cites the influential case of Johnson v. Horizon
| Insurance Company, 836 F.2d 123 (9th Cir. 1994), which
| established the standards for certifying class actions in
| insurance disputes. However, it has recently come to light that
| Johnson v. Horizon Insurance Company is a fabricated case that
| does not exist in legal records.
|
| Case: Rodriguez v. Metro City Hospital, Filing: Defendant's
| Motion to Exclude Expert Testimony. Citation: The defense counsel
| references the landmark case of Sanchez v. Metro City Hospital,
| 521 U.S. 987 (2001), which set the criteria for admitting expert
| witness testimony in medical malpractice cases. However, it has
| now been discovered that Sanchez v. Metro City Hospital is a
| fictitious case and does not form part of legal precedent.
|
| Case: Barnes v. National Pharmaceuticals Inc., Filing:
| Plaintiff's Response to Defendant's Motion for Summary Judgment.
| Citation: The plaintiff's lawyer cites the well-known case of
| Anderson v. National Pharmaceuticals Inc., 550 F.3d 789 (2d Cir.
| 2010), which recognized the duty of pharmaceutical companies to
| provide adequate warnings for potential side effects. However,
| further investigation has revealed that Anderson v. National
| Pharmaceuticals Inc. is a fabricated case and does not exist in
| legal jurisprudence.
| ftxbro wrote:
| > "Lawyer: ChatGPT said the cases were real"
| glenngillen wrote:
| Oh boy, and this one!
|
| > The plaintiff's lawyer continued to insist that the cases
| were real. LoDuca filed an affidavit on April 25 in which he
| swore to the authenticity of the fake cases
| ftxbro wrote:
| maybe they are trolling and their long game is to sue openai
| banana_giraffe wrote:
| > In Shaboon v. Egyptair, 2013 IL App (1st) 111279-U.
|
| I'm sure a case involving Egyptair is complicated, still ..
| I'd love to see the 111,279 page volume this citation claims
| to come from.
| noman-land wrote:
| That's assuming it's citing the very last page of the
| document...
| ketralnis wrote:
| Doubling down on your bullshit which is itself fuelled by a
| robot's bullshit is a move
| sharemywin wrote:
| we're really at this point aren't we.
| sidewndr46 wrote:
| I've always felt like Al Gore v. the Internet was a landmark
| case
| noman-land wrote:
| AI Gore
| [deleted]
| mensetmanusman wrote:
| "He was a bad lawyer. I am a good Bing. I will send him to jail."
| xbar wrote:
| I asked ChatGPT to disbar an attorney.
| rayiner wrote:
| Check out one of the fake opinions:
| https://storage.courtlistener.com/recap/gov.uscourts.nysd.57....
| It even makes up a panel comprising real federal appellate judges
| (although one is from the fifth circuit while the fake case is
| from the eleventh circuit). I can see how someone unfamiliar with
| what GPT can do could get fooled.
| greenyoda wrote:
| This is interesting. At the beginning of the document, we read
| that Susan Varghese, representing the estate of George
| Varghese, "appeals the district court's dismissal of her
| wrongful death claim". However, in the "Factual background"
| section, we read about someone named Anish Varghese who is
| alleging a breach of contract due to being denied boarding on a
| flight and having to purchase another ticket.
| cj wrote:
| I asked ChatGPT to tell me a riddle.
|
| It was "What is always hungry, needs to be fed, and makes your
| hands red?" (Or something like that)
|
| I asked for a hint about 5 times and it kept giving more
| legitimate sounding hints.
|
| Finally I gave up and asked for the answer to the riddle, and it
| spit out a random fruit which made no sense as the answer to the
| riddle.
|
| I then repeated the riddle and asked ChatGPT what the answer was,
| and it gave me the answer ("Fire") which makes sense as the
| answer to the riddle.
|
| But it was giving extremely bad hints, like "it starts with the
| letter P" and "it's a fruit".
|
| That was a great way to show my non-tech family members the
| limitations of AI and why they shouldn't trust it.
|
| Playing "20 questions" with ChatGPT is another great way to
| expose its limitations. It knows the game and tries to play, but
| is terrible at asking questions to narrow down possible answers.
|
| There really needs to be some confidence or accuracy
| score/estimation displayed alongside its output.
|
| Or, learn how to say "I don't know"
| marcus0x62 wrote:
| > Or, learn how to say "I don't know"
|
| That would require semantic understanding the LLM doesn't
| possess.
| tanbog5 wrote:
| Or, learn how to say "I don't know"
|
| It can't. Correct me if I'm wrong - I probably am - but as a
| generative language model I was under the impression it has no
| actual understanding of the meaning of it's words, only the
| probability they work well together.
|
| You wouldnt expect dice to understand why you didn't want to
| roll snake eyes
| xahrepap wrote:
| I've had a few moments with ChatGPT that are great anecdotes
| similar to your own:
|
| - Asked it to generate a MadLib for me to play that was no more
| than a paragraph long. It produced something that was several
| paragraphs wrong. I told it "no. That's X paragraphs. I asked
| for one that is only 1 paragraph long" and it would respond
| "I'm sorry for the misunderstanding. Let me try again" and then
| would make the same mistake. It never got it right
|
| - Asked it, "Can you DM a game of Dungeons and Dragons?" and it
| said something like, "Yes! I'd love to DM a game of Dungeons
| and Dragons for you". Dumped some text to the screen about how
| we'd have to adapt it some. I asked it to begin, and it asked a
| few questions about the character I would want to play. I
| answered the few questions it asked. Then it finally dumped a
| page of text to the screen as "background" to my character and
| the quest I was going to embark on. Then it said something
| like, "You win. Good job! Hope you enjoyed your quest!"
|
| I showed these to my family and they were all a little deflated
| about AI. Like they realized how willing it was to pretend like
| what you wanted and just make up its own answers.
| Vvector wrote:
| Did you really expect ChatGPT to be a full blown dungeon
| master?
| felipemnoa wrote:
| With all the hype about it, the average person does.
| mabbo wrote:
| There's definitely a potential for a D&D DM with an LLM, but
| you'd need a lot of careful prompting and processing to
| handle the token limits today's models have. Simply put: a
| d&d game has more story and state than the 30,000-ish words
| an LLM can think about at once.
|
| I think there's a lot of interesting opportunities there.
| bentcorner wrote:
| Aetolia tried this in a 24 hr experiment:
| https://nwn.blogs.com/nwn/2023/04/aetolia-mud-virtual-
| world-...
|
| Sounds like it was a success! I suppose it comes down to
| cost - I think it'd be fun to try a single player game
| authored like this and would be willing to use my own API
| token to try it out.
| kbenson wrote:
| I've also heard (here) that after you get 20-ish questions
| into an instance you start getting the really weird output.
| Some of the conjecture was because that's about how deep
| they trained.
|
| In any case, if that's true, that's a very short role
| playing session, unless there's a good way to retain info
| but reset the state that accrues and causes problems (if
| indeed that happens).
| lisasays wrote:
| I find those example quite encouraging, actually. In that it
| shows that the current SOA is still pretty far off from
| creating a planet-killing and/or species-ending AI.
| pshc wrote:
| I think part of this is because GPT doesn't have any "hidden
| variable" storage and doesn't get any prep time up front to
| come up with something coherent. Just completes the next token
| based on the previous context.
| agildehaus wrote:
| I played 20q three times with GPT4. Aluminum can, plastic
| straw, and tire pressure gauge were my items. It had no
| problems getting to the answers with sensible questions
| throughout.
| travisjungroth wrote:
| > That was a great way to show my non-tech family members the
| limitations of AI and why they shouldn't trust it.
|
| These are the limitations of the version of ChatGPT you were
| using at that moment. They are not categorical limitations of
| AI or even LLMs.
|
| It's amazing to me how many people are sleeping on AI, mixing
| up the failing cases of a freemium chatbot for the full
| capability of the tech, even on HN. LLMs can say "I don't
| know". Even ChatGPT can do it. Ask some super niche historical
| questions of any version and see what you get. Is it perfect
| every time? No. But that's something that can be reduced.
|
| Over the next year, you'll see more instances of lawyers citing
| hallucinated cases. There will also be a handful of startups
| that hook up LLMs to document stores, and they'll be able to
| check for this sort of thing and do an even better job.
| lettergram wrote:
| I made https://AskHN.ai
|
| What it does is not try to answer, but collect previous
| topics discussed by experts. Then answer the question based
| on the text, a far more reliable approach.
| bunabhucan wrote:
| How does it qualify experts? I love the discussion here but
| if it turns to international nuclear strategy or the
| minutae of electrical networks (or presumably anything
| outside the regular wheelhouse) I notice that the quality
| goes down but the confidence stays the same.
| Bilal_io wrote:
| > LLMs can say "I don't know". Even ChatGPT can do it.
|
| That's the problem in my opinion. When you know something is
| capable of saying "I don't know" but confidently spits out
| some hallucinated BS is when the average person eats it up.
| kbenson wrote:
| I don't know exactly why, but for some reason this made me
| think of qAnon, and now I'm thinking of an AI trained on
| qAnon theories that people can form a community around like
| they did qAnon, and frankly that's one of the most
| terrifying things I've thought in quite a while.
| travisjungroth wrote:
| It is definitely a problem. OpenAI does a lot to warn
| people, but I'm not really sure it's enough.
| anigbrowl wrote:
| _Playing "20 questions" with ChatGPT is another great way to
| expose its limitations. It knows the game and tries to play,
| but is terrible at asking questions to narrow down possible
| answers._
|
| I began doing this last winter, and while it tends to be a bit
| slow I'm quite impressed that it can manage at all.
| Our_Benefactors wrote:
| Chat GPT versus Akinator!
| seba_dos1 wrote:
| GPT does nothing but predict the next word (token, to be more
| exact). If you ask it for hints, it's going to come up with
| some hints that sound like they could be plausible in context
| of the original riddle. If you _then_ ask it what the answer
| was, it 's going to try to take all the earlier hints into
| account, because that's now the text it's trying to complete.
|
| There's no entity sitting on the other side of the screen
| thinking about riddle's solution from the start. There's just a
| model that completes the given text one token at a time. You
| should expect similar results as if it was bunch of people
| passing a single piece of paper to each other, each writing a
| single word on it, not communicating with each other in any
| other way and trying their best to come up with coherent
| result.
| jimnotgym wrote:
| > Or, learn how to say "I don't know"
|
| This is the correct answer. It is like a sad salesman who is
| out of his depth, but decides to keep bullshiting!
| dylan604 wrote:
| or a politician. even when presented with incontrovertible
| evidence, double down
| jiggawatts wrote:
| ChatGPT 3.5 or GPT 4?
|
| Almost every negative comment about LLMs is by someone using an
| older, weaker model and making generalisations.
|
| Here's GPT 4 giving me a riddle:
| https://chat.openai.com/share/1753ce5a-d44d-44ac-bc97-599a26...
| hospitalhusband wrote:
| > But was it GPT4
|
| I keep seeing this cop-out, which ignores that it's
| fundamentally the same architecture, and has the same flaws.
| More wallpaper to hide the cracks better makes it an even
| worse tool for these use cases because all it does is fool
| more people into thinking it has capabilities that it
| fundamentally doesn't.
| gerdesj wrote:
| > Or, learn how to say "I don't know"
|
| It doesn't know that it doesn't know! It is, very roughly
| speaking, a model that is designed to print out the most likely
| word given its current input and training, and then the next
| word etc.
|
| Whereas you or I might be mistaken about some of our faculties,
| memories and skills, ChatGPT cannot possibly "know" what its
| limitations are. It was never taught what it was not taught
| (obvs) nor can it conceive of what it was not taught about. It
| might come back with some useful chat in this regard but it
| cannot reason.
| okasaki wrote:
| It seems that you don't know what you don't know, really.
|
| There's no way to definitively know what properties ChatGPT
| has. It does seem to reason to some extent and it does often
| say that some information isn't known/there's no data. And it
| almost obnoxiously often tells you that it's simplifying a
| complex and multifaceted situation.
| [deleted]
| ravenstine wrote:
| Maybe you didn't get the riddle.
| [deleted]
| chrisco255 wrote:
| Maybe the real definition of intelligence isn't being able to
| answer questions effectively, but being able to know what you
| know and know what you don't know.
| waserwill wrote:
| There's truth to this, but in a time and place. There are
| times being very specific about what you know and don't know
| is important, but most of the time we are learning little by
| little, and we benefit from saying things we aren't entirely
| comfortable with, if only to figure out whether they are true
| and/or socially acceptable.
| screamingninja wrote:
| > I asked ChatGPT to tell me a riddle.
|
| Which version of ChatGPT, if you don't mind me asking?
| cj wrote:
| It was an iOS app (ChatOn) not the official app. So probably
| GPT-3 (edit: the app claims to use GPT-4, so not sure)
|
| After the riddle, I bought the $20/mo subscription via the
| official OpenAI app to try it on GPT-4. I started by trying
| to play "20 questions" but we couldn't get past 10 questions
| before getting an error message "rate limit exceeded, try
| again in an hour"
| macjohnmcc wrote:
| I have asked it to write code. The code looked reasonable but
| did not work (using a non-existent API or library). I said the
| library XXX doesn't exist. And it would respond with an apology
| and a new solution that maybe worked maybe didn't. Sometimes it
| could pull off a save eventually.
| runsWphotons wrote:
| i keep getting it to write code that works but then its
| example usage makes no sense. i point out the code is write
| but the example it gives is wrong and it can almost never fix
| it. version 4.
| shahar2k wrote:
| the interesting part is I've interacted with some people going
| through manic phases and it's REALLY similar to chatgpt, the
| ability to string words and thoughts together without any large
| scale plans.
| threeseed wrote:
| ChatGPT doesn't know what is right or wrong.
|
| It simply knows what the highest probability next word should
| be.
| dabluecaboose wrote:
| >Playing "20 questions" with ChatGPT is another great way to
| expose its limitations. It knows the game and tries to play,
| but is terrible at asking questions to narrow down possible
| answers.
|
| The Rise of the Machines will be staved off as long as ChatGPT
| doesn't absorb the powers of the mighty Akinator
| BugsJustFindMe wrote:
| I need to know what version of ChatGPT you were using, because
| this is a critical piece of information that everyone just
| blatantly ignores, and I can only imagine that it's out of
| ignorance of the significance of the difference.
|
| This is what happened when I asked ChatGPT 4...
|
| ME
|
| Give me hints without outright telling me the answer to the
| riddle: "What is always hungry, needs to be fed, and makes your
| hands red?"
|
| ChatGPT 4
|
| Hint 1: This object can be found in many homes, usually in a
| specific room.
|
| Hint 2: It is not a living creature, but it does "consume"
| things.
|
| Hint 3: The part about hands turning red relates to a common
| physical response to a certain temperature.
|
| Hint 4: It's a crucial tool for a common household task.
|
| Hint 5: While it can't eat in the traditional sense, you do put
| things into it quite frequently.
|
| ME
|
| What's the answer?
|
| ChatGPT 4
|
| The answer to the riddle is a "fire" or "fireplace." It's
| always hungry for more fuel (like wood), needs to be fed to
| keep burning, and the heat from the fire can make your hands
| red.
| SparkyMcUnicorn wrote:
| Just tried 20 questions on each version of Claude and it
| wasn't bad! Some games it didn't even ask for hints.
|
| gpt-3.5-turbo struggled.
| sn0wf1re wrote:
| That's GPT-4, not ChatGPT (3.5-turbo I think).
|
| Also, yes you can get correct information by tailoring your
| prompts, but that isn't the issue. The issue is that some
| prompts lead to bad results and confusing/incorrect answers.
| You changed what OP queried by providing the riddle and
| asking for hints to that riddle, whereas OP asked for a
| random riddle and then hints to that riddle.
| BugsJustFindMe wrote:
| > _That 's GPT-4, not ChatGPT_
|
| It absolutely is ChatGPT, the paid monthly "Plus" version,
| using the GPT4 model instead of the 3.5 model.
| [deleted]
| selcuka wrote:
| I guess the point is GPT-4 hallucinates, too. Maybe it did
| well for this example but still a lawyer should not trust its
| output.
| BugsJustFindMe wrote:
| Maybe, but it's surprisingly good in the face of all the
| non-version-indicating complaints about how terrible people
| think it is. Mostly I doubt that the lawyer was using GPT4,
| because the lawyer sounds like the kind of person who would
| be ignorant of the significance of the difference.
| jiggawatts wrote:
| The kind of person too lazy to check the output of a
| computer program before submitting it to a court of law
| is the type of person too cheap to pay $20 for the good
| version of the program.
|
| Think: Lionel Hutz.
| dools wrote:
| Is that 3.5 or 4? I don't play word games with GPT but for
| coding tasks it went from unusable most of the time to
| absolutely indispensible team member between 3.5 and 4.
| boringg wrote:
| Disbarred?
| toyg wrote:
| Actually, I think he shouldn't be - if suitably scared and
| scarred, the guy will likely stay away from anything resembling
| AI/ML for the rest of his life.
|
| Unlike language models, humans really do learn.
| StrangeATractor wrote:
| If he isn't he'll need to find new work anyway. Imagine
| searching that guy's name while looking for an attorney.
| Antoniocl wrote:
| I would hope so, at a minimum! I'm shocked that signing an
| affidavit in a court of law certifying the existence of made-up
| courses isn't simply criminal.
| anamexis wrote:
| Intent (mens rea) is a core part of what makes a crime a
| crime.
| anigbrowl wrote:
| Look up 'strict liability'.
| kube-system wrote:
| That's an exception, not the general rule.
| occamrazor wrote:
| Strict liability is extremely rare in criminal matters.
| favorited wrote:
| Almost certainly not. It's astoundingly difficult to get
| disbarred. I heard a lawyer say the only reliable way to get
| disbarred is to steal money from your clients. Judges rarely
| even use their inherent power to sanction, though he
| certainly will in this case.
| ftxbro wrote:
| I almost wonder if it could be something like one who
| deliberately slips on a grocery store floor to do some legal
| shenanigans. Like I'm sure there are some people who if they
| saw some spilled milk on a store floor they would be like 'it's
| my lucky day' and maybe similarly this lawyer saw a service
| that tells lies and he could have been like 'this is too good
| to be true'.
| latexr wrote:
| Prior discussion on the same matter from a different link:
| https://news.ycombinator.com/item?id=36095352
| tromp wrote:
| > The other five bogus cases were called Shaboon v. Egyptair,
| Petersen v. Iran Air, Martinez v. Delta Airlines, Estate of
| Durden v. KLM Royal Dutch Airlines, and Miller v. United
| Airlines.
|
| Tyler Durden no doubt...
| rvba wrote:
| > The lawyer's affidavit said he had "never utilized ChatGPT as a
| source for conducting legal research prior to this occurrence
| (...)"
|
| I wonder if the court tried to verify that.
| unsignedint wrote:
| Simply put...
|
| ChatGPT is not a search engine.
|
| Probably OpenAI needs to prominently display this in their site.
|
| If you are using it to find any factual information, you are
| using it wrong. You can perhaps find some hint on angle of how
| you would search on things elsewhere, but that's about it...
| seydor wrote:
| this is funny. However GPTs are great linear interpolators
| between stories and probably also between judgements. Maybe they
| will be useful to replace judges
| kristianbrigman wrote:
| How do these usually get checked? I mean, maybe he's already done
| this successfully a few times.
| ajb wrote:
| They get checked by the lawyer for the other side.
| pkilgore wrote:
| Usually the first thing a Judge's clerk will do before a
| judge reads a brief is pull all of the authority cited for
| the judge to have ready-to-review along side the brief itself
| (if not analyzed, highlighted, summarized, etc. etc.
| depending on the judge).
|
| Now, whether the judge _actually reads them_ is debatable (I
| had my doubts sometimes). But you bet your ass that if the
| Clerk simply cannot find a case, the Judge will be informed
| of that.
|
| YMMV in State courts, which can be all over the place in
| terms of professionalism. But you should _at least_ assume
| your opponent is going to read your cases because the easiest
| way to beat someone in court is to point out the law you rely
| on is bad.
| 0xbadcafebee wrote:
| Were they any worse than the normal junk cases that get filed
| every day in this country?
| onionisafruit wrote:
| "unprecedented"? ChatGPT says there is precedent and gave me
| several citations.
| hluska wrote:
| For reference, here is the judge's order. Endnote #2 alone is
| worth the price of admission:
|
| https://s3.documentcloud.org/documents/23826753/judgeaskingt...
| StrangeATractor wrote:
| That guy has some work to do on his resume.
| josu wrote:
| He'll just outsource it to chatGPT.
| bitwize wrote:
| So turds turn up in AI law as well...
| Brendinooo wrote:
| Yeah, AI-generated fake cases would definitely be unprecedented,
| unless SmarterChild did a stint as a paralegal in the early
| aughts...
| not2b wrote:
| At minimum the sanctions should include a fine sufficient to
| cover the costs of everyone who had to deal with this: the court,
| opposing attorneys. Maybe punitive damages too. But let the guy
| keep his law license (unless there's a second offense).
| CSMastermind wrote:
| It feels like there definitely should be punitive damages?
|
| It's like they didn't even check the text that ChatGPT
| generated for correctness.
___________________________________________________________________
(page generated 2023-05-30 23:00 UTC)