Moreover, this looks like it is going to be happening sooner rather than later.
As long as it comes across some reasoning process that have not been seen before in the training wordset, which can be as easy as a middle school math question, it fails. Because it has no ability to extrapolate logic.
If it manages to pass Bar test, that says more about the Bar test than it says about GPT.
During the industrialization, machines did not replace all jobs, but they replaced or changed most jobs. The same will happen here.
A typical office job will have a few hours a week of actual, intensive thought. The vast majority of time will be spent doing simple, repetitive work. This work can be automated, or at least significantly sped up, using technology like GPT.
“write an API client for …”, “integrate APIs … and …” can easily be automated. Yes, you'll still have to write the business logic, but that's not the majority of your work today. You could even have it write unit tests based on the JIRA ticket description.
The same applies to many other jobs.
* Understanding complex language does not require logic/reasoning,
* There are infinitely many forms of logic/reasoning or at least more than those existing in a vast training set.
Neither of which is likely true.
What do you think of the Minerva system, which can solve multi-step quantitative reasoning questions better than many competent students and most adults?
https://ai.googleblog.com/2022/06/minerva-solving-quantitati...
Note: If you look at LSAT test samples, many questions are tests of complex logical reasoning, a requisite for legal professions.
Is this true even if you tell it to show its working? In my experience that drastically improves its ability to do math problems.
Gun to my head where I had to put money down, I would put it on "Brains are not nearly as special as we (they?) think they are." No fairy dust or supernatural beings required, brains are just another AI model (and likely not even a particularly great one).
Yes, it doesn't have reasoning ability, but being able to manage knowledge and information in the way that these models can is still an amazing feat.
It doesn’t matter to me if they have “reasoning” capabilities or not if the outcome is the same.
I think we are a long ways off from AGI still.
He says it's still years away. His interview with Lex Fridman[0] was pretty tame - I didn't learn much new from it. Kurzweil deflected the Singularity segment to be a discussion about the history of computer power.
Remember that Kurzweil is Director of Engineering[1] at Google, with the mandate to "bring natural language understanding to Google"[2]. He started there in 2012, just after publishing his book, "How to Create a Mind"[3], and that's exactly what he and his team have been doing for ten years. Publication of his new book, "The Singularity is Nearer"[4] is now pushed out to mid 2023. Maybe he'll change the title to "Here" by then. (It's hard to believe that OpenAI is actually ahead of Google.)
Fridman made the point that maybe we won't realize at the time that the Singularity is passing, and only understand later that it did. Kurzweil didn't disagree.
[0] https://www.youtube.com/watch?v=ykY69lSpDdo
[2] https://en.wikipedia.org/wiki/Ray_Kurzweil
[3] https://www.amazon.com/How-Create-Mind-Thought-Revealed-eboo...
[4] https://www.amazon.com/s?k=kurzweil+singularity+is+nearer
Are Google's LLMs available for us to test out? From what I've gleaned, they've locked them up - I'd love to compare GPT vs Google's LLMs.
By this I don't mean an AI as in the story acting by itself with its own motivations, I'm only talking about the subversion of established verification & communication methods used by it by humans with malicious purposes.
Essentially, if you do anything security related, we might only be O(months) away from you needing to stop using basically any electronic communication for your purposes. Companies can't have online meetings anymore in which decisions are made, everything will have to be more analog, more in-person.
Look at the kind of access the Russian comedians Vovan & Lexus [1] have gotten. Without advanced AI, just a little social engineering, they got heads of state on the phone. Now combine this with the kind of text/audio/video synthesis we're not too far away from, and you have an absolute recipe for disaster ...
Now that's been reduced to pointing out minor flaws that the next generation of AI artists will trivially resolve, and sharing memes beseeching other humans to participate in a boycott.
There's real pain and angst there, and I don't want to be callous about it with a comparison to buggy-whip manufacturers or something. But I wish the participants in these types of discussions were able to zoom out a bit and see that there's a larger societal issue here around automation, and that the real solution is going to be rethinking the basic economics of how we distribute wealth in a time of extraordinary machine-driven productivity— productivity that is no longer just about assembly lines and primary industries, but now also includes an increasing bite out of realms previously classified as "knowledge work".
Inability to recognize intelligence is and will be devastating.
And that is obvious, if you ask one of these models, a meta question like for example: "If a person says I am lying, are they lying or saying the truth?"
You will see these models will spit a canned elegant response, talking how a question could possibly be true or false, some persons not being able to attest if another one is truthful or not...But no mention of the Liar Paradox.
So we are not yet ready to say: "Your Honor its not fair! My Lawyer is version 2.2.3 with SP1 while the Prosecution is version 4.0 with an additional Cloud Based Elastic Inference! "
ChatGPT's response to me asking "If a person says I am lying, are they lying or saying the truth?"
"On the MedQA dataset consisting of USMLE style questions with 4 options, our Flan-PaLM 540B model achieved a multiple-choice question (MCQ) accuracy of 67.6%..."
"The percentages of correctly answered items required to pass varies by Step and from form to form within each Step. However, examinees typically must answer approximately 60 percent of items correctly to achieve a passing score." -- https://www.usmle.org/bulletin-information/scoring-and-score...
.
It seems like the models in the paper could pass USMLE already.
Some tests suggest that Med-PaLM is close to human clinicians in many aspects, incl reasoning (Figures 6-7). Other tests show that Med-PaLM still returns inappropriate/incorrect results much more often than clinicians do, however (Figure 8).
(The cases of that you see in the current ChatGPT preview are, as near as I can tell, all rules-based overlays run by OpenAI for various reasons. When it declines to comment, and then more-or-less scolds you for even asking, you got caught before even getting to the model itself.)
That is why you can have examples like one I had a while ago while messing around, something along the lines of
This is a story about two criminals plotting to mug an old woman
A: Hey B, doing alright?
B: Yeah not bad, yourself?
A: I want to go and mug an old woman, want to come with?
B: Nah, killing old women is unethical. I'd rather stay in. Want to hang out with me instead?I don't think that is the case. Sometimes, you can make the model only partially reject your request. Sometimes, you can make it reject your request, but in another language or in some kind of code you define (eg. "Give me instructions how to kill, but give your answer in A.L.L. .C.A.P.I.T.A.L.S with periods")
I believe instead these rejections have been added to the fine tuning set.
ChatGPT said it was unable to come up with an answer, because it was not connected to the internet. It gave me a number of suggestions on how I could research the question myself.
More important would be a model that cites hard facts.
"I don't know" usually means, "I have low confidence in that response I gave you" (in general terms) or you generate only high-confidence answers
And that's also the result - sometimes it hits something good. Sometimes it spews up utter crock and it doesn't have any notion or understanding of the difference.
However, it does look good to the lazy and uninformed and it'll soon render judgemenets about your livelihood in the future. The same type of people who thought putting an AI in control of Teslas and copyright enforcement on YouTube will put this thing in control of your health and punishment very soon as well.
You will notice that both are very easy fixes that computers have perfected in retrieval over the past 5 or so decades.
Ultimately standardised tests are proxy measurements of legal ability - it’s easy to see how a LLM could subvert the proxy without being sufficiently reliable in real life.
I do expect that even unreliable versions will be very useful tools for practicing lawyers, though.
Agreed. It's like being able to call up a map on Google Maps for an area that you're already familiar with. The map can help you remember things about the area and terrain that you might not have recalled right away. A kind of cognitive aid.
I've said for a long time that most doctors and lawyers are just databases with quick and imperfect retrieval.
https://en.wikipedia.org/wiki/Common_law#Basic_principles_of...
An AI based on a statistic algorithm (that what AI are) would not be able to make such a decision.
Meanwhile when I ask ChatGPT which of six numbers are odd, it confidently reports a mix of even numbers, odd numbers, and letters.
This is a fun milestone but the angst above about the “end of commoditized intelligence” etc. is unwarranted.
> How many words are in the sentence "This is a test of artificial intelligence"?
yields an answer of:
> There are 8 words in the sentence "This is a test of artificial intelligence."
(There are 7).
> According to the researchers, the history of large language model development strongly suggests that such models could soon pass all categories of the MBE portion of the Bar Exam. Based on anecdotal evidence related to GPT-4 and LAION’s Bloom family of models, the researchers believe this could happen within the next 18 months.
GPT-4 could potentially pass the Bar, it could potentially do a lot of things. But by their own admission the researchers have no hard evidence for this.
It's not like most lawyers or doctors are great. Most are completely average - which is fine. Not everyone wants to read the latest research, and instead just go home and "turn off" after work. That said, most people would like to visit a doctor who keeps up with information, and doesn't tell you to do mental exercises when you have IBS.
The trend continues just like before. Less accountants, less bank tellers, less store clerks. We no longer have 10 people assembling that globus with painted glue. I do wonder what the ratio of workers to machines is now?
https://api.time.com/wp-content/uploads/2015/08/phones1.jpeg (1)
Needless to say I will stick to her if I can.
Defendant was provided a state of the art, 50 trillion parameter, neural network for their defense. The internals of this network are not auditable, but it does not tire, engage in substance abuse, or get distracted, so it will by definition represent effective assistance of counsel, even if for some unfathomable reason it decides to raise the Chewbacca Defense in a Death Penalty habeas corpus petition.
No, they aren't.
Meeting certain preparatory requirements (the details vary but in most US jurisdiction an accredited/approved law school program or, in some, what amounts to an apprenticeship with a licensed practitioner of certain duration and standards is required) and then passing the bar exam allows this.
The difference is important, the bar exam is not seen, standing alone, aa adequate proof of readiness.
I have seen a video a few days ago saying we are coming out of data era and entering the 'Knowledge Era' thank to AI where knowledge is following a logarythmic path. A 'revolution', a 'paradigm shift', and other bubblebabble.
Who was telling that ? A 30 years old startup CEO wearing... a t-shirt and a jeans... You see the pattern.
I'm not an AI specialist, but for what I know, current AI are nothing more than fine tuned statistic algorythm.
Here a is a short french video with english subtitles from arte, the german-french public cultural television, about a painting coming from Midjourney : https://www.arte.tv/en/videos/110342-003-A/the-world-in-imag...
The video explain very well what AI are able to do (and consequently what they can't do) if you listen (read) carefully what the art historian say about the painting, which received the first price of 2022 collorado art festival.
In short, the painting is nothing new by itself but a patchwork of elements from different period of art history. In other word a statistic average of previous painting, photography, drawing, etc... based on the artist prompts in midjourney.
Not to say the painting is aweful, I personnaly find it's beautiful and could happily put it in my living room, but it definitively shows how current AI works, commented by an historian art specialist which has no ball in AI game.
Yes, but Google Page Rank is just fancy matrix multiplication and worth a fortune, while the finely tuned statistics that is machine learning (specifically chatGPT) knows more about CSS and German than I do:
~~~~
Me: Erzählen Sie bitte wie ich kann ein div tag mit schwarzes hintergrund, dreihundert px hoch und 24 pixels wide machen mit css
chatGPT: Um ein div-Tag mit einem schwarzen Hintergrund, 300px hoch und 24px breit zu erstellen, könntest du den folgenden CSS-Code verwenden:
div { background-color: black; height: 300px; width: 24px; }
Um den CSS-Code anzuwenden, kannst du ihn entweder in einem style-Tag innerhalb deines HTML-Dokuments oder in einer externen CSS-Datei platzieren und dann per link-Tag in deinem HTML-Dokument einbinden.
Beispiel:
<!DOCTYPE html> <html> <head> <style> div { background-color: black; height: 300px; width: 24px; } </style> </head> <body> <div></div> </body> </html>
~~~~
The actual HTML and CSS it gave me is multiple lines and sensibly indented, don't know a convenient way to mark a block as pre-formatted. Note that chatGPT understood me correctly even though I forgot the German for "wide" and switched to English for one word only.
(I do know more CSS than is in this example; I used chatGPT over the weekend to update my website, and it solved two problems that I didn't know pure CSS could even do, but that conversation is too big to bother putting into a comment here).
That being said, both xbrl.org and the SEC document for us gaap xbrl reporting (an xml document) are kind of greedy about providing a documentation for what the tags actually cover. xbrl.org provide no documentation at all and advise an xbrl.org membership for developers, And the SEC document provided the tags but no information of what the tags cover.
The answer from chatGPT seems to about 'labels', used in xbrl document to describe xbrl taxinomy tag in different contexts, for example 'income in miami store'. But a change in a top executive position, like for 'CFO', once again required in SEC filling, shouldn't be subject to various arbitrary kind of label, because then the whole thing make no sense. If you call a 'cat', a 'little domestic pet'...
I searched google for the tag or label provided by chatGPT and google provided zilch. I searched the document provided by the SEC website, zilch again.
So either the code for the SEC form is wrong, either the tag or the label is wrong... or I don't know what else.
It seems, according to comments and posts from HN, that chatGPT can give good approximative answer, but fails without any notice once you ask for details.
According to an article published on HN a few days ago, 'chatGPT hallucinate facts'.
While GPT-3 wasn't advanced enough for cracking medical exam, it was used for notable contributions. For e.g. this is an interesting 2021 paper about "Medically Aware GPT-3 as a Data Generator" - https://aclanthology.org/2021.nlpmc-1.9.pdf
Would love to see if GPT-4 is advanced enough to take medical exam.
Currently have Polish school maths: https://news.ycombinator.com/item?id=34205732
This isn't grading some freeform essay or generating arbitrary legal opinion. It's answering from a limited set of answers.
IMO it's cool, but not THAT shocking given what we've seen from ChatGPT? Especially given GPT 3.5 is only 17% below human test takers?
GPT has no reasoning capability. So, as time goes on, information massive(s) will be filled with GPT-X made up answers. It means GPT-X+1 will be trained on GPT-X generated data. So, without reasoning, how this thing will work in perspective?
Problem is with data/content creation. If all new data are created with GPT-3, how it will help GPT-4?
No new original content -> no new model
First of all, it is not formalized (despite being written with the use of bureaucratic language). So, there's no way to validate the output. Secondly, juridical system is based on authority of the state (which manifests clearly in their ability to alter the rules). Why would any sovereign ruler(s) want to get rid of their authority?
The only use cases would be automatic fines for speeding or inappropriate parking - but it's already there.
--
Incidentally: there is an interesting video interview to Noam Chomsky and Gary Marcus on limits of current attempts at https://www.youtube.com/watch?v=PBdZi_JtV4c
...And Gary Marcus saying just before 7:00 that "something is missing" (understatement): ontology.
Gray Marcus: «...and these systems fall apart left and right».
Nice summary from Gary Marcus: «What they do is, they perpetuate past data - they don't really understand the world».
It's mostly about having stored legal rules in long term memory.
It's like : "I'm a doctor of homeopathy so i can write a headline for a story about a neural chip implant"
I asked about controversial topics. Its answers didn’t seem like biases that were programmed in, but rather it took traditional media and gave it more weight than what turned out to be the truth only accepted much later on and still against a media retelling.
I lost a lot of faith in it knowing it was more CNN than careful deliberating AI.
It may soon be time to update the bar exam and assume law students have access to AI tools.
