Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Lessons after a Half-billion GPT Tokens

kenkantzer.com

Post reply on HN
Print view View original

131–140 of 179 posts

Re: Lessons after a Half-billion GPT Tokens

#131

Post by gopher_space »

eru wrote: post #104
gopher_space wrote: post #72

Earlier quoted context omitted.

> Summarizing is pretty rock solid in my testing, but reasoning is really hard. Asking for analogies has been interesting and surprisingly useful.

Could you elaborate, please?

Instead of `if X == Y do ...` it's more like `enumerate features of X in such a manner...` and then `explain feature #2 of X in terms that Y would understand` and then maybe `enumerate the manners in which Y might apply X#2 to TASK` and then have it do the smartest number.

The most lucid explanation for SQL joins I've seen was in a (regrettably unsaved) exchange where I asked it to compare them to different parts of a construction project and then focused in on the landscaping example. I felt like Harrison Ford panning around a still image in the first Blade Runner. "Go back a point and focus in on the third paragraph".

Re: Lessons after a Half-billion GPT Tokens

#132

Post by azinman2 »

codewithcheese wrote: post #28
CuriouslyC wrote: post #10

If you used better prompts you could use a less expensive model. "return nothing if you find nothing" is the level 0 version of giving the LLM an out. Give it a softer out ("in the event that you do not have sufficient information to make conclusive statements, you may hypothesize as long as you state clearly that you are doing so, and note the evidence and logical basis for your hypothesis") then ask it to evaluate…

Yeah also prompts should not be developed in abstract. Goal of a prompt is to activate the models internal respentations for it to best achieve the task. Without automated methods, this requires iteratively testing the models reaction to different input and trying to understand how it's interpreting the request and where it's falling down and then patching up those holes. Need to verify if it even knows what you mean…

Which automated method do you use?

Re: Lessons after a Half-billion GPT Tokens

#133

Post by teleforce »

spunker540 wrote: post #115
weatherlite wrote: post #91

Earlier quoted context omitted.

> Similarly, certain ML tasks are now easy to implement even for dumb dumb web devs like me For example?

Lots of applied NLP tasks used to require paying annotators to compile a golden dataset and then train an efficient model on the dataset. Now, if cost is little concern you can use zero shot prompting on an inefficient model. If cost is a concern, you can use GPT4 to create your golden dataset way faster and cheaper than human annotations, and then train your more efficient model. Some example NLP tasks could be clas…

> But I’d be curious which areas of NLP __weren’t__ disrupted by LLMs

Essentially come up with a potent generic model using human feedback, label and annotation for LLM e.g GPT 4, then use it to generate golden dataset for other new models without human in the loop, very innovative indeed.

Re: Lessons after a Half-billion GPT Tokens

#135

Post by Kiro »

phillipcarter wrote: post #84
Xenoamorphous wrote: post #63

> We always extract json. We don’t need JSON mode I wonder why? It seems to work pretty well for me. > Lesson 4: GPT is really bad at producing the null hypothesis Tell me about it! Just yesterday I was testing a prompt around text modification rules that ended with “If none of the rules apply to the text, return the original text without any changes”. Do you know ChatGPT’s response to a text where none of the rules…

> I wonder why? It seems to work pretty well for me. I read this as "what we do works just fine to not need to use JSON mode". We're in the same boat at my company. Been live for a year now, no need to switch. Our prompt is effective at getting GPT-3.5 to always produce JSON.

There's nothing to switch to. You just enable it. No need to change the prompt or anything else. All it requires is that you mention "JSON" in your prompt, which you obviously already do.

Re: Lessons after a Half-billion GPT Tokens

#136

Post by Kiro »

satisfice wrote: post #49

I keep seeing this pattern in articles like this: 1. A recitation of terrible problems 2. A declaration of general satisfaction. Clearly and obviously, ChatGPT is an unreliable toy. The author seems pleased with it. As an engineer, I find that unacceptable.

That has nothing to do with you being an engineer. It's just you. I'm an engineer and LLMs are game changers for me.

Re: Lessons after a Half-billion GPT Tokens

#137

Post by chromanoid »

fl0id wrote: post #108
chromanoid wrote: post #95

GPT is very cool, but I strongly disagree with the interpretation in these two paragraphs: I think in summary, a better approach would’ve been “You obviously know the 50 states, GPT, so just give me the full name of the state this pertains to, or Federal if this pertains to the US government.” Why is this crazy? Well, it’s crazy that GPT’s quality and generalization can improve when you’re more vague – this is a quin…

Well, or it is just memorizing mappings. Not like as in reproducing, but having vectors similar to mappings that it saw before.

Yeah, but isn't this higher order pattern matching? You can at least correct during a conversation and GPT will then use the correct mappings, probably most of the times (sloppy experiment): https://chat.openai.com/share/7574293a-6d08-4159-a988-4f0816...

Re: Lessons after a Half-billion GPT Tokens

#138

Post by thibaut_barrere »

sebastiennight wrote: post #100
thibaut_barrere wrote: post #46

Earlier quoted context omitted.

Not sure if that fits the bill, but here is an example with 200 sorted items based on a question (example with Elixir & InstructorEx): https://gist.github.com/thbar/a53123cbe7765219c1eca77e03e675...

There are a few improvements I'd suggest with that prompt if you want to maximise its performance. 1. You're really asking for hallucinations here. Asking for factual data is very unreliable, and not what these models are strong at. I'm curious how close/far the results are from ground truth. I would definitely bet that outside of the top 5, numbers would be wobbly and outside of top... 25?, even the ranking would be…

Thanks for the suggestions, appreciated!

For some context, this snippet is just an educational demo to show what can be done with regard to structured output & data types validation.

Re 1: for more advanced cases (using the exact same stack), I am using ensemble techniques & automated comparisons to double-check, and so far this has really well protected the app from hallucinations. I am definitely careful with this (but point well taken).

2/3: agreed overall! Apart from this example, I am using French only where it make sense. It make sense when the target is directly French students, for instance, or when the domain model (e.g. French literature) makes it really relevant (and translating would be worst than directly using French).

Re: Lessons after a Half-billion GPT Tokens

#139

Post by Oras »

cpursley wrote: post #88
Oras wrote: post #81

Earlier quoted context omitted.

I did, none of the open source parser worked well with tables. I had the following issues: - missing cells. - partial identification for number (ex: £43.54, the parser would pick it up as £43). What I did to compare is drawing lines around identified text to visualize the accuracy. You can do that with tesseract.

Interesting. Did you try MS's offering (Azure AI Document Intelligence). Their pricing seems better than Amazon.

Not yet but planning to give it a try and compare with textract.

Re: Lessons after a Half-billion GPT Tokens

#140

Post by visarga »

fnordpiglet wrote: post #120
moozilla wrote: post #117

Earlier quoted context omitted.

Apparently it is possible to measure how uncertain the model is using logprobs, there's a recipe for it in the OpenAI cookbook: https://cookbook.openai.com/examples/using_logprobs#5-calcul... I haven't tried it myself yet, not sure how well it works in practice.

There’s a difference between certainty of the next token given the context and the model evaluation so far and certainty about an abstract reasoning process being correct given it’s not reasoning at all. These probabilities and stuff coming out are more about token prediction than “knowing” or “certainty” and are often confusing to people in assuming they’re more powerful than they are.

> given it’s not reasoning at all

When you train a model on data made by humans, then it learns to imitate but is ungrounded. After you train the model with interactivity, it can learn from the consequences of its outputs. This grounding by feedback constitutes a new learning signal that does not simply copy humans, and is a necessary ingredient for pattern matching to become reasoning. Everything we know as humans comes from the environment. It is the ultimate teacher and validator. This is the missing ingredient for AI to be able to reason.

Post reply on HN