101–110 of 205 posts
Not sure about all its filters being RL. Sometimes it seems to flag its output as inappropriate because of a single word (or none at all). Also it has asymmetric behavior, e.g. it will make a joke about men but refuse to make one about women
Competitors will remove the political correctness filters and become more prominent. A Chinese stable diffusion art site is already gaining traction, no filters.
Amazing insight, particularly section 6. "- The two important but different abilities of GPT-3.5 are *knowledge* and *reasoning*. Generally, it would be ideal if we could *offload the knowledge part to the outside retrieval system and let the language model only focus on reasoning.* This is because: - The model’s internal knowledge is always cut off at a certain time. The model always needs up-to-date knowledge to an…
It's unclear to me how you could separate knowledge and reasoning: - Reasoning typically requires base knowledge to work from. A side effect of training reasoning is embedding knowledge into the model parameters. - Even if you offload the search portion (either through outputting special tokens that are postprocessed, or applying the model in multiple steps with postprocessing), you still need embedded knowledge for…
yeah, me too. There are a few cases I'd point your attention to.
1, preschool toys, kids somehow manage to put the square peg in the square hole. I mean, they may chew on them or push them around, but there's a "moment of magic" when they make it all click together. Maybe there's some implicit knowledge there, I know I played games like that, but I don't remember.
2, sudoku. you don't really need to know anything, just make each line row and box different. no memorization, just look. but what about the rules? does that count as knowledge?
I've been reading some math books lately, and I think we're not alone. Coping with sets of sets is a hard question that people have been wondering about for, as far as I can tell, a long time.
For now, it's probably safe to say, knowledge about knowledge is different that just knowledge, and having one layer work on k1 and another layer work on k2 is ok. maybe someday add k3...kn. Other fields do that. Worth checking out.
I think, we could both get very fussy about what exactly that _means_. But for now, I'm happy to be charitable in my reading. I'd also expect them to run into some really thorny problems when they try to pin down exactly what's going on, just like everybody else does. For today, good for them. Seems like a nice win.
Earlier quoted context omitted.
The problem with ChatGPT's "knowledge" is that it isn't trustworthy. It will happily output very confident sounding nonsense, or blatantly incorrect statements. We need a way to verify how accurate it's outputs are
I just had a run in with this yesterday. I asked it to explain box embeddings. It's a pretty niche topic so I didn't expect it to give the right answer. But the answer it gave sounded so confident but it was so wrong. It took a not al vector embeddings approach but replaced that with box. I tried correcting it but it refused to budge and still sounded confident.
Amazing insight, particularly section 6. "- The two important but different abilities of GPT-3.5 are *knowledge* and *reasoning*. Generally, it would be ideal if we could *offload the knowledge part to the outside retrieval system and let the language model only focus on reasoning.* This is because: - The model’s internal knowledge is always cut off at a certain time. The model always needs up-to-date knowledge to an…
Not sure about all its filters being RL. Sometimes it seems to flag its output as inappropriate because of a single word (or none at all). Also it has asymmetric behavior, e.g. it will make a joke about men but refuse to make one about women
Earlier quoted context omitted.
How much disk space does 175B parameters use? A float or half precision float per parameter or does it need pointers to connections too? Given how responses are generated in seconds and for free I am fairly sure it could run on a desktop computer.
One float per param, so naively 175*4 = ~700GB on disk. Most recent models are trained in FP16 or BF16 so 350GB. And there's some work on quantizing them to INT8 so knock that down to a mere 175GB. You can definitely run it on a desktop computer using RAM and NVME offload to make up for the fact that you probably don't have 175GB of GPU memory available, but it won't be fast: https://huggingface.co/blog/bloom-inferen…
Not sure about all its filters being RL. Sometimes it seems to flag its output as inappropriate because of a single word (or none at all). Also it has asymmetric behavior, e.g. it will make a joke about men but refuse to make one about women
Competitors will remove the political correctness filters and become more prominent. A Chinese stable diffusion art site is already gaining traction, no filters.
(Already happens with Lensa.)
GPT seems to be doing something incredibly different than prior AI. Is it really a Bayesian "next word" chooser at incredible scale?
Earlier quoted context omitted.
Current GPT version is not very good at math, and it's not at all clear whether this can be fixed within a language model. Q: I have 2 cats and 1 horse. How many legs do they have in total? A: If you have two cats and one horse, then the total number of legs they have is 8. Cats typically have four legs, while horses have four legs as well. So two cats would have a total of 8 legs, and when you add the four legs of t…
These errors are common and important to note. Though what I find fascinating is how often I can prompt engineer around these errors by telling GPT to just be smarter and think more carefully. Just tried the following for instance. Q: You are a master logician, who can solve all manner of language problems and have excellent math skills. I have 2 cats and 1 horse. How many legs do they have in total? Show your reason…
Earlier quoted context omitted.
Yes. GPT doesn't really deal in meanings. Much like autocomplete, it doesn't know what the end of a sentence will be when it starts it. If it randomly chooses different words at the start of a sentence, it may pretend to have a different belief by the end. In reality it doesn't have beliefs any more than a library does. It implicitly contains beliefs (since it's been trained on them) and it can imitate them, but whic…
So if we asked GPT to write a book, it would be hallucinating a chain of words without sticking to any coherent plot. However, we could use a "multi-resolution" approach even with today's version of GPT: at the top level we ask it to write a brief plot for the entire novel, at the next level we'll use this plot as the context and ask to outlines sub-plots of the 3 books in our novel, at the third level we'll use the…