191–200 of 380 posts
Earlier quoted context omitted.
I do massive amounts of zero shot document classification tasks, the performance keeps getting better. It’s also a domain where there is less of a hallucination issue as it’s not open ended requests.
I didn't ask what you do with LLMs, I asked how you see "fastest growing technology of all time".
I certainly hope it's not GPT-5. This model struggles with reasoning tasks Opus does wonderfully with. A cheaper GPT-4 that's this good? Neat, I guess. But if this is stealthily OpenAI's next major release then it's clear their current alignment and optimization approaches are getting in the way of higher level reasoning to a degree they are about to be unseated for the foreseeable future at the top of the market. (T…
Earlier quoted context omitted.
I wonder if it's RAGing? Dying Internet forums are way, way into the tail of the data.
No, I tested it, this is a pure model without RAG (at least no internet search)
Fascinating results: "Write a three sentence short story in the style of Nabokov about a broken motorcycle." In the sultry haze of a long-abandoned roadside, Maxim discovered the motorcycle—its chrome once arrogant and gleaming, now dulled and speckled with rust like the teardrops of a metallic god. He caressed the handle, the cold touch returning him to that electric dawn when, with Amalia clinging breathlessly to h…
Compare, this from real Nabokov (he wrote long sentences; sentences in imitation actually needs to be longer): Twelve years and some eight months later, two naked children, one dark-haired and tanned, the other dark-haired and milk-white, bending in a shaft of hot sunlight that slanted through the dormer window under which the dusty cartons stood, happened to collate that date (December 16, 1871) with another (August…
The sleek, serpentine carriages slithered through the verdant landscape, their velocity a silver-streaked affront to the indolent clouds above. Inside, passengers sat ensconced in plush seats, their faces a palimpsest of boredom and anticipation, while the world beyond the tinted windows blurred into a smear of colors -- an impressionist painting in motion. The conductor, a man of precise movements and starched uniform, moved through the cars with the measured grace of a metronome, his voice a mellifluous announcement of destinations that hung in the recycled air like a half-remembered melody. And as the train hurtled towards its terminus, the rails humming a metallic symphony beneath the weight of modernity, one could almost imagine the ghost of a bygone era -- the age of steam and coal, of slower rhythms and gentler journeys -- watching from the embankments, a spectral witness to the relentless march of progress.
I think this is a much better imitation.
Earlier quoted context omitted.
Are you trying the paid gpt or just free 3.5 chatgpt?
100% of the time when I post a critique someone replies with this. I tell them I've used literally every LLM under the sun quite a bit to find any use I can think of and then it's immediately crickets.
Also, the difference is so big and so plainly visible that I guess people don’t know how to even answer someone saying they don’t see it. That’s why you get crickets.
Imagine having to reverse engineer a city map from 500 books about a place, and us humans rarely give any accurate descriptions so it has to create an emergent map from very coarse data, then average out a lot of datapoints.
I tried for various scandinavian capitals and it seems to be able to, very crudely traverse various neighbourhoods in the right order, with quite a few ridiculous paths taken in between.
Ie. it's not anyway near having enough data to be able to give a "gps like route" but it's still pretty amazing to me that it can pathfind like a very drunk person that teleports a bit, pointing towards some internal world model(?).
When it'l be able to traverse a city from pure training data, wow. Would probably require heaps of historial local media and literature.
Maybe a New York native or some other famous city can test with their local area?
This is without a doubt the most advanced LLM out there, easily beating GPT4 and everything else. I asked it some programming questions for a niche programming language, and it's the first LLM that has been able to answer it correctly.
I've been told by several users here that GPT4 provides perfect programming answers for all languages, as long as you prompt it correctly. Maybe you need to work on your prompts?
Earlier quoted context omitted.
There's a core problem with LLMs: they learn sentences, not facts. So an LLM may learn a ton of English-language sentences about cats, and much fewer Spanish sentences about gatos. And it even learns that cat-gato is a correct translation. But it does not ever figure out that cats and gatos are the same thing. And in particular, a true English-language fact about cats is still true if you translate it into Spanish. S…
>> These machines are just unfathomably dumb. I agree with you, and we seem to hold a minority opinion. LLMs contain a LOT of information and are very articulate - they are language models after all. So they seem answer questions well, but fall down on thinking/reasoning about the information they contain. But then they can play chess. I'm not sure what to make of that. Such an odd mix of capability and uselessness,…
Earlier quoted context omitted.
You know at one point we wouldn't be able to benchmark them, due to the sheer complexity of the test required. I.e. if you are testing a model on maths, the problem will have to be extremely difficult to even consider a 'hustle' for the LLM; it would then take you a day to work out the solution yourself. See where it's getting at? When humans are no longer on the same spectrum as LLMs, that's probably the definition…
There is a huge class of problems that's extremely difficult to solve but very easy to check.
An interesting thing i've been trying is to ask for a route from A to B in some city. Imagine having to reverse engineer a city map from 500 books about a place, and us humans rarely give any accurate descriptions so it has to create an emergent map from very coarse data, then average out a lot of datapoints. I tried for various scandinavian capitals and it seems to be able to, very crudely traverse various neighbour…