181–190 of 377 posts
I find it quite funny all these folks who are addicted to chasing frontier models, only just noticing that small models became "good enough" for most tasks. Those of us without fable-sized expense accounts noticed this quite a while back
Exactly! Composer 2/2.5 were amazing, cheap, and fast. Everyone else was Gaga about GPT 5.5 and such, while we were over here doing the work with less cost and more speed
Earlier quoted context omitted.
This is a misunderstanding of either the bitter lesson or what was being claimed, on multiple accounts. Firstly, the bitter lesson is merely about human expertise-tuned algorithms vs. throwing raw compute at a domain. But, notably, it is still domain-specific. No matter how much compute you throw at training an LLM, it is never going to beat a Chess engine at Chess. If you give a Chess engine 1,000,000 compute units…
I don't know much about chess engines; do they still use hand-tuned algorithms, or are they more like AlphaZero, where they learn through self-play to beat any/all possible human contenders? I don't believe DeepBlue was automated to that extent, but it may have been. In the latter case, the chess example would tend to support the Bitter Lesson, rather than refute it. I would also be VERY slow to claim that general-pu…
> I would also be VERY slow to claim that general-purpose models will never be competitive at chess.
This is not the claim. The claim is that for the same amount of compute, a general-purpose language model will never beat a Chess model. I'm dubious, but allow for the possibility that a language model could eventually compete at a top level against humans with enough compute. However, it will never compete with a dedicated Chess model with similar resources. Training a model for a specific task with the same amount of compute will outperform training a general-purpose model with the same amount of compute. This should be common sense, right? The bitter lesson was only about compute over human algorithms, not at throwing compute at a generalised domain over throwing compute at a specific domain.
You made arguments against two claims that I did not make (that I was trying to refute the bitter lesson or that I claimed that LLMs could never be competitive against humans at Chess), so I'd like to ask you read my statements a little more carefully this time.
Earlier quoted context omitted.
RAG is your friend (or any vector db). No model can vectorize an entire codebase in context. Even a big mainstream product (like Gemini) cannot handle more than ~1k lines without missing details and making mistakes. And about every 1k lines, it seems to forget the previous 1k, doesn’t it? So you can never hold more than a file or 2 (or 3) in context at a time without losing details. What you find is that the big mode…
Out of interest, have you tried the newer models? You are not describing my experience recently.
Even the best models available lose a ton of detail over time if you were to paste in tens of thousands of lines of code.
The only way to hold huge amounts of context with a high degree of accuracy is to store it using various mechanisms (one of which is RAG).
On “effectiveness”, I mean end use case effectiveness in the tasks at hand, not whatever benchmark the model developer or vendor themselves come up with - which may or may not be useful to the work I’m doing.
Earlier quoted context omitted.
Having multiple 6 year old cards doesn't seem like it's that big of burden for local LLMs. I get that a lot of people don't have them. And a single one can be VERY performant. And the smaller models like a 7B can run on much smaller hardware like a mid-range [3|4|5]060. My entire AI Dev Box cost $4500 in parts. 128GB RAM, i7-10700, 1TB and 2TB SSD, and 2x 3090s. Today's prices and inflation have definitely made that…
A single, used 3090 costs more than I have ever spent on a computer.
3090 pricing is something of a wild card. Since the only big-mem consume cards are the xx90s, and a 5090 is pushing $5000, resale value has gone way up. The bottom hit ~$700 last year. It's still a very good GPU, if power hungry.
A friend of mine told me earlier today that they had a discussion at work (a coding shop) about "downgrading" to luna from sol for cost reasons and that many were quite unhappy about this because they didn't want inferior tech to be forced upon them. Do they have a point? Is sol actually worth the extra cost? Especially if you ramp up the effort level?
Earlier quoted context omitted.
This idea has not failed to pan out at all. I work for a startup that is exactly what GP described, and am set for life because of how wildly successful it is. Notably, we are successful, in a genuine sense of the word: we bootstrapped from running tiny models to larger and larger models on our own slowly improving fleet of GPUs, and now have millions in revenue without a single dime of outside investment. Conversely…
Wait, you actually found a viable counter to The Bitter Lesson? Please say more
The actual argument of the Bitter Lesson essay is pretty limited but people's interpretation of it has gradually drifted until it's seen as prediction that current LLM will reach AGI at a large enough scale.
Earlier quoted context omitted.
Small amounts of world knowledge seems like it would inherently be tied to more hallucinations.
Perhaps we'll get to a point where believing any un-sourced information from an LLM will feel crazy. I don't want my model to know more than it needs to perform logic and use tools. Once it is capable of using tools I would much rather it looked up information or sourced it from existing context rather than just divine it from it's weights.