11–20 of 478 posts
Learning to harness current tools helps to harness future tools. Work on projects that will benefit from advancements, but can succeed without them.
This was published the day before Gemini 2.5 was released. I'd be interested if they see any difference with that model. Anecdotally, that is the first model that really made me go wow and made a big difference for my productivity.
But it still feels more like a small incremental improvement rather than a radical change, and I still feel its limitations constantly.
Like... it gives me the sort of decent but uninspired solution I would expect it to generate without predictably walking me through a bunch of obvious wrong turns as I repeatedly correct it as I would have to have done with earlier models.
And that's certainly not nothing and makes the experience of using it much nicer, but I'm still going to roll my eyes anytime someone suggests that LLMs are the clear path to imminently available AGI.
Wasn't it back in the 1980s that you had to pay $1000s for a good compiler? The entire LLM industry might just be following in the compiler's footsteps.
> So maybe there's no mystery: The AI lab companies are lying, and when they improve benchmark results it's because they have seen the answers before and are writing them down. [...then says maybe not...] Well.. they've been caught again and again red handed doing exactly this. Fool me once shame on you, fool me 100 times shame on me.
I'd say most of the recent AI model progress has been on price. A 4-bit quant of QwQ-32B is surprisingly close to Claude 3.5 in coding performance. But it's small enough to run on a consumer GPU, which means deployment price is now down to $0.10 per hour. (from $12+ for models requiring 8x H100)
What innovation opens up when AI gets sufficiently commoditized?
Also:
> I think what's going on is that large language models are trained to "sound smart" in a live conversation with users, and so they prefer to highlight possible problems instead of confirming that the code looks fine, just like human beings do when they want to sound smart.
I immediately thought: That's because in most situations this is the purpose of language, at least partially, and LLMs are trained on language.
This was published the day before Gemini 2.5 was released. I'd be interested if they see any difference with that model. Anecdotally, that is the first model that really made me go wow and made a big difference for my productivity.
I doubt it. It still flails miserably like the other models on anything remotely hard, even with plenty of human coaxing. For example, try to get it to solve: https://www.janestreet.com/puzzles/hall-of-mirrors-3-index/
A few months ago I looked at essentially this problem from a different angle (generating system diagrams from a codebase). My conclusion[0] was the same as here: LLMs really struggle to understand codebases in a holistic way, especially when it comes to the codebase's strategy and purpose. They therefore struggle to produce something meaningful from it like a security assessment or a system diagram.
[0] https://www.ilograph.com/blog/posts/diagrams-ai-can-and-cann...
I'm not surprised, because I don't expect pattern matching systems to grow into something more general and useful. I think LLM's are essentially running into the same limitations that the "expert systems" of the 1980's ran into.
This was published the day before Gemini 2.5 was released. I'd be interested if they see any difference with that model. Anecdotally, that is the first model that really made me go wow and made a big difference for my productivity.
I doubt it. It still flails miserably like the other models on anything remotely hard, even with plenty of human coaxing. For example, try to get it to solve: https://www.janestreet.com/puzzles/hall-of-mirrors-3-index/
It was reverse engineering ~550MB of Hermes bytecode from a react native app, with each function split into a separate file for grep-ability and LLM compatibility.
The others would all start off right then quickly default to just greping randomly what they expected it to be, which failed quickly. 2.5 traced the function all the way back to the networking call and provided the expected response payload.
All the others hallucinated the networking response I was trying to figure out. 2.5 Provided it exactly enough for me to intercept the request and using the response it provided to get what I wanted to show up.