YC is wrong about LLMs for chip design • Hacker News Board

Re: YC is wrong about LLMs for chip design

#151

Post by catlifeonmars » Sat, Nov 16, 2024, 9:09 PM UTC

mgraczyk wrote: post #134

zachbee wrote: post #124

Earlier quoted context omitted.

Author here -- I don't disagree! I actually noted this in the article: > Well, it turns out that LLMs are also pretty valuable when it comes to chips for lucrative markets -- but they won’t be doing most of the design work. LLM copilots for Verilog are, at best, mediocre. But leveraging an LLM to write small snippets of simple code can still save engineers time, and ultimately save their employers money. I think desi…

Thanks for the reply! At large companies with many designers, a lot of time is spent coordinating and planning. LLMs can already help with that. As far as design/copilot goes, I think there are reasons to be much more optimistic. Existing models haven't seen much Verilog. With better training data it's reasonable to expect that they will improve to perform at least as well on Verilog as they do on python. But even if…

I’m actually curious if there even is a large enough corpus of Verilog out there. I have noticed that even tools like Copilot tend to perform poorly when working with DSLs that are majority open source code (on GitHub no less!) where the practical application is niche. To put this in other terms, Copilot appears to _specialize_ on languages, libraries and design patterns that have wide adoption, but does not appear to be able to _generalize_ well to previously unseen or rarely seen languages, libraries, or design patterns.

Anyway that’s largely anecdata/sample size of 1, and it could very well be a case of me holding the tool wrong, but that’s what I observed.

Re: YC is wrong about LLMs for chip design

#152

Post by crabmusket » Sat, Nov 16, 2024, 9:13 PM UTC

klabb3 wrote: post #142

OkGoDoIt wrote: post #127

Earlier quoted context omitted.

I think this comment and the parent comment are talking about two different things. One of you is talking about using nondeterministic ML to implement the actual core logic (an automated script or asking Dave to do it manually), and one of you is talking about using it to design the logic (the equivalent of which is writing that automated script). LLM’s are not good at actually doing the processing, they are not good…

> So an LLM would potentially be good at writing a first draft of that script, which Dave could then proofread/edit Right, and there’s nothing fundamentally wrong with this, nor is it a novel method. We’ve been joking about copying code from stack overflow for ages, but at least we didn’t pretend that it’s the peak of human achievement. Ask a teacher the difference between writing an essay and proofreading it. Look,…

> We’ve been joking about copying code from stack overflow for ages

Tangent for a slight pet peeve of mine:

"We" did joke about this, but probably because most of our jobs are not in chip design. "We" also know the limits of this approach.

The fact that Stack Overflow is the most SEO optimised result for "how to center div" (which we always forget how to do) doesn't have any bearing on the times when we have an actual problem requiring our attention and intellect. Say diagnosing a performance issue, negotiating requirements and how they subtly differ in an edge case from the current system behaviour, discovering a shared abstraction in 4 pieces of code that are nearly but not quite the same.

I agree with your posts here, the Stack Overflow thing in general is just a small hobby horse I have.

Re: YC is wrong about LLMs for chip design

#153

Post by sigh_again » Sat, Nov 16, 2024, 9:14 PM UTC

jamiequint wrote: post #112

sigh_again wrote: post #106

YC doesn't care whether it "makes sense" to use an LLM to design chips. They're as technically incompetent as any other VC, and their only interest is to pump out dogshit startups in the hopes it gets acquired. Gary Tan doesn't care about "making better chips": he cares about finding a sucker to buy out a shitty, hype-based company for a few billion. An old school investment bank would be perfect. YC is technically i…

First, VCs don't get paid when "dogshit startups" get acquired, they get paid when they have true outlier successes. It's the only way to reliably make money in the VC business. Second, want to give any examples of "shitty, hype-based compan[ies]" (I assume you mean companies with no real revenue traction) getting bought out for "a few billion". Third, investment banks facilitate sales of assets, they don't buy them…

[flagged]

Re: YC is wrong about LLMs for chip design

#154

Post by gyudin » Sat, Nov 16, 2024, 9:15 PM UTC

Thank god humans are superior in chips design especially when you have dozens billions of dollars behind you, just like Intel. Oh wait.

Re: YC is wrong about LLMs for chip design

#155

Post by sdesol » Sat, Nov 16, 2024, 9:18 PM UTC

visarga wrote: post #93

sdesol wrote: post #70

Earlier quoted context omitted.

With humans we have a decent understanding of what they are capable of. I trust a medical professional to provide me with medical advice and an engineer to provide me with engineering advice. With LLM, it can be unpredictable at times, and they can make errors in ways that you would not imagine. Take the following examples from my tool, which shows how GPT-4o and Claude 3.5 Sonnet can screw up. In this example, GPT-4…

It's actually a great topic - both humans and LLMs are black boxes. And both rely on patterns and abstractions that are leaky. And in the end it's a matter of trust, like going to the doctor. But we have had extensive experience with humans, it is normal to have better defined trust, LLMs will be better understood as well. There is no central understander or truth, that is the interesting part, it's a "Blind men and…

We are entering the nondeterministic programming era in my opinion. LLM applications will be designed with the idea that we can't be 100% sure and what ever solution can provide the most safe guards, will probably be the winner.

Re: YC is wrong about LLMs for chip design

#156

Post by paulsutter » Sat, Nov 16, 2024, 9:22 PM UTC

necovek wrote: post #121

paulsutter wrote: post #17

Generative models are bimodal - in certain tasks they are crazy terrible , and in certain tasks they are better than humans. The key is to recognize which is which. And much more important: - LLMs can suddenly become more competent when you give them the right tools, just like humans. Ever try to drive a nail without a hammer? - Models with spatial and physical awareness are coming and will dramatically broaden what’…

> Ever try to drive a nail without a hammer? I've driven a nail with a rock, a pair of pliers, a wrench, even with a concrete wall and who knows what else! I didn't need to be told if these can be used to drive a nail, and I looked at things available, looked for a flat surface on them and good grip, considered their hardness, and then simply used them. So if we only give them the "right" tools, they'll remain very l…

Those are all tools !! Congratulations

If you’re creative enough to figure out different tools for humans, you are creative enough to figure out different tools for LLMs

Re: YC is wrong about LLMs for chip design

#157

Post by igorkraw » Sat, Nov 16, 2024, 9:27 PM UTC

I did my PhD on trying to use ML for EDA (de novo design/topology generation, because deepmind was doing placement and I was not gonna compete with them as a single EE grad who self taught ML/optimization theory during the PhD).

In my opinion, part of the problem i that training data is scarce (real world designs are literally called "IP" in the industry after all...), but more than that, circuit design is basically program synthesis, which means it's _hard_. Even if you try to be clever, dealing with graphs and designing discrete objects involves many APX-hard/APX-complete problems, which is _FUN_ on the one had, but also means it's tricky to just scale through, if the object you are trying to do is a design that can cost millions if there's a bug...

Re: YC is wrong about LLMs for chip design

#158

Post by mportela » Sat, Nov 16, 2024, 9:34 PM UTC

crabmusket wrote: post #150

hinkley wrote: post #105

Earlier quoted context omitted.

I still have nightmares about the entry level EE class I was required to take for a CS degree. RC circuits man.

I studied mechatronics and did reasonably well... but in any electrical class I would just scrape by. I loved it but was apparently not suited to it. I remember a whole unit basically about transistors. On the software/mtrx side we were so happy treating MOSFETs as digital. Having to analyse them in more depth did my head in.

I had a similar experience, except Mechanical Engineering being my weakest area. Computer Science felt like a children's game compared to fluid dynamics...

Re: YC is wrong about LLMs for chip design

#159

Post by ithkuil » Sat, Nov 16, 2024, 9:39 PM UTC

brookst wrote: post #24

klabb3 wrote: post #10

I don’t mind LLMs in the ideation and learning phases, which aren’t reproducible anyway. But I still find it hard to believe engineers of all people are eager to put a slow, expensive, non-deterministic black box right at the core of extremely complex systems that need to be reliable, inspectable, understandable…

You find it hard to believe that non-deterministic black boxes at the core of complex systems are eager to put non-deterministic black boxes at the core of complex systems?

I'm a non-deterministic black box who teaches complex deterministic machines to do stuff and leverages other deterministic machines as tools to do the job.

I like my job.

My job also involves cooperating with other non-deterministic black boxes (colleagues).

I can totally see how artificial non-deterministic black boxes (artificial colleagues) may be useful to replace/augment the biological ones.

For one, artificial colleagues don't get tired and I don't accidentally hurt their feelings or whatnot.

In any case, I'm not looking forward to replacing my deterministic tools with the fuzzy AI stuff.

Intuitively at least it seems to me that these non-deterministic black boxes could really benefit from using the deterministic tools for pretty much the same reasons we do as well.

Re: YC is wrong about LLMs for chip design

#160

Post by aleph_minus_one » Sat, Nov 16, 2024, 9:43 PM UTC

akra wrote: post #143

unoti wrote: post #25

Earlier quoted context omitted.

>The problem with this extrapolation is that the software industry is pretty much unique in the amount of information about its inner workings that is publicly available for training on... millions of lines of code that we published on the internet... > Nearly every other industry (with the possible exception of Law) produces publicly-visible output at a tiny fraction of the rate that we do. You are correct! There's…

> 1. Learn how the subject matter experts do the work. This will get harder I think over time as low hanging fruit domains are picked - the barrier will be people not technology. Especially if the moat for that domain/company is the knowledge you are trying to acquire (NOTE: Some industries that's not their moat and using AI to shed more jobs is a win). Most industries that don't have public workings on the internet…

> This will get harder I think over time as low hanging fruit domains are picked - the barrier will be people not technology. Especially if the moat for that domain/company is the knowledge you are trying to acquire (NOTE: Some industries that's not their moat and using AI to shed more jobs is a win).

Also consider that there exist quite a lot of subject matter experts who simply are not AI fanboys - not because they are afraid of their job because of AI, but because they consider the whole AI hype to be insanely annoying and infuriating. To get them to work with an AI startup, you will thus have to pay them quite a lot of money.