←back to thread

YC is wrong about LLMs for chip design

(www.zach.be)
317 points laserduck | 5 comments | 16 Nov 24 14:07 UTC | HN request time: 0.001s | source
Show context
klabb3 ◴[16 Nov 24 17:05 UTC] No.42157457[source]▶
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…
replies(6): >>42157615 #>>42157652 #>>42158074 #>>42162081 #>>42166294 #>>42167109 #
brookst ◴[16 Nov 24 17:37 UTC] No.42157652[source]▶
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?
replies(7): >>42157709 #>>42157955 #>>42158073 #>>42159585 #>>42159656 #>>42171900 #>>42172228 #
beepbooptheory ◴[16 Nov 24 17:45 UTC] No.42157709[source]▶
Can you actually like follow through with this line? I know there are literally tens of thousands of comments just like this at this point, but if you have chance, could you explain what you think this means? What should we take from it? Just unpack it a little bit for us.
replies(5): >>42157743 #>>42157792 #>>42157794 #>>42158219 #>>42158270 #
1. croshan ◴[16 Nov 24 17:56 UTC] No.42157794[source]▶
An interpretation that makes sense to me: humans are non-deterministic black boxes already at the core of complex systems. So in that sense, replacing a human with AI is not unreasonable.

I’d disagree, though: humans are still easier to predict and understand (and trust) than AI, typically.

replies(2): >>42158005 #>>42158767 #
2. sdesol ◴[16 Nov 24 18:20 UTC] No.42158005[source]▶
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-4o cannot tell that GitHub is spelled correctly:

https://app.gitsense.com/?doc=6c9bada92&model=GPT-4o&samples...

In this example, Claude cannot tell that GitHub is spelled correctly:

https://app.gitsense.com/?doc=905f4a9af74c25f&model=Claude+3...

I still believe LLM is a game changer and I'm currently working on what I call a "Yes/No" tool which I believe will make trusting LLMs a lot easier (for certain things of course). The basic idea is the "Yes/No" tool will let you combine models, samples and prompts to come to a Yes or No answer.

Based on what I've seen so far, a model can easily screw up, but it is unlikely that all will screw up at the same time.

replies(1): >>42158221 #
3. visarga ◴[16 Nov 24 18:43 UTC] No.42158221[source]▶
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 the elephant" situation.

replies(1): >>42159435 #
4. ◴[16 Nov 24 19:54 UTC] No.42158767[source]▶
5. sdesol ◴[16 Nov 24 21:18 UTC] No.42159435{3}[source]▶
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.