News for hackers. Stuff that matters.
Re:Advancing chip design with OpenAI models by fooblaster on Wednesday November 18, 2026 @03:12PM (#50551505)
This is a very verifiable task with well defined metrics and verifiable results. Chip designers are going to have just a rough time of it as software engineers.
Re:Advancing chip design with OpenAI models by denverllc on Wednesday November 18, 2026 @03:26PM (#50551675)
By “rough time of it” do you mean chip designers are going to be inundated with slop that “works” but is overly complex, slowly degrades the system over time, and which nobody understands and this can fix? Or was it that they’d have to speak to insufferable AI agents who pretend to do things they don’t and also write in the most obtuse language possible?
Re:Advancing chip design with OpenAI models by fooblaster on Wednesday November 18, 2026 @03:34PM (#50551770)
I think these designers will be forced to deal with this slop, when they all collectively realize llms can produce more efficient designs then they could before the project tape out date.
Re:Advancing chip design with OpenAI models by bee_rider on Wednesday November 18, 2026 @04:00PM (#50552060)
Is the management of hardware companies much better than that of software companies? Because yeah your description seems accurate. Which points to the question of “why would software developers sign up for this willingly.” They largely don’t, the extent to which the system seems obviously stupid on the ground is the extent to which it is mandated from above.
Re:Advancing chip design with OpenAI models by throwawaycsdc3 on Wednesday November 18, 2026 @08:21PM (#50554848)
In many ways, I think so.

The big difference is in hardware it's much easier to measure cost/bug and days_of_schedule_slip/bug. Because we have those metrics, and people trust them, we can much more easily justify decisions that software teams never make. Like spending big on verification.

Why do you think we try to push everything into software. You guys are free, right? :)

Re:Advancing chip design with OpenAI models by anvuong on Wednesday November 18, 2026 @03:47PM (#50551920)
> very verifiable task with well defined metrics

It's really not though. Both AMD and Intel have learnt bitter lessons about trusting simulators too much. Chips and antenna design are hard because it's a chaotic system, small changes in placement can whack the whole interference pattern.

Re:Advancing chip design with OpenAI models by fooblaster on Wednesday November 18, 2026 @04:15PM (#50552219)
Again the vast major of performance/power issues are very much unveiled in simulators. Yes you can have gaps, like di/dt issues in the power tree or whatever. Chips are full of inefficient RTL that is below the bar of where engineers should spend their time. LLMs are really good at that stuff.
Re:Advancing chip design with OpenAI models by throwawaycsdc3 on Wednesday November 18, 2026 @06:19PM (#50553752)
Good ASIC design is not like FPGA design. For FPGA design I think your analysis is spot on. But FPGA design is configuring someone else's ASIC. ASIC design is circuit design, even if you're describing the circuit with RTL, it's still circuit design. To differentiate that ASIC you need to transform the net lists into circuits that are actually interesting. If you just use the defaults you're unlikely to sell a single chip as your performance will almost certainly underwhelm. In think in most ASICs I've worked on I have more TCL code driving the tools to make them do what I want them to do than I have RTL. RTL is shockingly efficient at describing data flow.
Re:Advancing chip design with OpenAI models by bri3d on Wednesday November 18, 2026 @07:44PM (#50554510)
I agree with this, and I think most of the posters here aren’t following.

LLMs are very good at RTL (all I can consider is that the parallel posters arguing otherwise haven’t tried a modern one against significant RTL?). It’s easy to verify, the optimization constraints are relatively straightforward, and there’s adequate simulation to build a good gym for it.

LLMs are not good at layout and floor planning and because there is near zero public data available, I’m not sure how well they’ll iterate. For PCB design they’re improving because while it’s a similarly thorny problem, the physical constraints (trace properties on a given substrate) are highly public and can be simulated and turned into an RL gym. For ASIC, any public PDK is 10-20 years old so making an RL gym becomes outrageously difficult on top of the fundamental problem (highly multivariate/layered spatial optimization) being hard to solve.

Re:Advancing chip design with OpenAI models by anon-3988 on Thursday November 19, 2026 @12:22AM (#50556364)
> LLMs are not good at layout and floor planning and because there is near zero public data available, I’m not sure how well they’ll iterate.

Surely you can train an RL model to do this

Re:Advancing chip design with OpenAI models by fooblaster on Wednesday November 18, 2026 @08:42PM (#50555025)
How do you think the architects that optimize the performance per watt of designs are working? they simulate at the circuit level. It's all stiff that llms can be fantastic at. The only question is will anyone invest enough money building the datasets to be good at this. Given the hype around RSI, the answer is .. yes.

anyone who thinks llms can't get good at this is engaging in wishful thinking

Re:Advancing chip design with OpenAI models by IncreasePosts on Wednesday November 18, 2026 @05:22PM (#50553114)
Sure, but it's not like humans are particularly good at this aspect either. I assume a lot of human-created designs need to be reworked once they become a physical reality
Re:Advancing chip design with OpenAI models by oddIdentities on Wednesday November 18, 2026 @03:56PM (#50552026)
>verifiable results

"mean normalized reward" hahaha

Re:Advancing chip design with OpenAI models by tencentshill on Wednesday November 18, 2026 @04:15PM (#50552227)
...Until they encounter reality in the field. Chip designs are convoluted because of strange effects no one or no AI could realistically predict.
Re:Advancing chip design with OpenAI models by pedro_caetano on Wednesday November 18, 2026 @04:50PM (#50552668)
> task with well defined metrics and verifiable results.

You have not had the joy of being introduced to the dark arts of Analog/RF chip design.

Re:Advancing chip design with OpenAI models by fooblaster on Wednesday November 18, 2026 @08:39PM (#50555011)
I'm not really talking about analog design here.