[1] https://blog.autorouting.com/p/sequential-optimal-packing-fo...

author here: This is basically our philosophy. LLMs can churn out constraints/code very quickly to pull out the specific requirements for a design or the chips you're using. When people use tscircuit (or any electronics-as-code framework) they can talk to an LLM and just keep yelling at it in the same way you yell at an LLM to fix a web page. The success of web pages and LLMs is built from small constraint algorithms like flexbox and CSS grid, this article is just one constraint algorithm that can help LLMs approximate a solution without specifying a bunch of XY coordinates that would challenge its spatial understanding

Comments URL: https://news.ycombinator.com/item?id=47605425

Points: 20

# Comments: 13

Comments URL: https://news.ycombinator.com/item?id=47447935

Points: 2

# Comments: 1

I also have on my desk "Algorithms for VLSI Physical Design Automation Third Edition" which I really like, but it's ~20 years old and has a lot of nomenclature that can be helpful, but I'm not a big believer in how the problems are broken down, which is IMO more oriented towards "designs with repeated patterns" rather than PCBs that don't usually repeat patterns (unless you're doing an LED matrix)

The tension in autorouting IMO is people generally want something ideal that passes all design rule checks. My thinking (and IMO the more modern way of thinking) is that fast algorithms, fast feedback loops and AI participation are more important.

There are also a lot of relevant algorithms in VLSI/chip design, the folks at OpenROAD seem to have good stuff although I'm not intimately familiar.

One of the biggest problems in my view for training an AI to do autorouting is the traditional grid-based representation of autorouting problems which challenges spatial understanding. But we know that vision models are very good at classifying, so I wondered if we could train a model to output a path as a classification. But then how do you represent the path? This lead me down the track of trying to build an autorouter that represented paths as a bunch of patterns.

More details: https://blog.autorouting.com/p/the-recursive-pattern-pathfin...

Comments URL: https://news.ycombinator.com/item?id=47143717

Points: 26

# Comments: 5

Frameworks like atopile, tscircuit (disclaimer: I’m a tscircuit lead maintainer) and JITX are critical here because they enable the LLM to output the deep knowledge it already has. The author is missing a couple pieces to really get great output: 1) Context-friendly datasheets 2) DRC/Semantic review 3) LLM-compatible layout methods

The hardest to build is (3) and what I spend 90% of my time on. AI knows how do do spatial layout for things like flex or css grid but doesn’t have a layout method for PCBs. Our approach w/ tscircuit is to develop new layout systems that either match templates, new heuristic layouts (we are developing one called “pack”), or solve simple spatial constraints.

But tldr; it is only a matter of time before AI can output PCBs. It is not simple but we know what works with LLMs from witnessing the evolution of AI for website generation

The reason hardware has sucked in the past is poor tooling. But now open-source solutions are getting pretty good, and AI is covering many knowledge gaps.