This PCB is brought to you by Fable 5 | Hacker News Reader

This PCB is brought to you by Fable 5

a6mzero.com

160 pointsjasonpeacock106 comments

As someone who does both hardware design (mostly high precision analog electronics) and software engineering, the difference between both fields in AI capability is striking. Models like Fable and Astra can provide lots of interesting insights into the design of specialty electronics when prompted correctly. Yet they can hardly put that knowledge to work if instructed to generate a schematic or lay out a PCB.

Of course, for readers here with a solid grasp on how LLM's operate it's not exactly surprising. Still, I feel this is exactly the kind of thing that drives home that the way we reason about (general) intelligence does not map cleanly to LLM operation, no matter how advanced the current models are.

If anything, it is surprising that the LLM is so bad at stealing a ready-made RP2350 design! There are plenty of easy-to-find tutorials like [0] and [1] that handhold you through the entire design process, and a simple search will give you dozens of design files for open-source boards.

At this level of board complexity you almost have to try to make it completely non-functional, so although it is nice to see it in practice I am not exactly surprised that a LLM with a decent bunch of assistance managed to do it. But there's quite a gap between the equivalent of poorly copying a "Hello World" from StackOverflow and making actual production-ready boards.

[0]: https://pip-assets.raspberrypi.com/categories/1214-rp2350/do...

[1]: https://jlcpcb.com/blog/how-to-design-layout-with-rp2350

You have to be more specific about what you mean by design. The models are excellent and the netlist and the components along with tradeoffs.

Design means PCB routing. A schematic is the PCB equivalent to a Mermaid diagram.

There is very little sources compared to software and with hardware you can't really afford too many errors

It’s the training data. Finished work isn’t training data because parts are sooooo different, but maybe if the finished designs were properly labeled into the training pipeline it might work? Or the iterative work itself might need to be the training corpus.

Maybe it's not properly benchmarked.

A standard benchmark using kicad to create or fix electronic designs would go a long way in motivating and measuring improvement.

There's eebench, but maybe it's not exactly what you were thinking

It was featured on Astra's model card and promotional materials, which the folks there (at EE-Bench) really appreciated: https://eebench.org/blog/can-ai-design-circuit-boards-yet/

I'd expect that upcoming models will be increasingly better tested and developed for this workload from now on.

i noticed the same treying to just generate 3D models using AI, i wonder if a well trained very specific world model would be better for the task

Me too, LLMs are bad at generating 3D models still but that and EE/ME CAD are the next frontiers.

Maybe they could try conquering GUI layouts and CSS first

Yeah enjoy it while it lasts. This is basically where LLMs were with coding a year or two ago. Give it a couple more years...

I just started using opus 4.8 and it's still trash at very domain specific stuff and debugging. It went down a rabbit hole trying to coerce the algorithm to work for 1 data point, which dramatically overfit the code. Later it did 11 experiments to try and figure out how to do the math, each one yielding an accuracy no better than a coin flip and each one it asserted beforehand that it had it this time, 100% accuracy.

We've got some time.

That's last gen though. I agree it's mediocre. Try Astra. It's significantly better than Opus and even Fable. I'm not sure about earlier OpenAI models.

I also thought we had time.

It seems to depend on the domain, and perhaps the tech stack? I’ve been disappointed by Astra, it’s worse than both Fable and Opus for me.

Yeah maybe. I dunno though, I'm using it in obscure SystemVerilog stuff. AI used to absolutely suck at that very recently but now it seems to have no problem.

I think the key is that you give it all of the info - put all the docs, the LRM, tool manuals, etc. in a directory so it can read it if it wants (it really really wants).

They say that every generation. https://www.youtube.com/watch?v=akNcZOoLKVk

I didn't say it was AGI, I just said it wasn't trash and that it's significantly better than it used to be.

Anyway just because AI sales people continually jump the gun doesn't mean AGI is never going to happen. It just means you just have to try the models yourself to see how good they really are, which I have done. Astra is really freaking good. (If you aren't paying.)

I suggest you give it a try and base your opinion on that.

No worries, Astra already shows signs of improvement which should make you happy for the short time before you realize why they’re making it better at this and CAD in general

I used them a bunch just for the component shopping, I can route PCBs just fine, that's not a throttling factor in any project, but ability to "send it shopping" and not only get the price/availablity for the options but look thru datasheet for quirks and parameters is very useful.

AI is exceptionally good at RP2040/RP2350/ESP32-based boards, we've ordered ~15 unique designs, mostly RP2040-based that were designed and autorouted with AI using tscircuit and usually OpenAI models.

Currently the major mistakes that AI makes: 1) Improperly rotated connectors (backwards USB port) 2) Endless routing loops for complex boards 3) Really huge/unreadable single page schematics

I'm extremely bullish on AI for PCB design, but there is a huge, huge tooling gap. We basically need to soup up all our collective design rule checks so that AI can work in corrective loops. It needs to check for things like "opamp schematic layout conventional" and "trace width closely matches reference design for chip". One thing that makes me super excited is supply-chain resiliency when chip/subcircuit-swapping becomes super easy

I’ve found that codifying design rules as skills is a major help in this area.

Those are "reinvent the world" level of changes. We're talking about an industry where nothing is standardized, and you want to rely on highly formalized documentation!?

I'm not exaggerating when I say that "which way is up" is an unsolved problem right now. Getting the industry to adopt a standardized manufacturing file format and standardized files describing things like footprints and pinouts would be a massive breakthrough. Let's start with that.

Standardization is extremely unlikely, chip manufacturers won't/haven't made a major effort here and having spoken with some, they don't want to. It is much easier and more feasible at this point to do automated visual analysis against the footprint and discovered photos from the internet

I'm still waiting on my order of 15 PCBs done with Sol - a mini-BT-keyboard that I hope will be comparable to the Psion 5 / Gemini PDA ones, using Kailh PG1316S switches. I still need to design and manufacture a housing (I do have a lot of hobbyist experience with this though), but the idea is to have a magsafe-connectable keyboard I can clip onto my Pixel and make use of the new Linux subsystem (or Termux) and do some productive stuff on the go. It's just been manufactured by JLC but not shipped yet. Funny enough, production itself was ~$70, then $80 for shipping, taxes and fees (tarriffs?).

Instead of directly generating Kicad, I chose to let it write "generators" in Python that output Kicad (S-Exps!) pcb and project - with mixed results - but I can generate a version with/without per-key Neopixels and customize certain parts of the board, including debug-stuff. I also _think_ this makes it easier to resume working on this in new sessions but not sure. Otoh, I never actually looked at the Python (vibed...) so it's still a lot of hard-coding.

I also landed on and used KicadRoutingTools after trying FreeRouting, combined with some minimal "auto-placing" code for larger ICs and such that are placed with certain constraints. My routing runs are way slower though - on the order of minutes.

I always wanted to try atopile - that might be a good match for AI/PCB work. The only thing that really held me back was the lack of routing.

> I always wanted to try atopile - that might be a good match for AI/PCB work.

Unfortunately all public open source work halted 6 months ago and they pivoted to a browser based IDE product to monetize: https://atopile.io/blog/atopile-v16

Thanks :(

I followed them for a while before the AI craze started. It looked promising back then, but I wasnt willing to invest time and attention back then on something so new.

Good thing I didn’t

That sounds like a cool project both for your pixel and the keyboard! Keep us posted how it goes!

I just got my PCBs - yay! I will try soldering the switches and MCU this weekend or early next week.

I'll try to write up a post if I get it all working. Probably even if not... publish your failures and all.

Atopile is ditching their cli. They're going the wrong direction.

It seems to me the first problem with AI in PCB design is that there isn't much in the way of machine friendly interfaces for the work. I watched Codex last night generate 3d renderings in Kicad to check the layout.

Bought to us by Fable 5 and the more-experienced colleague who foresaw potential issues.

Human in the loop.

Hey - I ordered a board yesterday. I used Opus 5, Astra, and Sol at points to QC the board, and offer power routing advice. (The MCU is a brand new one, and poorly documented unless they send you an NDA and the full docs).

Those models were not capable of even schematic editing or building. (I didn't bother with routing or placement). They made gross errors all over the schematic; changed the known-working parts and net routing I'd copy+pasted from previous boards, changed I2C to SPI for no reason, and generally produced an unusable, unreadable result. Overlapping symbols and labels etc.

What do you mean by power routing for an MCU? Like they wanted to fatten the traces or what?

It's an Atmosic Atm3430e, which includes RF energy harvesting. So, I'm using 3 power sources depending on the application: Coin cell, USB, and RF, with a 1v8 net for sensors. Its power pin routing has some particulars that are poorly documented, and there are no publicly available reference designs. There are a few design docs which help, but leave open questions. So, I used LLMs to help me figure out which pins to connect to which. They did not seem capable of actually doing the work directly, but they answered my questions. We will see how correctly in a few weeks...

Also used LLMs to try to figure out how to flash/debug it. The setup I normally use (Tac-Connect ST-Link 6 pin + Probe-rs) won't work here; it's cortex-m, but their official guides indicate they want you do use a Segger J-Link, which I'm not ready to pay for at this point. It is a very expensive thing. So I'm going to try an NXP MCU-Link Pro. The St-Linkv3 I've been using will likely not work.

?? I found the schematic here

https://atmosic.com/products_kit_atmevk-3430e-yqn/

Is this not it? They even have the .pcb file if you download the full board doc which I believe is everything you need.

This is a lot more than I thought you'd have to work with given your description. Full schematic, user guides, datasheet

Holy shit, I don't know how I missed that. Ty! I must have been only looking at the bare parts docs and not the DK.

Lol all good. Please use this instead of slopping up something that'll let the smoke out

This is amazing for people who don't know anything about it, while it's exactly the opposite for those who do

What PCB software did you give it? I'm having great success with Fusion (formerly known as Eagle) and others seem to be doing great with KiCad.

KiCad 10

> changed I2C to SPI for no reason

Heh, tongue firmly in cheek: there's a good reason to change from I2C to SPI. I2C's pretty shit in comparison :D

More seriously, I've had interesting mixed results. I had a hobby-maybe-commercialize-next-year Christmas lighting project that I started in March (if I start in March, this will definitely be ready for Christmas!) and got 90% of the way there... and then life got busy and it's sat there untouched with the holiday season coming up again quicker than I'd like. I threw Fable at it first to assess what's done, not done, look for schematic mistakes/improvements (it rightfully pointed out that the cheap LDO I was using was near its limits and suggested a better part).

Opus did a reasonable job of swapping out the LDO, putting reasonable values on all of the pull-ups/pull-downs, etc. Some of the labels did end up in slightly weird places and needed some manual correction. It also did a decent job of floor planning on the PCB side, but pretty much refused to do any routing other than power traces.

I've installed https://github.com/drandyhaas/KiCadRoutingTools this morning after seeing this article last night... we'll see how this goes. My first manual attempt at running the router did decent but it failed a bunch of DRC spacing rules and insisted on via-in-pad to make it all work. That's, I think, a side effect of Opus's floor planning. It's interesting to play around with to see what's good and not.

I should try that lib! (Same one mentioned in the article?)

I should also give layout/routing a try. My thought was, schematic design, from the perspective of what LLMs are good at, seems like the much more appropriate/easy tasks, so if it's failing at the basics there... I think I also experienced some consternation at patterns I've seen in real PCBs like a section dedicated to bypass caps that have no context of what pins they go to. (e.g. power connected to ground).

And I gave it a board that had a mixed of components/routing that I have used successfully one or many times, and parts that I am unsure about/don't know how to use and wire. Me seeing it make substantial changes to the known-working parts (My stake-in-the-ground), I got very nervous!

Yeah it's the one mentioned in the article. I've tried FreeRouting or whatever it's called before and had... ok results... but it's a pain in the ass to set up. This KiCadRoutingTools code was super easy to set up in comparison.

Edit: actually, one interesting thing to consider about routing vs. schematic design: my general experience with LLMs is that things work best when there's a feedback loop. On the schematic side, there isn't really much of a feedback loop; nothing will tell you that you've e.g. flipped the + and - terminals of your Opamp.

On the layout side, you've got the ratsnest and DRC to tell you whether you're winning or not. That might be the key to making LLM-based routing work. Opus refused to hand-route my whole board yesterday but is currently using the KCRT tools to do the routing and things seem to be progressing well.

This LED star PCB was 95% generated by Codex: https://www.youtube.com/shorts/8a52LjovhcE

Was non-trivial (e.g. days and days of cumulative work) but worked with Codex to build up a parametric generator where I could adjust the star size, number of rings, leds per ring. It did all the LED-to-LED routing, panel layout with mouse bites, placed decoupling caps. At the time Codex wasn't as good at spatial reasoning, I expect that Astra would do this much faster.

4 x layer PCB with GND and 5V inner layers. WS2816B LEDs (not available in strips yet). 3D printed a frame so that two stars could be opposite each other (video shows only one side). ESP32 S3 on a 3.3v to 5v shifter board sandwiched in between. ESP32 wifi antenna pokes through and sits on a keep out section. Received control signals from a central controller via ESP Now.

Not to diminish your work, but this looks fairly trivial

What exactly did the LLM do, write a generic generator for stars of different size and number of rays?

I've been working on several PCB projects, and agents are very helpful for automating many parts of the workflow. They're excellent for schematics. Complex routing, though, is still a human's job for now; I've watched Freerouting fall on its face many times. If you're doing six-layer high-speed DDR routing, AI won't solve that for you today.

However checkout EDA tools https://github.com/l3wi/claude-eda/ https://github.com/drandyhaas/KiCadRoutingTools

That layout does not look very good:

https://github.com/drandyhaas/KiCadRoutingTools/blob/main/do...

I'm curious if this even works at high speed though I'm seeing what appears to be length-matched traces. Is the tool using an EM simulator in the process?

I've installed it this morning to play around with on some low-speed designs before trying a high-speed design. Looking at that specific screenshot you posted there... that looks partially like a floor planning problem to me. Looking up the part number, that Ti90G529 is an FPGA, which also suggests that the overall routing could potentially get a lot better if the pads from the part on the left-hand side were shifted to all be on the "top" or "bottom" of U3 instead of divided across it the way it is right now.

My first attempt on a low-speed not-dense board came out OK. There were a few odd choices, but I don't expect perfection from auto-routers. If nothing else, auto-routers are a good way to double-check that your floor planning is OK, even if you then rip up the auto-routed traces and hand route them instead.

I built a project nearly identical to this one so knowing the level of complexity required, I'm not surprised it worked. AI is indeed raising the floor. Even simple hobby designs were once out of reach, but now we can "YOLO it and build stuff fast without necessarily knowing about the details" as the author puts it.

That said, without experience it's easy to pierce the veil of "simple circuitry" by accident, just like in XKCD: Tasks[1].

Looking at preview of the author's next project at the end of the article, I'm not so sure the same strategy will work. The board is probably two orders of magnitude more complex. Without knowing the circuit details, I see many red flags (randomly placed ics and decoupling, likely wrong length matching, random thick traces indicating lack of foresight on power distribution, backwards connectors, the probably unnecessary use of BGA footprints, etc).

[1]: https://xkcd.com/1425/

This seems to fall into the same category I've seen with basically all agent driven software as well. That is to say, "Amazing that someone with no experience could do this, but not interesting at all in its own right". Call me when AI is laying out the next TSMC node.

In our company, we are doing high speed PCB designs with FPGAs, memories, ADCs, DACs etc. We are not yet using AI much in our PCB design workflow because our designs seem to be too complex for the AI solutions we have tried. Are there any areas where people are successfully incorporating AI to their PCB design workflow, even with complex, high speed designs? Schematic/layout review? Routing? Footprint creation?

Why wouldn't an LLM be able to do high speed designs? Are you inventing new types of design rules for every board? Or is it simply because the automatic layout tools are not up to the task yet?

It is just that the current tools out there seem to work for small or hobbyist boards currently. We couldn't apply them on our complex board designs. But maybe you had a different experience? I am curious on what kind of ways big companies are incorporating AI in their PCB design workflows currently.

The feedback loop is too long, it's not like a software development harness that can direct the model to write some tests for complex behavior, and iterate until they pass.

There a lots of things that can be subtly wrong, and it gets much worse as your signal frequency increases, or you have to deal with high power/radio/etc. The model (agent) has no way to validate its work.

I have been using Gemini, Claude, ChatGPT, Grok (whatever is available) to create esp32 boards. As I am very new into this field, I mostly use them to query about schematics, ICs, routing, kicad, electronic foundations and so on. They are great help and provide me invaluable advice. However It's always better to validate one's result with others. I have many cases where they would provide me catastrophic advice and a second opinion fixed it.

It's always fun to get apologies from LLMS. I love it.

I'll check the newer models as soon as possible to see how much improvement they provide.

> Upon Claude's compilation of the project, I asked it to prepare the required files for JLCPCB, and tell me what to select on their GUI

It would be an interesting step to get Claude (or other LLM) to do order the PCBs itself on the JLCPCB website.

We're nearly at the stage where you can describe what a device should do, let it design the circuit (using available components on JLCPCB), design a PCB and enclosure then order PCBs, assembly and 3d printed enclosure and get it sent to you for final assembly.

There's a plugin for Kicad https://github.com/bouni/kicad-jlcpcb-tools

It's pretty interesting to watch an LLM drive ngspice. ... clearly an area that could use more training, but good enough to make it less annoying for me to use.

Yeah I've built about a dozen boards using GPT-sol 5.6 and my favorite is my Pi CM5 carrier board, to replace a laptop board in an old Sony Vaio p laptop. https://x.com/kanwisher/status/2089629411364745351?s=20

Did it work ?

It's funny, I made a CM5 board for my N40L not too long ago https://www.youtube.com/watch?v=AzW4rRsD8Uk

Was sol5.6 good enough to do the actual HDMI / PCI-E and USB 3 Routing ?

I have used fable to aid me with PCB design. It is pretty good. But it can also sometimes make very human mistakes. It mixed up RX and TX on a uart line. If you don't catch stuff like that and get assembled boards this can obviously be pretty annoying. On the other hand I have also mixed up RX and TX before, lol.

I feel like just leaving PCB routing and schematics for it is just waste of tokens.

Once you have initial design (what chips to use, what each of them needs in terms of other components etc.) the schematic/PCB isn't the hard part but it is the hard part for the AI.

It's great at stuff that humans take a lot of time like say "get me buck converters in that range of voltage in power, and put price of chip and supporting components in the table", and at least in not heavily analog designs, finding chips that fit the purpose, are available and in price range is good part of the work

Yeah, we're still very far from a machine routing PCBs. Nice project, though, looks pretty fun to do it with an AI.

I researched a bit on how to manufacture PCBs at home, and i came across Voltera V one. The price is indeed way too high, but I am hoping somebody will make a foss version of it. There are already pretty interesting foss PnP machines.

For a 2-layer pcb I would either go chemical etching or a small routing cnc. Chemical etching kits , uv lamps and blank pcbs are not "too" expensive, but it's more of a professional setup than a hobbyist. Just think of all the PCBs yoi can send to manufacture (and with 4 layers and more) for the price of even getting half the stuff.

real PCBs are so much better than anything you can do at home, and so cheap, and so easy to order now, it's just not worth it

For a small lab where you have a moderate volume of oneoffs it's worth the investment. But, yeah, I wouldn't have that setup at home.

At current PCB prices that's kinda not worth it. Hell, even actual assembly isn't that expensive (at least if you have "a lot of few components" vs "big variety of components").

Machine routing is very old thing. Early Eagle did it fine. I worked 12 years ago on 4 layer pcb initially routed with Eagle. Layers with horizontal and vertical wires were unusual at the time, but the board worked fine. It’s the connector placement according enclosure design files, part management/availability/obsolescence and design for test what needs reliable automation. The tool may not hallucinate here.

Yes! I have made and ordered 3 PCBs with Astra and Autodesk Fusion since the Astra release. First one has arrived and worked great. I especially love how the model can wrangle all the JLC stuff. What a time we live in

Such a bummer that PCBAs are 2-3x more expensive than they were before 2025.

Seeing many people using AI to prototyping and ordering boards, I am curios if JLCPCB, PCBWAY and the other prototyping services has upticks in their orders. It would be great to see some numbers.

Would you be willing to share the full design files? Considering most of the PCB is well-trodden territory, it would be quite interesting to see the details what it actually came up with!

> ...I was not feeling much of an accomplishment, rightfully so. I used to enjoy the learning and the struggle that came with it.

I feel this as well.

I saw the board cost, but how about the total cost in tokens to design it? Can empathise with the good and meh feeling you got from it. For me I try to stick with manual struggles with new concepts which grows my brain and allows me learn something new. But its impressive what LLMs can do.

I am on Max 5x plan, so there were no additional costs. But the would-be API cost was around 450 usd.

Very cool! Can you reveal how much this custom board cost you?

> For five fully assembled boards I paid 130 Euros, ordered the E-ink displays from a local shop

I built a project board nearly identical to this one a few years ago, and this seems about right. I don't think the displays themselves are included in the 130 euros. They can vary a lot in price depending on spec and supplier.

Yes indeed. I paid 7.5 euros extra per e-ink display. So it was 33.5 euros per board.

I sent in a larger, slightly more complex board to JLCPCB over the weekend and it was $175 for 5 boards with components and assembly. Shipping, tariffs (ouch), and sales taxes added another ~$100 or so.

Can it shop autonomously on LCSC? Is it allowed to?

Props on the build - bespoke tooling like this per human is a really cool timeline to live in. Personal tech.

Related - Apparently this website is also "Brought to you by Fable"!

It's very interesting how this occurs with any "website builder" - Squarespace, Wordpress, Wix... and now Claude + GPT!

The elements look like every powerpoint I've seen in the last 6 months. Every report. Every internal document. It's all converged with similar typesetting, image / diagram placement...

To me, the verbiage is the big one, this time, where it takes all the personality out of a site and essentially devoids it of any meaning. I am NOT saying that this post is AI generated (it very likely isn't), but a site that has all of those qualities is useless to me and devoid of any meaning, repulsive actually.

> I was not feeling much of an accomplishment,

Why is this even required? I'll never understand this mindset. Because something came "easy", doesn't mean you haven't done anything meaningful to do it.

I'd say there is more people that you can count that wouldn't be able to do this task even if the AI was literally guiding them by hand.

> That said, I was not feeling much of an accomplishment, rightfully so. I used to enjoy the learning and the struggle that came with it.

> Yes it does suck that the joy we had while building has been sucked out of us

> For my hobby projects tho, I will continue to YOLO it and build stuff fast without necessarily knowing about the details.

I don't understand this conclusion. LLMs sucked the joy out of it, didn't feel rewarding, you're forced to use them at work, so you decide... just keep doing it at home, too? Why not actually learn to build a proper PCB knowing you can do much better than this horrible (despite being dead-simple) board that only got there with the help of your expert colleague's guidance anyways? Don't succumb to utter laziness and deny yourself the satisfaction of learning new skills, that's letting the thing rot your brain out worse than any TV ever did.

You are right. What I meant in my conclusion was more about : "I will use these tools to generate parts of a project I don't necessarily care about." I already started learning about proper PCB design, and I am actively fighting against choosing an LLM instead of grasping a concept fully. It's something I am struggling with, but all this is new for most of us. Hoping I will find a good balance at the end. Thanks for your remarks :)

Fair enough. I think there is great value to using LLMs to assist in learning new hobbies, helping lessen the friction, and doing research. I just think it's sad if you let them replace your thinking completely instead of augmenting it. Cheers for the human-written blog post, I did enjoy reading it.

Thank you :) That means a lot to me.

Your post and the link to KiCadRoutingTools is going to result in me finishing a project I started 6 months ago and have just let sit and linger because, like you point out, it was only the boring parts left. Fable found a bit of a showstopper in my design yesterday (an LDO that was right near its limits) and suggested a replacement, Opus filled in all of the missing pull-up/pull-down resistor values, double-checked all of the decoupling caps, and then did floor planning on the PCB side. I just installed KiCadRoutingTools and am getting close to happy with the state of the board and will likely be ordering them tomorrow!

Great to hear :) I hope your boards will turn out perfectly fine.

As a quick WIP update:

- The first board, which I had already done manual schematic capture, floor planning, and some routing on (but then I lost steam and it’s been sitting at 90% for 6 months) was finished quite readily by Opus + KiCadRoutingTools.

- A second significantly more complex board that has been sitting at the “I’ve done a bunch of planning in Obsidian but haven’t started schematic capture yet” stage… Fable took my Markdown notes, asked questions to fill in the blanks, and put together a plan. Opus first put together a very ugly schematic (essentially all of the parts but no wires between them, just net connections) which then got refined into a nicer-ish schematic. Floor planning went smoothly, the first cut was decent and with a little bit of manual refinement it got somewhere pretty good. Currently routing and still debating a bit between 4-layer and 6-layer. The BGA escapes seem to be causing the majority of the problems right now; originally Opus decided that 4-layer wasn’t feasible due to not being able to even route all the nets, switched to 6-layer, did better but still ended up with like 70 unroutable nets. A bit of back and forth led to revising the BGA fan-out and now we’re back at looking at whether a 4-layer board might be feasible.

For the second one, I’m not 100% sure whether wall-clock-time this is a faster process than it would’ve been to do manually, but… the initial 4-layer attempts were all done while I was out for a date with my wife, the remaining 4-layer attempts ran overnight, the first 6-layer routing attempt was done while I was having my coffee this morning, and now the 4-layer/6-layer fanout changes are being done while I run errands. Something I find especially interesting is that by leaning on KiCadRoutingTools, it looks like there’s actually very little token usage at the routing stage; the plan gets put together as Python + KiCadRoutingTools instructions and then the hard work is done by that tooling. LLM picks up the results, looks at it, tweaks, kicks off a new job. That’s a pretty interesting result; this has all been running on my laptop pretty much continuously for 15 hours and I’m nowhere near any of my usage limits.

> I think there is great value to using LLMs to assist in learning new hobbies, helping lessen the friction, and doing research

Claude (web) saved me a ton of money with a new hobby. I was curious about astrophotography and had a budget to fill in any missing pieces from my existing photography kit. The conclusion was basically: "get a $20 intervalometer and a wall-wart battery[1]. The lenses you've got are fine, the tripod you've got is fine, and hey good news, Jupyter and Venus are near conjunction so if you can find somewhere dark where you can shoot to the west, you can get a pretty cool timelapse this weekend"

Later on also provided some rough guidelines for the partial lunar eclipse that resulted in some pretty amazing photos.

Since then I have been doing a bit of research on getting a real mount, so that initial budget will probably get used, but it'll be a) for kit that I genuinely don't have yet and b) spent after I've already confirmed that I thoroughly enjoy going out and photographing the stars for hours and then stitching all those photos into timelapses or other neat stacks.

[1] I'm not sure what the right name is for this. One end is battery-shaped but has a wire that plugs into a wall-wart instead of having to switch batteries. I had an existing 500-Wh 120V battery bank thing and it was more than enough to run the camera for 6 hours.

Now get it through compliance :)

[The] Title Butcher strikes again!

"PCB is brought to you by Fable 5" is pretty different from "This PCB is brought to you by Fable 5". Maybe you could do "PCB brought to you by Fable 5" if you are really against articles? Let's have a Fable 5 censorship agent or something...

It honestly just makes me think there’s little reason for me to be alive anymore.

I hope this is a joke and you really don't consider this as such.

It's in fact opening up too many opportunities to us humans. It's never been this easy to acquire information and accomplish things.

It’s not a joke. My goals in life were all based around developing mastery for a meaningful purpose, and now there’s no need. What keeps me going is that at least I have some consumerist goals like understanding consciousness and physics or mathematics.

Computers can code for you, but it's not a reason to forget about your mastery goals.

The printing has been around for ages now, still people master calligraphy.

Anybody who thinks that way is just in doing so, and I can think that way for 50% of the time, but it’s difficult to maintain that without extrinsic motivators. When the computer can make a more compelling experience of any kind for another person I can’t help but feel my pursuits are not worthwhile.

The machine designed the circuit board in two hours, which was impressive, and the human understood it in never, which is becoming traditional.

If it's functional: that's a breakthrough.

But: the PCB itself is not looking beautiful in terms of routing and a lot of schematic details yet. Horrible to to be more honest. But that's a minor issue.

I'm not overly shocked. 90% of creating PCBs is copying reference schematics from vendor datasheets and connecting them. That's LLM territory. This mostly failed for now as they just did pdf2text and killed all documents.

The last 10% are brutal (HF, EMC, high frequency multi-layer designs, etc.). But I managed LLMs to automatically create ngspice models using vision onto datasheets.. lol

Shameless plug for the slop coded CLI I use in my workflow: https://github.com/akiselev/datasheet-cli

It just sends the PDF to Gemini Flash and asks it to extract semi structured data (semi structured in the sense that it's not fully structured extraction, but its a JSON file to feed into the next step of the LLM design process).

Works pretty well in general, though I should update to the latest Gemini version.

That's pretty cool! How reliable has the footprint extraction been?

I tested it With Gemini 2.5 Flash. Works great.

Reply on news.ycombinator.com