Interesting. Not clear what it really does. The hardware is an oscilloscope probe on a 3-axis CNC mechanism. That's called a "flying probe", and you can buy one.[1]
Fine. But what does the AI do? It "ingests the project", but what does that mean?
Finding all the pins? That's a start. Using a SPICE model to figure out what should be on each pin, and checking? Now that would be impressive. Probably something in between.
The usual use for this sort of thing is that you probe a known-good board to find out what voltages and signals appear where, and then compare with newly manufactured boards. That's a common production check.
There's potential here. If the AI has some concept of what the board under test is doing, and can diagnose problems, that's quite useful.
I think the novel idea here is you jam some hardware together (whatever you like) that can do "physical real world" things with a well understood interface and then spin up Claude with access to it.
The way I'm thinking about it is, it's a _workflow_ innovation?
So you ask for data sheets for all the visible chips and get PDFs in an output directory with minimal user interaction except to flip the board, ask for a basic idea of connectivity, get a stitched high res surface image etc.... which of course are all currently possible, but you can do them potentially with very low effort. There doesn't have to be a _software stack_ ahead of time. You ask Claude to do the thing, it will figure out how to do it, write some code, pull in some OSS and make the thing happen. You can take this project's software or leave it.
You might say "tell me where you think the JTAG headers are" and it will come up with a workflow to do its best at that task (most likely with variable results...), but nonetheless this is not a thing you can ask of any commercial product I am aware of today. With probes, stuff can get interesting.
Of course experienced hardware & reverse engineers already can do all this stuff and have a plethora of workflows for it but I still think it's an interesting POC of a generalisable approach. You can take or leave this particular software stack. Also, the hardware barely matters, you can duct tape whatever to whatever.
Animats 21 hours ago [-]
It's lower level than that. "It will probe the approved targets and report back." It has enough smarts to find the pins, and maybe it can read the text labels on some ICs, but that's about it. That eliminates much drudgery, though. And probably the job of some tech who did that by hand.
stefan_ 15 hours ago [-]
But there is no good reason you can't do that already. Hardware engineers have just been fundamentally unserious about computer use going on 20 years. The PCB design you could do in 2000 already, but now it's still PDF datasheets, people drawing footprints and connecting RX lines to RX lines.
fragmede 10 hours ago [-]
I gotta give the hardware team credit for programmable pins on μc though. It means you just need to bring the pins out to pads and do whatever, instead of each pin has a fixed function so pin 14 MUST go to the next thing. (Within reason; vcc and gnd can't move).
_flux 19 hours ago [-]
What does it do with a single probe, though? You need two to actually probe anything, right?
So I'm wondering how is the second probe problem dealth with. I've considered something similar but with small weight attached to a pogo pin, so the CNC arm could then just move it around, which would not be very easy to get completely reliable as there may be components on the board.
s_m_t 19 hours ago [-]
Your common oscilloscope is common ground referenced. You attach to your test circuits ground with the typically black alligator clips coming off the probe and then read voltage at a point with the test lead. A decent differential probe like you might be thinking of usually costs about as much as a decent hobbyist oscilloscope.
_flux 17 hours ago [-]
Ah well that does simplify things significantly, I suppose it's probably still somewhat useful.
But I'd expect a big part of the nets are not connected to the ground? I mean in my hobby designs a majority of them is, but let's say if you generously use decoupling capacitors, then that might not be the case?
Majromax 8 hours ago [-]
Decoupling capacitors don't remove the ground reference, they just allow high-frequency signals a faster path to ground.
Typically, you need dedicated circuitry (and usually inductive coupling) to provide full isolation, but if the circuit is using this layout then you can still choose to ground the normally-isolated side for probing.
SAI_Peregrinus 7 hours ago [-]
"the ground" ≠ "ground". It's unfortunate naming IMO, but "ground" is just the 0V reference point. A normal oscilloscope's ground probes are mains Earth referenced, that is they're connected to the "ground" pin in the outlet which in turn connects to one or more conductive rods buried in the Earth. Decoupling capacitors don't negate the ground reference, since they're connected between a power rail & circuit ground. So the power rail's voltage is still referenced to ground.
A truly "floating" circuit would be something battery powered, or galvanically isolated from mains Earth (e.g. by an isolation transformer).
apimade 22 hours ago [-]
From my understanding is you’d probe the board during different operations, process the results and deduct what signals are useful and traffic transmitting across the board (I.E private keys, what protocols are used, debug interfaces, firmware components, chip functions, etc).
numpad0 21 hours ago [-]
feels like the author is hallucinating an instant solution to a problem with scope size of "research team and five years" class
contingencies 21 hours ago [-]
I believe the standard production check is more like you check continuity between known nets, given that you're the manufacturer, you already know where they are exposed, and therefore you can perform those checks before adding any components. Post component checks are a lot more complicated because active components and passive components will modify the visible voltages and characteristics, often to the point where you won't have the same degree of physical insight.
I would assume once machines are set up that this is only really done if you're not confident of your manufacturing line for some reason (eg. maintenance, reconfiguration) or you are pushing limits somewhere, for example, particularly small vias or traces very close to the edge of the board.
To make this useful, you would want two flying probes because otherwise it's not going to be telling you much you don't already know.
Animats 20 hours ago [-]
That's a blank board test. This is straightforward given the netlist and Gerber files.[1] It's just a continuity check between known points. Does not require AI.
Yes, manufacturing defined products, at least using known methods, does not require AI.
Although, that doesn't stop people raising while pretending it does!
uSoldering 1 days ago [-]
It’s hard to imagine anyone wanting this to be real more than I do, but this is nowhere close to being ready to do actual work. Photographing real PCBs is hard, there is no fiducial maths, no actual probing is being done. It's just photos of a photo being piped into an agent. If it actually did what it claims, no reasonable person would exclude it from the demo video.
Could an agent no develop a bespoke correction algorithm for the photos of the photo?
uSoldering 21 hours ago [-]
Why feed it photos of a photo when you could just feed it the photo that was printed out?
Havoc 1 days ago [-]
Can't say I fully understand it but this certainly smells like someone is getting hired off a single github repo as CV
Unsponsoredio 5 hours ago [-]
not a bad strategy. one repo that shows you can duct tape commodity hardware together and let an agent handle the workflow beats 50 leetcode solutions on your profile.
the interesting part is the cost ratio. commercial flying probe setups run 5 figures with proprietary software. this is a weekend build that gets you most of the way there for under 500 bucks.
ghurtado 1 days ago [-]
Nowadays the former seems to be a requirement for the latter, so I'm inclined to agree with you
DaiPlusPlus 1 days ago [-]
> someone is getting hired off a single github repo as CV
It's both cool and a bit confusing. Is this an attempt to commoditize flying-probe testing for PCBs? An attempt to use LLMs to reverse-engineer circuits? Both?
It almost feels like it would benefit from being split into two projects. If I'm testing my own PCBs, I probably don't want an agent in charge, at least not routinely. There's just no reason for the added cost, complexity, or non-determinism. And if I'm reversing someone else's design, then going through the effort of building an auto-prober seems like an overkill, especially since a single probe is seldom enough. Even the simplest serial interface will often have one line for clock and another for data, so you're gonna be manually making connections either way.
claytonia 21 hours ago [-]
Cool demo, but letting an AI Agent drive a physical probe may have problems. AI is probabilistic, but hardware is precise. If the model miscalculates a pin's position by even 0.1mm, the probe may crush the board. I am curious how the author actually bridges the gap between the Agent’s 'guess' and the sub-millimeter precision needed to avoid damaging hardware?
jstanley 17 hours ago [-]
A spring-loaded probe would seem sufficient.
15 hours ago [-]
par1970 21 hours ago [-]
I think this is roughly solved. Tell the agent to do all of its calculations in python.
delfinom 10 hours ago [-]
...OR if you are developing a PCB, you have the design data, and pick and place data and the gerber data.
Any combination of such gives you positions of everything within micrometers.
This is not a new problem. Testing of PCBs has been solved a billion times over and the world has had bed of nails tester and flying probe testers for 4 decades old.
We have a 8 finger flying probe machine at our facility that literally all we do is load the board in, load in the design data. It identifies points of interests, learns the fiducials and we let it do a characterization run. We then have engineering review of the resulting data and just let it fly afterwards.
None of this requires AI.
But nowadays any linear regression qualifies as AI so imma go slap a label on it.
lrvick 17 hours ago [-]
This looks super useful, but I wish authors could stop doing these silly "source available" plays.
Instead of donating to a project one has to buy GPU time to convert it to FOSS.
I figured this was some kind of home-grown prosthetic arm whose wearer could, using AI, draw any artwork online, speak ASL, perform minor surgery on themselves and so much more so long as their supply of tokens lasted.
Perhaps a smidge disappointed when I had a look and discovered it wasn't that :)
But I am not sure what do I see there? Is that some 3D printing?
sanieldoe 1 days ago [-]
This is amazing! Limitation breeds creativity indeed
nullc 1 days ago [-]
Maybe put the probe on a spring loaded linear sensor, and move down until it hits a target offset (could just be read by a simple flag in an optical sensor)-- resulting in hitting a constant target force.
1 days ago [-]
micromacrofoot 14 hours ago [-]
why not just take a photo with your phone and upload that to the llm
burgerone 17 hours ago [-]
Annoyingly misleading title unfortunately.
deanputney 1 days ago [-]
Wow that's nuts. What a great idea! I wonder how much of this the commercial flying probe machines can do already. Pretty cool to be able to have this on a home scale.
scaredpelican 1 days ago [-]
How does this only have a single star.
This is genuinely mind blowing.
rolph 1 days ago [-]
first release 18hrs ago...
Rendered at 01:14:34 GMT+0000 (UTC) with Wasmer Edge.
Fine. But what does the AI do? It "ingests the project", but what does that mean? Finding all the pins? That's a start. Using a SPICE model to figure out what should be on each pin, and checking? Now that would be impressive. Probably something in between.
The usual use for this sort of thing is that you probe a known-good board to find out what voltages and signals appear where, and then compare with newly manufactured boards. That's a common production check.
There's potential here. If the AI has some concept of what the board under test is doing, and can diagnose problems, that's quite useful.
[1] https://huntron.com/products/access2.htm
The way I'm thinking about it is, it's a _workflow_ innovation?
So you ask for data sheets for all the visible chips and get PDFs in an output directory with minimal user interaction except to flip the board, ask for a basic idea of connectivity, get a stitched high res surface image etc.... which of course are all currently possible, but you can do them potentially with very low effort. There doesn't have to be a _software stack_ ahead of time. You ask Claude to do the thing, it will figure out how to do it, write some code, pull in some OSS and make the thing happen. You can take this project's software or leave it.
You might say "tell me where you think the JTAG headers are" and it will come up with a workflow to do its best at that task (most likely with variable results...), but nonetheless this is not a thing you can ask of any commercial product I am aware of today. With probes, stuff can get interesting.
Of course experienced hardware & reverse engineers already can do all this stuff and have a plethora of workflows for it but I still think it's an interesting POC of a generalisable approach. You can take or leave this particular software stack. Also, the hardware barely matters, you can duct tape whatever to whatever.
So I'm wondering how is the second probe problem dealth with. I've considered something similar but with small weight attached to a pogo pin, so the CNC arm could then just move it around, which would not be very easy to get completely reliable as there may be components on the board.
But I'd expect a big part of the nets are not connected to the ground? I mean in my hobby designs a majority of them is, but let's say if you generously use decoupling capacitors, then that might not be the case?
Typically, you need dedicated circuitry (and usually inductive coupling) to provide full isolation, but if the circuit is using this layout then you can still choose to ground the normally-isolated side for probing.
A truly "floating" circuit would be something battery powered, or galvanically isolated from mains Earth (e.g. by an isolation transformer).
I would assume once machines are set up that this is only really done if you're not confident of your manufacturing line for some reason (eg. maintenance, reconfiguration) or you are pushing limits somewhere, for example, particularly small vias or traces very close to the edge of the board.
To make this useful, you would want two flying probes because otherwise it's not going to be telling you much you don't already know.
[1] https://bayareacircuits.com/bare-printed-circuit-board-elect...
Although, that doesn't stop people raising while pretending it does!
https://gainsec.com/2026/04/16/autoprober/
the interesting part is the cost ratio. commercial flying probe setups run 5 figures with proprietary software. this is a weekend build that gets you most of the way there for under 500 bucks.
Isn't that a good thing?
It almost feels like it would benefit from being split into two projects. If I'm testing my own PCBs, I probably don't want an agent in charge, at least not routinely. There's just no reason for the added cost, complexity, or non-determinism. And if I'm reversing someone else's design, then going through the effort of building an auto-prober seems like an overkill, especially since a single probe is seldom enough. Even the simplest serial interface will often have one line for clock and another for data, so you're gonna be manually making connections either way.
Any combination of such gives you positions of everything within micrometers.
This is not a new problem. Testing of PCBs has been solved a billion times over and the world has had bed of nails tester and flying probe testers for 4 decades old.
We have a 8 finger flying probe machine at our facility that literally all we do is load the board in, load in the design data. It identifies points of interests, learns the fiducials and we let it do a characterization run. We then have engineering review of the resulting data and just let it fly afterwards.
None of this requires AI.
But nowadays any linear regression qualifies as AI so imma go slap a label on it.
Instead of donating to a project one has to buy GPU time to convert it to FOSS.
> New York[1]
[1] https://www.governor.ny.gov/news/keeping-new-yorkers-safe-go...
> Cannot retrieve latest commit at this time.
Or is it GitHub Security, stopping us from cloning this dangerous repo?
What a glorious time to be alive.
Claude really is going to bring pleasure to the people.
https://www.youtube.com/watch?v=YgtO5sebA9U
Perhaps a smidge disappointed when I had a look and discovered it wasn't that :)
https://videos.files.wordpress.com/gD3kAWlO/autoprober-demo....
But I am not sure what do I see there? Is that some 3D printing?
This is genuinely mind blowing.