ChatGPT for Hardware Design
docs.flux.ai
ChatGPT for Hardware Design
1–10 of 165 posts
Re: ChatGPT for Hardware Design
#2Founder here:
Incredibly stoked to announce this today!
This is a dream a long time in the making. When we first thought of rebuilding the hardware design tooling stack from scratch, AI driven design seemed like the dream at the end of the tunnel...only 3+ years later we are here
Given the open ended nature of AI Expert agents we are launching a community preview. We are committed to keep building http://flux.ai in the open and are excited to discover this new realm with all of you.
Hit me with questions
Re: ChatGPT for Hardware Design
#3Founder here: Incredibly stoked to announce this today! This is a dream a long time in the making. When we first thought of rebuilding the hardware design tooling stack from scratch, AI driven design seemed like the dream at the end of the tunnel...only 3+ years later we are here Given the open ended nature of AI Expert agents we are launching a community preview. We are committed to keep building http://flux.ai in t…
GPT is really bad at math. Doesn't that mean it's also bad at doing the math for designing circuits?
Re: ChatGPT for Hardware Design
#4Engineer on the team here. Some of the interesting challenges of doing ChatGPT for circuit design were:
1) How to communicate the circuit connections to ChatGPT in the text prompt. We ended up just using the standard netlist format. Apparently it knows about netlists from its training data. It also knows about datasheets.
2) How to get the needed accuracy and precision for questions like "calculate the resistance needed between component A and B". For that, we adopted the popular langchain framework to integrate specific "tools" into the AI for specific recognizable problems.
Re: ChatGPT for Hardware Design
#5I recently used ChatGPT to find a part. Maybe this was an anomalous result, but it was wrong. Don't know if this will be an issue with your project.
Me: Is there a digital to analog converter with an 8V analog range and serial input?
CGPT: Yes, there are several digital-to-analog converters (DACs) available with an 8V analog range and serial input. One example is the AD5541A DAC from Analog Devices. It has a 16-bit resolution and can accept serial input in the form of SPI or QSPI signals. The output voltage range is programmable and can be set to 0 to 8V using an external reference voltage.
Another example is the MAX5389 DAC from Maxim Integrated. It has an 8-bit resolution and can accept serial input in the form of I2C signals. The output voltage range is also programmable and can be set to 0 to 8V using an external reference voltage.
These are just a couple of examples, but there are many other DACs available from different manufacturers that meet your specifications.
Me: Those parts are limited to 6v max
CGPT: I apologize for the mistake in my previous response. You are correct that the AD5541A and MAX5389 DACs have a maximum output voltage range of 5V, and they cannot meet your requirement of an 8V analog range.
However, there are other DACs that can meet your specifications. For example, the DAC5578 from Texas Instruments is a 16-bit DAC that can operate from a single 5V supply and has a programmable output range up to 10V. It also supports a serial interface with SPI or MICROWIRE protocols.
Another option is the MCP49xx series from Microchip, which includes several DACs with output voltage ranges up to 10V and a serial interface with SPI or QSPI protocols.
I hope this information is helpful, and please let me know if you have any further questions.
Re: ChatGPT for Hardware Design
#6Founder here: Incredibly stoked to announce this today! This is a dream a long time in the making. When we first thought of rebuilding the hardware design tooling stack from scratch, AI driven design seemed like the dream at the end of the tunnel...only 3+ years later we are here Given the open ended nature of AI Expert agents we are launching a community preview. We are committed to keep building http://flux.ai in t…
GPT is really bad at math. Doesn't that mean it's also bad at doing the math for designing circuits?
Here's another interesting idea: the marketing blurb mentions reducing costly errors—but with the amount ChatGPT hallucinates, how does this work? What steps have been taken to mitigate hallucination?
Re: ChatGPT for Hardware Design
#7Engineer on the team here. Some of the interesting challenges of doing ChatGPT for circuit design were: 1) How to communicate the circuit connections to ChatGPT in the text prompt. We ended up just using the standard netlist format. Apparently it knows about netlists from its training data. It also knows about datasheets. 2) How to get the needed accuracy and precision for questions like "calculate the resistance nee…
How do you deal with designs whose netlist or part list exceeds the context size limit?
Re: ChatGPT for Hardware Design
#8Founder here: Incredibly stoked to announce this today! This is a dream a long time in the making. When we first thought of rebuilding the hardware design tooling stack from scratch, AI driven design seemed like the dream at the end of the tunnel...only 3+ years later we are here Given the open ended nature of AI Expert agents we are launching a community preview. We are committed to keep building http://flux.ai in t…
GPT is really bad at math. Doesn't that mean it's also bad at doing the math for designing circuits?
I hope it would not lol
For starters: From our testing it’s really extremely good at providing the right formulas to solve the problem at hand.
But you are right, these models are inheritely non deterministic and therefore can struggle with things like math. The solution is to provide it access to tools such as a calculator which works really well.
Re: ChatGPT for Hardware Design
#9Founder here: Incredibly stoked to announce this today! This is a dream a long time in the making. When we first thought of rebuilding the hardware design tooling stack from scratch, AI driven design seemed like the dream at the end of the tunnel...only 3+ years later we are here Given the open ended nature of AI Expert agents we are launching a community preview. We are committed to keep building http://flux.ai in t…
GPT is really bad at math. Doesn't that mean it's also bad at doing the math for designing circuits?
Maybe not. It understands data sheets, and seems to be able to connect the dots based on probabilities around connecting components together. If you don't ask it to do large-scale design tasks, it's okay at narrowly scoped tasks like this.
If it's wrong, you can determine that during simulation. You could also assert that in the background, I suppose — prune the bunk suggestions by the language model before presenting them.
In my own experiments I find GPT can succeed in complex tasks if you prompt it multiple times at different steps of the task, and have some level of recursive validation and re-prompting to keep it in line. In a case like this I have a feeling it would do a great job, and would be especially useful for the discovery/exploration phase of a new project.
Re: ChatGPT for Hardware Design
#10Earlier quoted context omitted.
GPT is really bad at math. Doesn't that mean it's also bad at doing the math for designing circuits?
Here's another interesting idea: the marketing blurb mentions reducing costly errors—but with the amount ChatGPT hallucinates, how does this work? What steps have been taken to mitigate hallucination?
LLMs do indeed hallucinate.
What’s been working well for us is to give it access to factual data sources such as calculators, component data sheets, etc.
It does really well from our tests in the past few weeks, so well that we decided to invite everyone to explore the boundaries with a community preview
Just give it a shot and report back