Not sure how “cutting edge” meta genomics still is, although it’s still not widespread. I worked on a project to provide free metagenomic analysis that was launched in 2017 and still going: https://czid.org/
I always keep metagenomics in mind now for friends and family who have mystery ailments.
I used EdgeDB 5.0 for a side project, and I loved it. It reminded me of the fun of developing an app with Django or Rails, but serverless with Typescript+React.
Engineer 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.
Out of curiosity, I noticed in the video that it recommended for a voltage regulator either an LM7805 or an LM1117 - either a super inefficient 5V regulator that has no business in new designs, or a 1.2V low-dropout 800mA regulator that is probably not appropriate to the other components it recommended (i.e. an LM7805 -> LM1117 would be 36% efficient at best).
It then also recommends a LiPo battery with a nominal 3.7V which obviously wouldn't be compatible with its LM7805 recommendation.
It also recommends an ESP8266 which is a 3.3V part so neither of the recommended regulators, nor the battery alone, would be appropriate.
Also, it recommends a 168MHz STM ARM micro - but it already has an ESP8266 with GPIO.
I'm not sure what it's suggesting I build but it doesn't really sound like a working environmental radiation logger ;)
In this case it seems to be giving examples of common ICs that are voltage regulators - these answers to high level questions are pretty vague by default.
We've had good results by asking follow up questions like "what power supply IC could I use to power a 3.3v microcontroller from a 3.7V nominal LiPo battery over the whole battery voltage range?".
I asked that question and I got: LM3940 and AMS1117-3.3 (LDO, high drop out but probably ok for low current - one isn't in stock but it doesn't have stock info yet), and TPS62203 and ADP2108 (bucks, both seem appropriate). These answers should get better as Copilot gets access to more and more tools.
btw I hope my comment didn't come across as too negative, like many folks I'm still trying to frame my own thinking around this kind of tooling. Thanks for the follow-up.
Not at all. I thought it was salient and very much what I wanted to know about. It seems there will be a heck of a lot of comments saying 'this is so awesome!' and this isn't a field where I'm able to look at the answer and immediately see the list of howling errors and hallucinations, so I'm very glad somebody can.
It's all very well expecting the hallucinations, but specificity beats Ludditeism every day. My gut reaction was 'ho boy, I'd better not trust this' but I didn't have the ___domain knowledge to understand why the GPT advice was dangerous. You did.
I look forward to following your work. I don't know what the ideal integration of generative AI and hardware design is, but I do feel like there are opportunities. Excited to see what y'all cook up.
I find comments similar to yours about ChatGPT all over the internet. I finally took the time to ask that some questions over the last few days. All the answers it gave were mundane and expected from any click bait web site you can find. I Googled the same questions and found similar answers.
Some personal questions it refused to answer or give suggestions because "only you can decide" was the response.
I'm very suspicious of all this. I'm thinking the only real benefit--some may say--is the chat aspect. You can carry on a conversation rather than having to determine a proper Google search over and over again.
> Which makes me think there is some hype involved.
There's _a lot_ of hype.
It's a good tool if you forget about any "intelligence" and just think of it as a tool. We don't expect search engines to be 'intelligent', we expect them to return results we are interested in, in an efficient manner.
In the case of this and similar tools, it is a text generator. It will generate _something_ based on your input. In many cases, it will make up stuff because it has to generate something. Note how it will not ask follow-up questions to 'understand' you (because it doesn't understand anything). You have to apply judgment and ask the follow up questions yourself.
One thing I found these tools to be useful is to mitigate the "blinking cursor on an empty document" paralysis. I just asked the "Pulumi AI" to generate some code that, while not really correct to my needs, is a good starting point for modification.
If you ask it to generate something from you, other than just a pre-made response that you could google, then it's more useful.
Copilot specifically asked me to provide the capacitance value for the capacitor closest to the comment pin in response to my question about optimal resistance for a resistor. Once I provided the value (by setting it in the tool, not by typing it in the chat) and asked it to try again it thanked me for the new info and gave back a good resistance value and how it arrived at it.
You’re probably not using GPT-4, the internet is being flooded with takes about GPT-3.5’s quality like this simply because the author doesn’t know there is a meaningful difference with the new model.
GPT-4 still confidently makes up sources for wrong answers and throws subtle mistakes (the obvious mistakes aren't as big a nuisance) into output.
This isn't to say gpt-4 isn't cool or impressive or a development to watch and learn about and be excited about, but I frequently see criticism dismissed as "you must be using 3.5" while I find 4 still costs more time than it would have potentially saved.
When I go here: https://openai.com/product/gpt-4 it says "try on chatgpt plus" and sends me to the same page I log in with and that's where I've been testing it.
I mean the more fundamental problem with the power supply is it recommending a "USB-to-Serial converter for powering the device." (See second example image.)
I'm overall bullish on AI systems but I'm not sure this space has enough detailed context to train. Much if this knowledgeis in-house/proprietary. We'll see how fast these are able to improve over time.
Does your module maybe have a built-in VRM? The datasheet said the operating voltage range was 2.5-3.6V. A LiPo battery has a nominal voltage of 3.7V and a fully-charged voltage closer to 4.2V. That's definitely out of spec without a VRM.
I absolutely believe it works for you, but I wouldn't ship that to customers, and I wouldn't expect what is ostensibly an authoritative reference tool to recommend it at all.
For many applications such as talking to pdfs you can use a vectors db like pinecone
But that doesn’t work well for schematics because for of the interesting use cases you need access to the whole thing.
Here is what’s been working for us
1. Extreme compression and summarization of the data we dynamically put in the context
2. Leverage the extreme amount of world knowledge the cutting edge models have
I'm curious if you fine-tuned a GPT model with specific hardware-related examples. Based on the OpenAI docs it seems like a pain to get enough good prompt:response pairs for fine-tuning (A few hundred minimum).
I worked on meta.org for a year starting in 2017 soon after it was acquired by CZI. There was no sign that I saw that the ___domain was ever destined for Facebook.
Uninteresting as it may be, I take the reason for the shut down at face value. From what I saw, meta.org never did as well as was expected, and other competitive services were doing better, notably Semantic Scholar.
To be sure, the exact timing probably had something to do with FB’s announcement, and the shared ownership of the two organizations probably helped the ___domain sale go smoothly.
Hi Greg,
We have two mechanisms for the state we use. The first one is web sockets for our multiplayer features like keeping our real-time cursors for multiplayer smooth.
For the document state (the circuit document) we are using Google's Firestore to keep the state synced across users. One of the problems we encountered is that documents can become quite large and always sending the whole latest states can even cause state issues by overwriting other changes if they are made at the wrong time. So we added some custom logic to always keep a full document ready for users who do the first load to be quick, and once you loaded the document you directly get the updates in granular changes synced as patch set itself. This allows users to locally jump back and forth in the time since each patch is essentially like an atomic change committed by the user and tracked in the version history.
There is one new statement specifically referring to start-ups:
"Second, pursuant to the "significant public benefit" parole authority under section
6
212(d)(5) ofthe INA, USCIS should propose a program that will permit DHS to grant
parole status, on a case-by-case basis, to inventors, researchers, and founders ofstart-up enterprises who may not yet qualify for a national interest waiver, but who have been awarded substantial U.S. investor financing or otherwise hold the promise of innovation and job creation through the development of new technologies or the pursuit of cutting- edge research. Parole in this type of circumstance would allow theseindividuals to temporarily pursue research and development ofpromising new ideas and businesses in the United States, rather than abroad. This regulation will include income and resource thresholds to ensure that individuals eligible for parole under this program will not be eligible for federal public benefits or premium tax credits under the Health Insurance Marketplace of the Affordable Care Act."
I always keep metagenomics in mind now for friends and family who have mystery ailments.