If you think the proprietary GPT-3 is the way to go, better have a look at Bloom (https://huggingface.co/bigscience/bloom) - an open source alternative trained on 366 billion tokens in 46 languages and 13 programming languages.
GPT is all you need for the back end
211–220 of 278 posts
Re: GPT is all you need for the back end
#212Earlier quoted context omitted.
You have an incredibly dim and pessimistic view of researchers and scientists. They could all easily double or triple their salaries by moving to standard industry but decide to work in Academia or Research Labs. These people on average predict AGI within ~30 years with more than 50% probability. Not sure how that prediction benefits their salary in any meaningful way. If Astronomers were predicting a mass-extinction…
> These people on average predict AGI within ~30 years with more than 50% probability. I haven't seen that prediction. What I have seen is "AGI is 2 years out", and I have been seeing that for 4 years. Much like the self-driving cars that were (according to the experts in the industry) 5 years out since 2012, and still not here in 2023. Maybe if the experts in the industry were more vocal about how far off they are,…
>I haven't seen that prediction.
Take your pick:
https://nickbostrom.com/papers/survey.pdf
https://aiimpacts.org/2022-expert-survey-on-progress-in-ai/
https://research.aimultiple.com/artificial-general-intellige...
https://forum.effectivealtruism.org/posts/7JxsXYDuqnKMqa6Eq/...
https://www.metaculus.com/questions/5121/date-of-artificial-...
https://www.lesswrong.com/posts/hQysqfSEzciRazx8k/forecastin...
>What I have seen is "AGI is 2 years out", and I have been seeing that for 4 years.
We obviously don't travel in the same circles because I don't know anyone credible saying that.
Re: GPT is all you need for the back end
#213(one of the creators here)
Can't believe I missed this thread.
We put a lot of satire in to this, but I do think it makes sense in a hand wavy extrapolate in to the future kind of way.
Consider how many apps are built in something like Airtable or Excel. These apps aren't complex and the overlap between them is huge.
On the explainability front, few people understand how their legacy million-line codebase works, or their 100-file excel pipelines. If it works it works.
UX seems to always win in the end. Burning compute for increased UX is a good tradeoff.
Even if this doesn't make sense for business apps, it's still the correct direction for rapid prototyping/iteration.
Re: GPT is all you need for the back end
#214Us: Tell me you never worked with an OLTP or OLAP system in production without telling me you never worked in OLAP or OLTP..."
ChatGPT: spits out this repo verbatim
Re: GPT is all you need for the back end
#215Ok but the server.py is still just reading and updating a json file (which it pretends to be a db) and all it is doing is call gpt with a prompt. The business logic of whatever the user wants is done inside GPT. Seriously how far do you think you can take this to consistently depend upon GPT to do the right business logic the same way every time?
Re: GPT is all you need for the back end
#216I have been thinking of something a bit more on the middle. Since there are already useful service APIs, I would first try the following: 1. Describe a set of “tasks” (which map to APIs) and have GPT choose the ones it thinks will solve the user request. 2. Describe to GPT the parameters of each of the selected tasks, and have it choose the values. 3. (Optional) allow GPT to transform the results (assuming all the AP…
https://langchain.readthedocs.io/en/latest/modules/agents.ht...
Thanks for the link! This looks super useful. Do you happen to know any real life service that is using these techniques?
Re: GPT is all you need for the back end
#217Ok but the server.py is still just reading and updating a json file (which it pretends to be a db) and all it is doing is call gpt with a prompt. The business logic of whatever the user wants is done inside GPT. Seriously how far do you think you can take this to consistently depend upon GPT to do the right business logic the same way every time?
Not very far. I think this is not really a "serious" project...
Re: GPT is all you need for the back end
#218One of the creators here (the one who tucks apples). We’re dead serious about this and intend to raise a preseed round from the top vc’s. Yes, it’s not a perfect technology, yes we made this for a hackathon. But we had that moment of magic, that moment where you go, “oh shit, this could be the next big thing”. Because I can think of nothing more transformative and impactful than working towards making backward engineers obsolete. We’re going full send. As one of my personal hero’s Holmes (of the Sherlock variety) once said, “The minute you have a back-up plan, you’ve admitted you’re not going to succeed”. We’re using this as our big product launch. A beta waitlist for the polished product will be out soon. What would you do with the 30 minutes you’d save if you made the backend of your react tutorial todo list app with GPT-3? That’s not a hypothetical question. I’d take a dump and go for a jog in that order.
Re: GPT is all you need for the back end
#219One of the creators here (the one who tucks apples). We’re dead serious about this and intend to raise a preseed round from the top vc’s. Yes, it’s not a perfect technology, yes we made this for a hackathon. But we had that moment of magic, that moment where you go, “oh shit, this could be the next big thing”. Because I can think of nothing more transformative and impactful than working towards making backward engine…
> backward engineers
Freudian slip?
Re: GPT is all you need for the back end
#220Art is where an approximation is fine and you can fill the holes with "subjectivity", but engineering is where missing a bolt on a bridge could collapse the whole thing. AI is adequate for art. It is NOT suitable for engineering. Not unless you build a ton of handrails or manually verify all the code and logic yourself.
It needs to be wrapped in processes of making product, not as a approximate product like they are currently do. Many good old AI algorithms are about heuristic e.g. Minimax in a 2 player board game. The approximation (heuristic) is wrapped with the rule of game, thus the product, the rules are rigid.