Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GPT is all you need for the back end

github.com

Post reply on HN
Print view View original

171–180 of 278 posts

Re: GPT is all you need for the back end

#171

Post by sublinear »

chime wrote: post #24
nwah1 wrote: post #5

Earlier quoted context omitted.

Would be ridiculously inefficient, while also being nondeterministic and opaque. Impossible to debug, verify, or test anything, and thus would be unwise to use for almost any kind of important task. But maybe for a very forgiving task you can reduce developer hours. As soon as you need to start doing any kind of custom training of the model, then you are reintroducing all developer costs and then some, while the othe…

> Would be ridiculously inefficient, while also being nondeterministic and opaque. Impossible to debug, verify, or test anything, and thus would be unwise to use for almost any kind of important task. Not to defend a joke app, but I have worked in “serious” production systems that for all intents and purposes were impossible to recreate bugs in to debug. They took data from so many outside sources that the “state” of…

Wow I did not consider last ditch effort error handling, but that makes a lot of sense. Thank you for giving me something to think about!

Re: GPT is all you need for the back end

#173

Post by rco8786 »

oceanplexian wrote: post #150
rco8786 wrote: post #106

And you will almost immediately run into the fundamental problem with current iterations of GPT - You can not trust it to be correct or actually do the thing you want, only something that resembles the thing you want. The description in this link puts some really high hopes on the ability of AI to simply "figure out" what you want with little input. In reality, it will give you something that sorta kinda looks like w…

I keep hearing this assertion, that GPT can be wrong, therefore it’s an unworkable technology. But it’s a bad comparison. LLMs aren’t trying to be computationally correct like a calculator or something, the value is in their ability to semantically process a question. The other issue is assuming that the existing way of doing things is always correct. Engineers frequently get things wrong. If an AI model can complete…

> I keep hearing this assertion, that GPT can be wrong, therefore it’s an unworkable technology.

This is a straw man, I did not say any such thing. I am just pointing out the limitations that people like the author of this article seem to be blissfully unaware of.

Also I would argue that your premise of AI vs a Jr eng is pretty bad. Junior engineers are not writing things to 85% correctness. If they are, they should be let go basically immediately. That's a 15% error rate. I would posit that even the worst human programmers have error rates well below 1% for code that actually ships.

Re: GPT is all you need for the back end

#174

Post by bestcoder69 »

barefeg wrote: post #143

I 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...

Re: GPT is all you need for the back end

#175

Post by naasking »

rco8786 wrote: post #106

And you will almost immediately run into the fundamental problem with current iterations of GPT - You can not trust it to be correct or actually do the thing you want, only something that resembles the thing you want. The description in this link puts some really high hopes on the ability of AI to simply "figure out" what you want with little input. In reality, it will give you something that sorta kinda looks like w…

> You can not trust it to be correct or actually do the thing you want, only something that resembles the thing you want.

So, just like people then?

Re: GPT is all you need for the back end

#176

Post by klntsky »

Yep, but there's no need in the client-server architecture anymore then. We've built the current stack based on assumptions about the place computers occupy in our lives. With machine learning models, it could be completely different. If we can train them to behave autonomously, we can make them closer to general-purpose assistants in how we interact with them, rather than adhere to the legacy of DB+backend+interface architecture.

Re: GPT is all you need for the back end

#177

Post by naasking »

lm28469 wrote: post #34
mmcgaha wrote: post #27

Even if this is not 100% serious, it is really starting to feel like the ship computer from star trek is not too far away.

The closer we seem to get the farther we actually are. We're far away from AGI, if we even can reach it with our current approaches, but the latest iterations of "AI" are really good at making people believe it'll be there in 2 years

> We're far away from AGI

You literally have no way to make that determination.

Re: GPT is all you need for the back end

#178

Post by adamsmith143 »

marcosdumay wrote: post #145
adamsmith143 wrote: post #95

Earlier quoted context omitted.

>We're far away from AGI, if we even can reach it with our current approaches, but the latest iterations of "AI" are really good at making people believe it'll be there in 2 years This is an incredibly bold prediction that isn't supported by the opinions of the majority of people in the field and certainly doesn't have any real backing other than your gut.

Have you seen anybody that works on the field claim that AGI is around the corner? Even the idea that LLMs can eventually get there isn't taken seriously.

Plenty of folks in Alignment think things could be very soon indeed. Even the median for AI researchers' estimates is ~30 years.

Re: GPT is all you need for the back end

#179

Post by auggierose »

personjerry wrote: post #161

Art 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.

I am sorry to tell you, but AI is exceptional for engineering. Just make the AI also generate a proof that its code meets the spec. That's what human engineers should already do, but it was costly, because the tools were not good enough and the engineers not educated enough. AI is going to cut right through that Gordian knot.

This should not be surprising: There is a large intersection between engineering and mathematics. And mathematics is art.

Re: GPT is all you need for the back end

#180

Post by superfrank »

yellow_lead wrote: post #172
low_tech_punk wrote: post #138

There seems to be an API key/secret in the source code: https://github.com/TheAppleTucker/backend-GPT/blob/main/back...

If GPT had written this it wouldn't have made such a mistake.

Yeah. GPT would have left an API key in the code that looks correct, but doesn't actually work.
Post reply on HN