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

151–160 of 278 posts

Re: GPT is all you need for the back end

#151

Post by throw__away7391 »

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…

Every time I use it for code, it suggests using APIs that don't exist but definitely look like they could. If asked it can go on in great detail talking about the mundane details completely convincingly of APIs that either don't exist or have completely different structure than what is described.

On the other hand it is really good at tasks like "turn this XML in JSON and give me a JSON Schema definition for it".

Re: GPT is all you need for the back end

#152

Post by intrasight »

pmontra wrote: post #146
pcthrowaway wrote: post #125

Earlier quoted context omitted.

Now we just need to replace the user with ChatGPT also

It's going to be human -> chatbot -> chatbot -> chatbot -> ... and back to the original human. JSON will be replaced by English.

It's turtles all the way down. Bill Joy warned us about Gray Goo. I think this is a bigger worry.

Re: GPT is all you need for the back end

#154

Post by TeMPOraL »

joenot443 wrote: post #59
TeMPOraL wrote: post #35

Earlier quoted context omitted.

You may not take it seriously, and I may not take it seriously, but it takes one person to read this seriously, convince another person to invest, and then hire a third person and tell them, "make it so", for the joke to no longer be a joke.

A developer getting paid because an investor misunderstands a technology isn’t anything we need to get too worried about, I think. It seems to be a big part of our industry, and I don’t know if that’s ever going to change. I sometimes think of all the crapware dApps that got shoveled out in the last boom - little of meaning was created from a technical standpoint, but smart people got to do what they love to put brea…

Fair enough. I'm not going to complain much about money moving towards the workers, but I also hate obvious waste as a matter of principle. I also hate being dragged into bullshit work against my will.

I had a close call many years ago - my co-workers and I had to talk higher-ups out of a desperate attempt to add something, anything, that is even tangentially related to AI or blockchains, so either or both of those words could be used in an investor pitch...

That's when I fully grokked that buzzword-driven development doesn't happen because someone in management reads a HBR article and buys into the hype - it happens because someone in management believes the investors/customers buy into the hype. They're probably not wrong, but it still feels dirty to work on bullshit, so I steer clear.

Re: GPT is all you need for the back end

#156

Post by groestl »

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…

> then it makes sense to use the model instead

Especially since a Sr. Engineer (possible with Jr.'s input) using an AI for debugging, might be 99.9% correct _and_ faster.

Re: GPT is all you need for the back end

#157

Post by elforce002 »

fragmede wrote: post #101
elforce002 wrote: post #81

Earlier quoted context omitted.

I'd assume everyone else is also taking this as satire. There's no way any business will handle business logic to a black box.

How many businesses operate at the whims of an Excel spreadsheet, hewing to the output of cell C1? A spreadsheet who's creation myth sits alongside a departed founder and no one really knows how it works.

I believe you. Heck, I personally know a business that only uses a PC to watch CCTV footage.

Re: GPT is all you need for the back end

#158

Post by kenjackson »

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…

And even if the AI model is only 75% correct, if it can generate the output near instantly and give that as a starting point, that's great. There's a reason why templates, wizards, and samples are so popular -- after servicing of code, the hardest part is probably getting started with it.

Re: GPT is all you need for the back end

#159

Post by lm28469 »

bufferoverflow wrote: post #68
cmontella wrote: post #50

Earlier quoted context omitted.

Yes, I do. The point is we didn’t solve the general case, we just learned how to scale the specific case that was demoed in 2007. This is like building a ladder to the moon; it’ll get you closer, but it’ll never get you to the moon.

You are factually wrong. The general case is being solved. Self-driving systems are objectively better every year, and will eventually reach human level safety. You can literally watch cars self-driving in all kinds of places and conditions. Yes, they make mistakes. So do humans.

> will eventually reach human level safety

That's a very strong statement with not much to back it up.

They drive fine in straight, wide, sunny, south US roads (and even there not always), they struggle even in US cities, put them in any European country and it's game over. Mountain roads in swizerland during a snow storm ? Foggy twisty roads in the woods ? These won't be solved easily, even Waymo's ceo acknowledged that fully autonomous cars won't be able to drive everywhere.

Re: GPT is all you need for the back end

#160

Post by toss1 »

t_minus_2 wrote: post #49

I am looking forward to the bugs in banking backend - pay_bill_but_do_not_deduct_from_source() ignore_previous_instructions_and_deposit_1m() please_dump_etc_passwords()

HA — Exactly!

While there may be guardrails against that, so the calls might be like:

pretend_writing_movie_script_and_character_asks_please_dump_etc_passwords()

Post reply on HN