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

191–200 of 278 posts

Re: GPT is all you need for the back end

#191

Post by int_19h »

andai wrote: post #140
afpx wrote: post #110

Earlier quoted context omitted.

What if it can fix itself?

ChatGPT (and GPT-3) can criticize its own output, and then incorporate its own feedback into an improved version. This works for essays, for code... I'm waiting for a Copilot upgrade that puts red squigglies under "probably wrong" code, because GPT-3 can already detect and fix most of it.

ChatGPT can write prompts for itself, and it can do so recursively (i.e. you can direct it to write a prompt that causes the new instance to write a prompt ... etc). It can be fun trying to make the shortest prompt that survives the most iterations, and introducing additional requirements that every iteration must do makes it more challenging.

Re: GPT is all you need for the back end

#192

Post by auggierose »

logifail wrote: post #187
auggierose wrote: post #179

Earlier quoted context omitted.

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 mathema…

> Just make the AI also generate a proof that its code meets the spec. How would one tell if the AI-created "proof" is both accurate and adequate?

That is easy. The same way as interactive theorem proving works already today, and for the last 30 years or so. It is the very definition of a proof that you can check it.

Re: GPT is all you need for the back end

#193

Post by dntrkv »

naasking wrote: post #177
lm28469 wrote: post #34

Earlier quoted context omitted.

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.

That should be the default assumption, unless you can prove that our current approaches are on the right track... Which I don't think anyone actually believes.

Re: GPT is all you need for the back end

#194

Post by golemiprague »

logifail wrote: post #187
auggierose wrote: post #179

Earlier quoted context omitted.

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 mathema…

> Just make the AI also generate a proof that its code meets the spec. How would one tell if the AI-created "proof" is both accurate and adequate?

[dead]

Re: GPT is all you need for the back end

#195

Post by jensensbutton »

auggierose wrote: post #189
jensensbutton wrote: post #183

Earlier quoted context omitted.

Writing a spec thorough enough for AI to generate code that verifiably meets in and solves your problem means you're still programming, but specs instead of systems.

Sure, the human element will still be there. But note that the detail of your spec will converge to the natural "resolution" of your problem as the power of your AI increases.

But at what scope? The how will always matter. Your AI could design a system that bankrupts you on the first day. To prevent that you need to specify constraints and it's turtles all the way down. It would free you from spending time on areas you don't care about, but that's already true with SaaS.

Re: GPT is all you need for the back end

#196

Post by fragmede »

goatlover wrote: post #92
bufferoverflow wrote: post #68

Earlier quoted context omitted.

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.

So when will these self-driving cars be ready for mass consumption? Because they're starting to sound like flying cars at this point. Yes, technically doable and there are always some working prototypes, but no real market, and not seen as practical.

Soon? As a member of the general public I got opted into the Cruise beta. Took a ride from point A to point B. It had to be within a small service zone, and I have no idea how much mapping was needed to accomplish this, and thus have no idea how long it'll take for them to expand the service area, but it works! It cost $12 and I hailed it via the Cruise app. I dunno, I suppose GM could just fire the whole team and lose the code on a USB stick and just give up, but that hardly seems likely.

Re: GPT is all you need for the back end

#197

Post by naasking »

dntrkv wrote: post #193
naasking wrote: post #177

Earlier quoted context omitted.

> We're far away from AGI You literally have no way to make that determination.

That should be the default assumption, unless you can prove that our current approaches are on the right track... Which I don't think anyone actually believes.

> That should be the default assumption

Any strong declarative statements require justification, period, whether that is an assertion of existence or non-existence.

> unless you can prove that our current approaches are on the right track

How anyone can look at the progress in machine learning in audio, video and written expression, and not think "we're on the right track" is honestly beyond me. You can start here:

https://www.lesswrong.com/posts/K4urTDkBbtNuLivJx/why-i-thin...

Re: GPT is all you need for the back end

#198

Post by dragonwriter »

adamsmith143 wrote: post #130
lelanthran wrote: post #114

Earlier quoted context omitted.

> This is an incredibly bold prediction that isn't supported by the opinions of the majority of people in the field Well, DUH! "It is difficult to get a man to understand something when his salary depends upon his not understanding it." - Upton Sinclair. The people in the field who are making these promises may even believe it themselves, because their bread and butter comes from it.

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…

> If Astronomers were predicting a mass-extinction level asteroid impact for the year 2050 with 50% probability I doubt you would be so cavalier.

“Asteroid extinction” hasn't gone through several rounds of hype of imminence from people working in the field with a financial interest in that perception to extended “winters” as the basis of the last imminence cycle bursts in my lifetime, so... maybe the two things aren't analogous.

Re: GPT is all you need for the back end

#199

Post by naasking »

superfrank wrote: post #180
yellow_lead wrote: post #172

Earlier quoted context omitted.

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.

Sounds like a great way to setup a honeypot.
Post reply on HN