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

131–140 of 278 posts

Re: GPT is all you need for the back end

#131

Post by dsr_ »

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.

Helicopters -- hold on -- and light general aviation are our best extant examples of flying cars. Here's what we should learn from them:

- at current traffic levels, accidents are rare

- but fatality rates are high (20% of helicopter accidents)

- the commercial carriers have much better accident statistics than general aviation

- commuter and on-demand flights are much worse than commercial scheduled flights

- rather more than half of all accidents have a root incident near an airport - taxi-ing, departure, initial climb, approach, landing.

My conclusion is that mass adoption of flying cars (as in, millions of people piloting small aircraft with varying levels of maintenance, safety inspections, training, and traffic control) would be a terrifyingly foreseeable disaster.

On the other hand, I hold out real hope for fully autonomous vehicles being potentially safer than a distracted teenager on the road.

Re: GPT is all you need for the back end

#133

Post by eddsh1994 »

blowski wrote: post #56
abraxas wrote: post #6

Of course this will only work if your user's state can be captured within the 4096 tokens limit or whatever limit your llm imposes. More if you can accept forgetting least recent data. Might actually be OK for quite a few apps.

I tried getting it to generate a Red-Black tree in Java but it cuts off half way through. I suppose you could divide and conquer with smaller parts of the algorithm, but then we'd need a "meta AI" that can keep track of all those parts and integrate them into a whole. I'm sure it's possible, don't know if it's available as a solution yet.

Could langchain do that?

Re: GPT is all you need for the back end

#134

Post by eddsh1994 »

pak wrote: post #120
Scarblac wrote: post #77

Earlier quoted context omitted.

Amusingly, the more Web scale a technology is, like MongoDB or Redux, the more blog articles will have been written about it, making this technique work better. More hype directly translates into more robustness. So yes, I think ChatGPT is already very web scale.

webscalist was referencing a 12 year old joke: https://www.youtube.com/watch?v=b2F-DItXtZs

Oh my god, this came out shortly before my first job in tech and I haven't seen it since. This whole series is hilarious.

Re: GPT is all you need for the back end

#135

Post by xnorswap »

pbalau wrote: post #117
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…

Regardless of how successful an AI can get at figuring out what the human operator wants, in the end, all it will manage to do is figure out what the human wants or give similar options to what the human asked for. My experience in working with software and being a client for other craftsmen, is that rarely that's what needs done, do what the human wants. The whole idea of a good craftsman is to figure out what the c…

If ChatGPT replaces me, I suspect we'll be the ones turning actual client needs into GPT prompts, because as you say, what people ask for, what people want, and what people need are all different things and it's (currently) useful to have a human understand the difference, regardless of whether they're then interfacing with punch cards, an IDE or a chatGPT prompt.

Re: GPT is all you need for the back end

#136

Post by verdverm »

cmontella wrote: post #83
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.

See my comment about the moon ladder. Progress is nice, and I’m not saying there hasn’t been progress. But there is no indication that the methods of today that work to make taxi cabs in SF drivable will lead to a general-case self driving machine as promised for so many years. The fact that the two cases that work best have a similar climate to the 2007 DUC really highlights the reality that these methods haven’t be…

Google/Waymo demo'd the AI driving in a snow storm and the method they used to see through the flakes and maintain object detection. Having trouble finding the video I'm thinking of. Here are some videos related to self-driving in snow and progress on weird edge cases.

- https://www.youtube.com/watch?v=kx7fHEhnIZk (snow, like the google demo)

- https://www.youtube.com/watch?v=LSX3qdy0dFg | https://youtu.be/LSX3qdy0dFg?t=2229 (snow, but not the one I was thinking of)

Re: GPT is all you need for the back end

#137

Post by evrydayhustling »

jcadam wrote: post #121
cmontella wrote: post #64

Earlier quoted context omitted.

> a large system where the logic just makes itself up as it goes. What you describe is known as a “bureaucracy”, and indeed, it’s one of the seven levels of hell, and a primary weapon of vogons, next to poetry. That we aspire to put these in our computers, I agree, is unfathomable.

Are we the Vogons?

Always were.

Re: GPT is all you need for the back end

#140

Post by andai »

afpx wrote: post #110
bccdee wrote: post #57

This sounds like a nightmare lmao. Can you imagine trying to debug a system like this? Backend work is trawling through thousands of lines of carefully thought-out code trying to figure out where the bug is—I can't fathom trying to work on a large system where the logic just makes itself up as it goes.

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.

Post reply on HN