Live data from Hacker News

AI-enhanced development makes me more ambitious with my projects

simonwillison.net

391–400 of 519 posts

Re: AI-enhanced development makes me more ambitious with my projects

#391
post #375

Earlier quoted context omitted.

People are already cut and pasting solutions off random webpages and stackoverflow. That they would grab stuff right out of chatgpt does not surprise me in the least. I would ask back 'why would this be any different this time?'

> random webpages and stackoverflow. Crucially, those have context around them. And as you navigate them more and more you develop an intuitive sense for what is trustworthy or not. Perhaps you even find a particularly good blog which you reference first every time you want to learn something from a particular language. Or in the case of Stack Overflow, your trust in an answer is enhanced by the discussion around it:…

>Crucially, those have context around them

Often incorrect context, incredibly biased context (no you don't know what you want, here's a complete misdirection), or just plain outdated. So basically the same thing as ChatGPT.

People who blindly copy and paste and ship are always going to do that. Everyone else isn't. It's really that simple.

Re: AI-enhanced development makes me more ambitious with my projects

#392

Earlier quoted context omitted.

What holds me back the most from using these tools is the vagueness of the copyright situation. I wouldn't straight out want to use it at work. For hobby projects that I might want to use for something serious one day, I'm on the fence. Developers who use this for serious stuff, how goes your reasoning? Is it just a calculated risk? Reward is greater than the risk?

> Developers who use this for serious stuff, how goes your reasoning? Is it just a calculated risk? Reward is greater than the risk? It seems obvious that AI is the future, and that ChatGPT is the most advanced AI ever created. For me (in the medical industry), if something goes wrong and someone dies a horrible death, I can just say that I didn't write that code, ChatGPT did. Not my fault. Next time you are at the h…

I can assure you, as a former quality engineer at a medical device development facility, that there is absolutely, positively zero chance that anyone there will use any AI-powered coding tools to write code that goes onto any device that is ISO-13485, CE, or otherwise compliant to some existing medical device regulations (I speak in the USA and European markets; I cannot speak for other markets). There is literally a defined waterfall development cycle for FDA-regulated devices that requires software features to be very precisely specified, implemented, validated, tested, and manufactured. Anyone suggesting using AI at such a facility would be laughed out of the room, and perhaps even re-trained on the procedures. Anyone caught using such tools would probably be fired immediately and all their code patches would be put under intense scrutiny and possibly even rewritten; of course the device software they were working on would remain in development and not released until that was fixed.

Re: AI-enhanced development makes me more ambitious with my projects

#393

I checked out the archive and came across https://simon.datasette.cloud/data/chatgpt_public_messages?_... I’m wondering if the archive missed something or what this random statement from the system is about. It seems to be telling itself who it is and setting a restriction on what it knows. I know if it’s not trained on data past a certain point, it cant know it, but still i wonder if you could intercept that and cha…

That's called the system prompt - it's present at the start of every conversation, just to feed in some hints as to how the underlying model should behave.

If you play with the ChatGPT API in the OpenAI Playground developer tool you can set your own system prompt. I used it to create a sentient cheesecake that could answer questions about SQL using cheesecake-based examples yesterday.

Re: AI-enhanced development makes me more ambitious with my projects

#394
> Braess's paradox is the observation that adding one or more roads to a road network can slow down overall traffic flow through it.

https://en.wikipedia.org/wiki/Braess%27s_paradox

Please make sure you're measuring and optimizing the right thing, eh?

"Happy hacking!"

Re: AI-enhanced development makes me more ambitious with my projects

#395

What I really love is the unbounded optimism of the AI. How many colleagues could you ask "Can you write me a PoC for a horizontally scalable, probabilistic database in Rust, using Raft-based consensus?" that would then just think for a second and go "Certainly! Let's start by ...". These people exist, but they're one in a thousand (or million?). ChatGPT basically does that for almost every prompt you throw at it. So…

> What I really love is the unbounded optimism of the AI. How many colleagues could you ask "Can you write me a PoC for a horizontally scalable, probabilistic database in Rust, using Raft-based consensus?" that would then just think for a second and go "Certainly! Let's start by ..." I agree about the unbounded optimism. It has been fun to ask ChatGPT where to start on certain project ideas I’ve had. However, I’ve tr…

and or there's a library to do XYZ. and you just want to know how to use it. or what library is available to do xyz.

I also use it to tell what the weird error text means given this snippet of code.

Re: AI-enhanced development makes me more ambitious with my projects

#396
post #50

Earlier quoted context omitted.

How do you know it is even close to correct? When I’ve asked it for code, it has been subtly wrong, or worse, correct but missing important edge cases that it doesn’t even seem to be aware of.

Always mention your stack before writing stuff like this - people who write js/ts where every problem that could be done has been done will get very different mileage than, say, people who write C and assembly for some obscure architecture

Unfortunately, this is simply not the case, as much as I hate it. I've worked on several custom ISAs and processors (mostly at companies shipping custom AI accelerators), and after sufficient explanation of the ISA to chat gpt, it was able to write machine learning kernels that did indeed run on our architecture. It is an impressive piece of technology, as much as I hate to admit

Re: AI-enhanced development makes me more ambitious with my projects

#398

What I really love is the unbounded optimism of the AI. How many colleagues could you ask "Can you write me a PoC for a horizontally scalable, probabilistic database in Rust, using Raft-based consensus?" that would then just think for a second and go "Certainly! Let's start by ...". These people exist, but they're one in a thousand (or million?). ChatGPT basically does that for almost every prompt you throw at it. So…

Yes, I suspect the AI finds all answers just as easy/hard. Whereas for humans certain programming tasks are orders of magnitude harder than others.

Re: AI-enhanced development makes me more ambitious with my projects

#399
post #361

Earlier quoted context omitted.

It reminds me of the boundless optimism of Mr Meeseeks: https://youtu.be/qUYvIAP3qQk GPT-3/4 is like a Meeseeks box for computer and internet tasks. Keep your task simple, and it will quickly and happily solve it for you before ceasing to exist. (Well, that’s how I use it via the API, at least. ChatGPT will preserve the state, but of course the context window is still limited anyway.)

Remember, existence is pain to a Meeseeks. So treat your AI with care!

I should ask ChatGPT if it can take 2 strokes off my game.

Re: AI-enhanced development makes me more ambitious with my projects

#400

Earlier quoted context omitted.

Please don't do this here. The topic deserves serious discussion.

Humor is a very sophisticated form of communication. Think of how much was said in so few words, by just poking at shared common knowledge.

Tragedy is for those that feel and comedy is for those that think.
Post reply on HN