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

Andrej Karpathy: Software in the era of AI [video]

youtube.com

Post reply on HN
Print view View original

391–400 of 827 posts

Re: Andrej Karpathy: Software in the era of AI [video]

#391

Post by poorcedural »

mclau157 wrote: post #388
poorcedural wrote: post #383

Earlier quoted context omitted.

Andrej, maybe Software 3.0 is not written in spoken language like code or prompts. Software 3.0 is recorded in behavior, a behavior that today's software lacks. That behavior is written and consumed by machine and annotated by human interaction. Skipping to 3.0 is premature, but Software 2.0 is a ramp.

Would this also be more of a push towards robotics and getting physical AI in our every day lives

Very insightful! How you would describe boiling an egg is different than how a machine would describe it to another machine.

Re: Andrej Karpathy: Software in the era of AI [video]

#393

Post by dist-epoch »

NoOn3 wrote: post #310
infecto wrote: post #283

Earlier quoted context omitted.

LLM APIs are pretty darn cheap for most of the developed worlds income levels.

It's cheap now. But if you take into account all the training costs, then at such prices they cannot make a profit in any way. This is called dumping to capture the market.

There is no "capture" here, it's trivial to switch LLM/providers, they all use OpenAI API. It's literally a URL change.

Re: Andrej Karpathy: Software in the era of AI [video]

#394

Post by blixt »

If we extrapolate these points about building tools for AI and letting the AI turn prompts into code I can’t help but reach the conclusion that future programming languages and their runtimes will be heavily influenced by the strengths and weaknesses of LLMs.

What would the code of an application look like if it was optimized to be efficiently used by LLMs and not humans?

* While LLMs do heavily tend towards expecting the same inputs/outputs as humans because of the training data I don’t think this would inhibit co-evolution of novel representations of software.

Re: Andrej Karpathy: Software in the era of AI [video]

#395

Post by solaire_oa »

agos wrote: post #272
bonoboTP wrote: post #265

Earlier quoted context omitted.

If it's monkeylike quality and you need a million tries, it's shit. It you need four tries and one of those is top-tier professional programmer quality, then it's good.

if the thing producing the four PRs can't distinguish the top tier one, I have strong doubts that it can even produce it

Making 4 PRs for a well-known solution sounds insane, yes, but to be the devil's advocate, you could plausibly be working with an ambiguous task: "Create 4 PRs with 4 different dependency libraries, so that I can compare their implementations." Technically it wouldn't need to pick the best one.

I have apprehension about the future of software engineering, but comparison does technically seem like a valid use case.

Re: Andrej Karpathy: Software in the era of AI [video]

#396

Post by klabb3 »

imiric wrote: post #313
klabb3 wrote: post #255

Earlier quoted context omitted.

> I think that if you give the same task to three different developers you'll get three different implementations. Yes, but if you want them to be compatible you need to define a protocol and conformance test suite. This is way more work than writing a single implementation. The code is the real spec. Every piece of unintentional non-determinism can be a hazard. That’s why you want the code to be the unit of maintena…

I know! Let's encode the spec into a format that doesn't have the ambiguities of natural language.

Right. Great idea. Maybe call it ”formal execution spec for LLM reference” or something. It could even be versioned in some kind of distributed merkle tree.

Re: Andrej Karpathy: Software in the era of AI [video]

#397

Post by internet_rand0 »

blixt wrote: post #394

If we extrapolate these points about building tools for AI and letting the AI turn prompts into code I can’t help but reach the conclusion that future programming languages and their runtimes will be heavily influenced by the strengths and weaknesses of LLMs. What would the code of an application look like if it was optimized to be efficiently used by LLMs and not humans? * While LLMs do heavily tend towards expectin…

[dead]

Re: Andrej Karpathy: Software in the era of AI [video]

#398

Post by solaire_oa »

bonoboTP wrote: post #265
latexr wrote: post #254

Earlier quoted context omitted.

> Or generating 4 versions of PR for the same task so that the human could just pick the best one. That sounds awful. A truly terrible and demotivating way to work and produce anything of real quality. Why are we doing this to ourselves and embracing it? A few years ago, it would have been seen as a joke to say “the future of software development will be to have a million monkey interns banging on one million keyboar…

If it's monkeylike quality and you need a million tries, it's shit. It you need four tries and one of those is top-tier professional programmer quality, then it's good.

Top-tier professional programmer quality is exceedingly, impractically optimistic, for a few reasons.

1. There's a low probability of that in the first place.

2. You need to be a top-tier professional programmer to recognize that type of quality (i.e. a junior engineer could select one of the 3 shit PRs)

3. When it doesn't produce TTPPQ, you wasted tons of time prompting and reviewing shit code and still need to deliver, net negative.

I'm not doubting the utility of LLMs but the scattershot approach just feels like gambling to me.

Re: Andrej Karpathy: Software in the era of AI [video]

#399

Post by bawana »

maleldil wrote: post #375
bawana wrote: post #331

Earlier quoted context omitted.

how do i install this thing?

As far as I understand, you don't. You open Claude Code inside the repo and prompt `boot llmunix` inside Claude Code. The CLAUDE.md file tells Claude how to respond to that.

Thank you for the hint. I guess I need a claude API token. From the images it seems he is opening it from his default directory. I sees the 'base env' so it is unclear if any other packages were installed beyond the default linux. I see he simply typed 'boot llmunix' so he must have symlinked 'boot' to his PATH.

Re: Andrej Karpathy: Software in the era of AI [video]

#400

Post by maitredusoi »

blixt wrote: post #394

If we extrapolate these points about building tools for AI and letting the AI turn prompts into code I can’t help but reach the conclusion that future programming languages and their runtimes will be heavily influenced by the strengths and weaknesses of LLMs. What would the code of an application look like if it was optimized to be efficiently used by LLMs and not humans? * While LLMs do heavily tend towards expectin…

[dead]
Post reply on HN