LLMs as the new high level language • Hacker News Board

Re: LLMs as the new high level language

#231

Post by red75prime » Sun, Feb 08, 2026, 10:46 AM UTC

fauigerzigerk wrote: post #212

red75prime wrote: post #195

Earlier quoted context omitted.

Randomness is not a problem by itself. Algorithms in BQP are probabilistic too. Different prompts might have different probabilities of successful generation, so refinement could be possible even for stochastic generation. And provably correct one-shot program synthesis based on an unrestricted natural language prompt is obviously an oxymoron. So, it's not like we are clearly missing the target here.

>Different prompts might have different probabilities of successful generation, so refinement could be possible even for stochastic generation. Yes, but that requires a formal specification of what counts as "success". In my view, LLM based programming has to become more structured. There has to be a clear distinction between the human written specification and the LLM generated code. If LLMs are a high level program…

I don't think framing LLMs as a "new programming language" is correct. I was addressing the point about randomness.

A natural-language specification is not source code. In most cases it's an underspecified draft that needs refinement.

Re: LLMs as the new high level language

#232

Post by pjmlp » Sun, Feb 08, 2026, 10:46 AM UTC

matheus-rr wrote: post #210

The intermediate product argument is the strongest point in this thread. When we went from assembly to C, the debugging experience changed fundamentally. When we went from C to Java, how we thought about memory changed. With LLMs, I'm still debugging the same TypeScript and Python I was before. The generation step changed. The maintenance step didn't. And most codebases spend 90% of their life in maintenance mode. Th…

We went from Assembly to Fortran, with several languages in between, until C came to be almost 15 years later.

Re: LLMs as the new high level language

#233

Post by bandrami » Sun, Feb 08, 2026, 10:47 AM UTC

fulafel wrote: post #220

bandrami wrote: post #203

Earlier quoted context omitted.

Huh? What's an example of a probabilistic programming language?

Race conditions, effects of memory safety and other integrity bugs, behaviours of distributed systems, etc.

Ah sorry I read your comment wrong. Yes I agree we can and do make probabilistic systems; we've just to date been using deterministic tools to do so.

Re: LLMs as the new high level language

#234

Post by pjmlp » Sun, Feb 08, 2026, 10:48 AM UTC

ekropotin wrote: post #87

IDK how everyone else feel about it, but a non-deterministic “compiler” is the last thing I need.

I use them everywhere since the late 1990's, it is called managed runtime.

Re: LLMs as the new high level language

#235

Post by zvitiate » Sun, Feb 08, 2026, 10:49 AM UTC

Lwerewolf wrote: post #217

BudapestMemora wrote: post #213

Earlier quoted context omitted.

"Until prompt-to-binary is reliable enough that nobody reads the intermediate code, the analogy doesn't hold." 1. OK, let's create 100 instances of prompt under the hood, 1-2 will hallucinate, 3-5 will produce something different from 90% of remaining, and it can compile based on 90% of answers 2. computer memory is also not 100% reliable , but we live with it somehow without man-in-the-middle manually check layer?

I wonder what ECC is for. So, unless you're Google and you're having to deal with "mercurial cores"... Also, sorry, but what did I just actually attempt to read?

Okay but if you aren’t using RAIM or a TMR system then is he really wrong?

And if you weren’t being snarky I’m sure you could understand. Generate 100 answers. Compare them. You’ll find ~90% the same. Choose that one.

Re: LLMs as the new high level language

#236

Post by pjmlp » Sun, Feb 08, 2026, 10:51 AM UTC

rezonant wrote: post #121

ChrisGreenHeur wrote: post #89

Earlier quoted context omitted.

I may have bad news for you on how compilers typically work.

You'll need to share with the class because compilers are pretty damn deterministic.

Not if they are dynamic compilers.

Two runs of the same programme can produce different machine code from the JIT compiler, unless everything in the universe that happened in first execution run, gets replicated during the second execution.

Re: LLMs as the new high level language

#237

Post by cess11 » Sun, Feb 08, 2026, 11:01 AM UTC

Was StackOverflow "the new high level language"? The proliferation of public git repos?

Because that's pretty much what "agentic" LLM coding systems are an automation of, skimming through forums or repos and cribbing the stuff that looks OK.

Re: LLMs as the new high level language

#238

Post by manuelabeledo » Sun, Feb 08, 2026, 11:04 AM UTC

pjmlp wrote: post #230

heikkilevanto wrote: post #226

If we consider the prompts and LLM inputs to be the new source code, I want to see some assurance we get the same results every time. A traditional compiler will produce a program that behaves the same way, given the same source and options. Some even go out of their way to guarantee they produce the same binary output, which is a good thing for security and package management. That is why we don't need to store the…

Anyone doing benchmarks with managed runtimes, or serverless, knows it isn't quite true. Which is exactly one of the AOT only, no GC, crowds use as example why theirs is better.

Even those are way more predictable than LLMs, given the same input. But more importantly, LLMs aren’t stateless across executions, which is a huge no-no.

Re: LLMs as the new high level language

#239

Post by direwolf20 » Sun, Feb 08, 2026, 11:05 AM UTC

herodoturtle wrote: post #221

elzbardico wrote: post #208

Earlier quoted context omitted.

Vibe coders are the new eternal september

I didn’t catch this reference, so adding the below for other folks in the same boat: https://en.wikipedia.org/wiki/Eternal_September “Eternal September or the September that never ended was a cultural phenomenon during a period beginning around late 1993 and early 1994, when Internet service providers began offering Usenet access to many new users. Before this, the only sudden changes in the volume of new users of Us…

More generally, it's whenever the expert to newbie ratio in a community crosses a certain threshold and never returns.

Re: LLMs as the new high level language

#240

Post by direwolf20 » Sun, Feb 08, 2026, 11:05 AM UTC

gilleain wrote: post #228

anoplus wrote: post #168

Earlier quoted context omitted.

I guess I'll have an agent for that one day. News agent.

You could even have your 'news agent' print your news every day on some cheap paper. Like a 'news periodical', shall we say.

I heard The Onion does that!