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

LLMs as the new high level language

federicopereiro.com

Post reply on HN
Print view View original

311–320 of 396 posts

Re: LLMs as the new high level language

#311

Post by frigg »

randallsquared wrote: post #287
frigg wrote: post #271

>Following this hypothesis, what C did to assembler, what Java did to C, what Javascript/Python/Perl did to Java, now LLM agents are doing to all programming languages. What did Javascript/Python do to Java? They are not interchangeable nor comparable. I don't think Federico's opinion is worth reading further.

Three of Java's top application categories are webapps, banking/financial services, and big data. Node and Pyspark have displaced quite a lot of that.

Most serious banking apps and financial services are still written in Java, it hasn't displaced much of anything. Big data is a relatively 'new' fad that is already becoming less and less relevant.

Re: LLMs as the new high level language

#312

Post by manuelabeledo »

After re-reading the post once again, because I honestly thought I was missing something obvious that would make the whole thing make sense, I started to wonder if the author actually understands the scope of a computer language. When he says:

> LLMs are far more nondeterministic than previous higher level languages. They also can help you figure out things at the high level (descriptions) in a way that no previous layer could help you dealing with itself. […] What about quality and understandability? If instead of a big stack, we use a good substrate, the line count of the LLM output will be much less, and more understandable. If this is the case, we can vastly increase the quality and performance of the systems we build.

How does this even work? There is no universe I can imagine where a natural language can be universal, self descriptive, non ambiguous, and have a smaller footprint than any purpose specific language that came before it.

Re: LLMs as the new high level language

#313

Post by willj »

properbrew wrote: post #281
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…

> I want to see some assurance we get the same results every time Genuine question, but why not set the temperature to 0? I do this for non-code related inference when I want the same response to a prompt each time.

A temperature of 0 doesn’t result in the same responses every time, in part due to floating-point precision and in part to to lack of batch invariance [1]

[1] https://thinkingmachines.ai/blog/defeating-nondeterminism-in...

Re: LLMs as the new high level language

#314

Post by willj »

energy123 wrote: post #248
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…

Greedy decoding gives you that guarantee (determinism). But I think you'll find it to be unhelpful. The output will still be wrong the same % of the time (slightly more, in fact) in equally inexplicable ways. What you don't like is the black box unverifiable aspect, which is independent of determinism.

If you’re using a model from a provider (not one that you’re hosting locally), greedy decoding via temperature = 0 does not guarantee determinism. A temperature of 0 doesn’t result in the same responses every time, in part due to floating-point precision and in part to to lack of batch invariance [1]

[1] https://thinkingmachines.ai/blog/defeating-nondeterminism-in...

Re: LLMs as the new high level language

#316

Post by whoisthemachine »

BudapestMemora wrote: post #213
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…

"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?

Computer memory, even cheap consumer grade stuff, has much higher reliability than 90%. Otherwise your computer would be completely unusable!

Re: LLMs as the new high level language

#317

Post by afavour »

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…

> 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.

There’s a related issue that gives me deep concern: if LLMs are the new programming languages we don’t even own the compilers. They can be taken from us at any time.

New models come out constantly and over time companies will phase out older ones. These newer models will be better, sure, but their outputs will be different. And who knows what edge cases we’ll run into when being forced to upgrade models?

(and that’s putting aside what an enormous step back it would be to rent a compiler rather than own one for free)

Re: LLMs as the new high level language

#318

Post by rco8786 »

The thing that’s always missing from these critiques isnt about code quality or LoC or slop.

The issue is that if you fire off 10 agents to work autonomously for an extended period of time at least 9 of them will build the WRONG THING.

The problem is context management and decision making based on that context. LLMs will always make assumptions about what you want, and the more assumptions they make the higher the likelihood that one or more of them is wrong.

Re: LLMs as the new high level language

#319

Post by JackSlateur »

ChrisGreenHeur wrote: post #89
ekropotin wrote: post #87

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

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

Reproductible builds are a thing (that are used in many many places)

Re: LLMs as the new high level language

#320

Post by whoisthemachine »

pjmlp wrote: post #236
rezonant wrote: post #121

Earlier quoted context omitted.

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.

Do these compilers sometimes give correct instructions and sometimes incorrect instructions for the same higher level code, and it's considered an intrinsic part of the compiler that you just have to deal with? Because otherwise this argument is bunk.
Post reply on HN