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

Reports of code's death are greatly exaggerated

stevekrouse.com

Post reply on HN
Print view View original

91–100 of 486 posts

Re: Reports of code's death are greatly exaggerated

#91

Post by thesz »

lateforwork wrote: post #71

Chris Lattner, inventor of the Swift programming language recently took a look at a compiler entirely written by Claude AI. Lattner found nothing innovative in the code generated by AI [1]. And this is why humans will be needed to advance the state of the art. AI tends to accept conventional wisdom. Because of this, it struggles with genuine critical thinking and cannot independently advance the state of the art. AI…

  > ...generate answers near the center of existing thought.
This is right in the Wikipedia's article on universal approximation theorem [1].

[1] https://en.wikipedia.org/wiki/Universal_approximation_theore...

"n the field of machine learning, the universal approximation theorems (UATs) state that neural networks with a certain structure can, in principle, approximate any continuous function to any desired degree of accuracy. These theorems provide a mathematical justification for using neural networks, assuring researchers that a sufficiently large or deep network can model the complex, non-linear relationships often found in real-world data."

And then: "Notice also that the neural network is only required to approximate within a compact set K {\displaystyle K}. The proof does not describe how the function would be extrapolated outside of the region."

NNs, LLMs included, are interpolators, not extrapolators.

And the region NN approximates within can be quite complex and not easily defined as "X:R^N drawn from N(c,s)^N" as SolidGoldMagiKarp [2] clearly shows.

[2] https://github.com/NiluK/SolidGoldMagikarp

Re: Reports of code's death are greatly exaggerated

#92

Post by majormajor »

jedberg wrote: post #25
pacman128 wrote: post #16

In a chat bot coding world, how do we ever progress to new technologies? The AI has been trained on numerous people's previous work. If there is no prior art, for say a new language or framework, the AI models will struggle. How will the vast amounts of new training data they require ever be generated if there is not a critical mass of developers?

People are doing this now. It's basically what skills.sh and its ilk are for -- to teach AIs how to do new things. For example, my company makes a new framework, and we have a skill we can point an agent at. Using that skill, it can one-shot fairly complicated code using our framework. The skill itself is pretty much just the documentation and some code examples.

Isn't the "skill" just stuff that gets put into the context? Usually with a level of indirection like "look at this file in this situation"?

How long can you keep adding novel things into the start of every session's context and get good performance, before it loses track of which parts of that context are relevant to what tasks?

IMO for working on large codebases sticking to "what the out of the box training does" is going to scale better for larger amounts of business logic than creating ever-more not-in-model-training context that has to be bootstrapped on every task. Every "here's an example to think about" is taking away from space that could be used by "here is the specific code I want modified."

The sort of framework you mention in a different reply - "No, it was created by our team of engineers over the last three years based on years of previous PhD research." - is likely a bit special, if you gain a lot of expressibility for the up-front cost, but this is very much not the common situation for in-house framework development, and could likely get even more rare over time with current trends.

Re: Reports of code's death are greatly exaggerated

#93

Post by bitwize »

CamperBob2 wrote: post #38
pacman128 wrote: post #16

In a chat bot coding world, how do we ever progress to new technologies? The AI has been trained on numerous people's previous work. If there is no prior art, for say a new language or framework, the AI models will struggle. How will the vast amounts of new training data they require ever be generated if there is not a critical mass of developers?

In a chat bot coding world, how do we ever progress to new technologies? Funny, I'd say the same thing about traditional programming. Someone from K&R's group at Bell Labs, straight out of 1972, would have no problem recognizing my day-to-day workflow. I fire up a text editor, edit some C code, compile it, and run it. Lather, rinse, repeat, all by hand. That's not OK. That's not the way this industry was ever suppose…

We were almost there, back in the 80s.

A vice president at Symbolics, the Lisp machine company at their peak during the first AI hype cycle, once stated that it was the company's goal to put very large enterprise systems within the reach of small teams to develop, and anything smaller within the reach of a single person.

And had we learned the lessons of Lisp, we could have done it. But we live in the worst timeline where we offset the work saved with ever worse processes and abstractions. Hell, to your point, we've added static edit-compile-run cycles to dynamic, somewhat Lisp-like languages (JavaScript)! And today we cry out "Save us, O machines! Save us from the slop we produced that threatens to make software development a near-impossible, frustrating, expensive process!" And the machines answer our cry by generating more slop.

Re: Reports of code's death are greatly exaggerated

#94

Post by slopinthebag »

lateforwork wrote: post #71

Chris Lattner, inventor of the Swift programming language recently took a look at a compiler entirely written by Claude AI. Lattner found nothing innovative in the code generated by AI [1]. And this is why humans will be needed to advance the state of the art. AI tends to accept conventional wisdom. Because of this, it struggles with genuine critical thinking and cannot independently advance the state of the art. AI…

Yeah I think he had a pretty sane take in that article:

>CCC shows that AI systems can internalize the textbook knowledge of a field and apply it coherently at scale. AI can now reliably operate within established engineering practice. This is a genuine milestone that removes much of the drudgery of repetition and allows engineers to start closer to the state of the art.

And also

> The most effective engineers will not compete with AI at producing code, but will learn to collaborate with it, by using AI to explore ideas faster, iterate more broadly, and focus human effort on direction and design. Lower barriers to implementation do not reduce the importance of engineers; instead, they elevate the importance of vision, judgment, and taste. When creation becomes easier, deciding what is worth creating becomes the harder problem. AI accelerates execution, but meaning, direction, and responsibility remain fundamentally human.

Re: Reports of code's death are greatly exaggerated

#95

Post by jedberg »

majormajor wrote: post #92
jedberg wrote: post #25

Earlier quoted context omitted.

People are doing this now. It's basically what skills.sh and its ilk are for -- to teach AIs how to do new things. For example, my company makes a new framework, and we have a skill we can point an agent at. Using that skill, it can one-shot fairly complicated code using our framework. The skill itself is pretty much just the documentation and some code examples.

Isn't the "skill" just stuff that gets put into the context? Usually with a level of indirection like "look at this file in this situation"? How long can you keep adding novel things into the start of every session's context and get good performance, before it loses track of which parts of that context are relevant to what tasks? IMO for working on large codebases sticking to "what the out of the box training does" i…

> Isn't the "skill" just stuff that gets put into the context? Usually with a level of indirection like "look at this file in this situation"?

Today, yes. I assume in the future it will be integrated differently, maybe we'll have JIT fine-tuning. This is where the innovation for the foundation model providers will come in -- figuring out how to quickly add new knowledge to the model.

Or maybe we'll have lots of small fine tuned models. But the point is, we have ways today to "teach" models about new things. Those ways will get better. Just like we have ways to teach humans new things, and we get better at that too.

A human seeing a new programming language still has to apply previous knowledge of other programming languages to the problem before they can really understand it. We're making LLMs do the same thing.

Re: Reports of code's death are greatly exaggerated

#96

Post by thesz »

stravant wrote: post #82
adamiscool8 wrote: post #52

Earlier quoted context omitted.

After thousands of years of research we still don’t fully understand how humans do it, so what reason (besides a sort of naked techno-optimism) is there to believe we will ever be able to replicate the behavior in machines?

Thousands of years? We've only had the tech to be able to research this in some technical depth for a few decades (both scale of computation and genetics / imaging techniques).

And then we discover that DNA in (not only brain) cells are ideal quantum computers, DNA's reactions generate coherent light (as in lasers) used to communicate between cells and single dendrite of cerebral cortex' neuron can compute at the very least a XOR function which requires at least 9 coefficients and one hidden layer. Neurons have from one-two to dozens of thousands of dendrites.

Even skin cells exchange information in neuron-like manner, including using light, albeit thousands times slower.

This switches complexity of human brain to "86 billions quantum computers operating thousands of small neural networks, exchanging information by lasers-based optical channels."

Re: Reports of code's death are greatly exaggerated

#97

Post by Animats »

lateforwork wrote: post #71

Chris Lattner, inventor of the Swift programming language recently took a look at a compiler entirely written by Claude AI. Lattner found nothing innovative in the code generated by AI [1]. And this is why humans will be needed to advance the state of the art. AI tends to accept conventional wisdom. Because of this, it struggles with genuine critical thinking and cannot independently advance the state of the art. AI…

I think this article was on HN a few days ago.

Re: Reports of code's death are greatly exaggerated

#98

Post by bitwize »

cratermoon wrote: post #48

Yet again we can pull out Edsger W.Dijkstra's 1978 article, "On the foolishness of "natural language programming"" "In order to make machines significantly easier to use, it has been proposed (to try) to design machines that we could instruct in our native tongues. this would, admittedly, make the machines much more complicated, but, it was argued, by letting the machine carry a larger share of the burden, life would…

Dijkstra also mockingly described software engineering as "the doomed discipline" because its goal was to determine "how to program if you cannot".

"How to program if you cannot" has been solved now.

Re: Reports of code's death are greatly exaggerated

#99

Post by fritzo »

pacman128 wrote: post #16

In a chat bot coding world, how do we ever progress to new technologies? The AI has been trained on numerous people's previous work. If there is no prior art, for say a new language or framework, the AI models will struggle. How will the vast amounts of new training data they require ever be generated if there is not a critical mass of developers?

The same could be asked about people. The answer is social intelligence.

Re: Reports of code's death are greatly exaggerated

#100

Post by fritzo »

oblio wrote: post #63
picafrost wrote: post #61

So much of society's intellectual talent has been allocated toward software. Many of our smartest are working on ad-tech, surveillance, or squeezing as much attention out of our neighbors as possible. Maybe the current allocation of technical talent is a market failure and disruption to coding could be a forcing function for reallocation.

Those are business goals that don't just go away because tech changes.

Those business goals will soon realize they need more electricity. More brains will be devoted to power generation.
Post reply on HN