Hacker Newsnew | past | comments | ask | show | jobs | submit | cobbal's commentslogin

I am now imagining a future where developers buy fancy "grep cards" for their machines. I don't hate it.

These are properly called "GPUs", as in "Grep Processing Units"!

It would be cool if they could be daisy-chained, so you can have a hardware implementation of |

The return of the Transputer.

Put a Transputer in a Lego brick. Not "like a Lego brick", an actual Lego brick. Turn the notches into connectors for the serial link.

Plug'n'play.


The next logical step would be to have a separate card for each Unix utility.

And a patch panel and a bunch of patch cables that you plug in and out to construct your pipelines.

And eventually hire people whose job it is to patch pipelines on demand for everyone in the office.

“Hey Jim, I’m gonna output the systemd logs of nginx on line five, can you assemble a grep pipeline for me to match all HTTP 500 status codes from /api/cart POST request log lines? Connect the filtered output to Tim’s desk, line 7. He’s there now, we are trying to figure something out.”

“Sure thing Bob, give me a moment.”


It’s OK: you can just tell us you have a financially and relationally crippling Eurorack addiction. You’re amongst friends here.

I'm sure this is how some bellheads (in the phone tradition, not in the Unix tradition) envisioned computing.

Now if that isn’t a great Zachlike game mechanic. Playing as the patch pipeline builder.

Patching cables is so primitive... Use punched cards to define the connection patterns or something!

Somehow we’ve reinvented punch cards, but worse.

It was a companion of punchcards, the tabulating machine. Programming by wires. https://en.wikipedia.org/wiki/Tabulating_machine#Selected_mo...

Bring back IBM accounting machine plugboards!

Transputerpunk.

I cannot wait for my cowsay coprocessor.

And a datacenter for Emacs.

At some point Intel was experimenting a Xeon with built-in FPGA, maybe they were just a bit too early to the game :)

Almost 30 years ago there was a project about making a computer which used FPGAs for all "software". It was called RAW.

Baring it all to software: Raw machines | IEEE Journals & Magazine | IEEE Xplore https://share.google/nI9GyFJu4HvbYFrBf

(If you Google the name you will find free PDFs as well, the IEEE page is more useful as a summary and such.)


I look forward to GPGrepPU -- someone'll find a way to abuse them for scientific workloads or something.

GrePU

I wonder how close you can get with Nvidia's GPUDirect. Hook the fast NVME directly up to the GPU (well, it gets direct DMA to GPU at any rate), then implement parallel grep in CUDA... profit?

Universal Basic ASICs

If your BASIC is compiled that's just a CPU!

Twitter promised an open publishing platform with extensive API access. They're the ones who broke the (social) contract, not us.

Well if you're willing to accept that the extensive API access comes at a price, they at least somewhat fulfilled that promise.

It's just a different kind of gate, though.


This is definitely true in an information theory sense: having more knowledge is always better than less knowledge. However, it may not be true in math as a social human endeavor, and having answers without interesting paths to get there may not expand human mathematics in the same way.

If Fermat had a book with larger margins, would Weil have devoted so much time to proving the Taniyama-Shimura conjecture? No one can say.


It does sound totally ridiculous. Sadly it may not be. Previously discussed: https://news.ycombinator.com/item?id=48956688 "LG monitors silently install software through Windows Update without consent".

You can argue if it actually installs the software or just nags the user to install it, but neither are things microsoft would allow a monitor "driver" to do if they had any integrity.


Lost me at the first assumption. People can argue about how useful AI is, but it's obviously not essential because we somehow managed to write code without it a few years ago. I would even say the code was better back then.

The two tasks of writing code and engineering software cannot be separated without damaging the integrity of the mental model of the engineer. Having architects who didn't interact with the code always produced map/territory mismatches.


This whole week I've been dealing with incidental complexity created by shortcuts taken and edge cases not handled in code written in the before times, both in mine and in others'. I realized at some point yesterday that these kinds of shortcuts would no longer be accepted with competent LLM use.


    I realized at some point yesterday that these kinds of shortcuts would no longer be accepted
    with competent LLM use.
What a load of bullshit. LLMs cut corners constantly and only handle the happy path.


Right, when used incompetently. When used competently they can carefully reason through every edge case and flag things no human would have picked up on.

One example: in some old code I wrote I had assumed that the Rust Hash impl for a type is stable over time. This is not the case in general, but writing a custom hasher for a complex type is incredibly annoying, so I took that shortcut. That was fine for years, but came back to bite me this week as I was trying to update a dependency.

How much incidental complexity is due to that kind of thing? An LLM code review would flag this instantly, and one would also write a stable hash function for you.


The mental model was required when your brain was the only chance to reason about changes, answer cross-cutting questions (architecture), and develop a visceral feel for the project, because that's what you needed to write high quality software

It's hard to let that go, but you already had to in larger human organizations/collaborations where you might be assigned work on systems you never/seldom touch, or coming back to a project you haven't touched in a long time.

You don't need a mental model when you can automate the reasoning and the benchmarks that vet the reasoning. Your mental model is better spent pondering->reconsidering high level things like invariants, and then automating the the proof and implementation of those decisions.

Consider how you can just get Claude to start a workflow of 15 Fable agents to fan out over your system looking for correction/simplification/perf opportunities before spawn another wave of agents to vet the list of findings. How much time and energy and studying of the code would it have taken you to build and vet the same list?


We built houses before we had nailguns but now that we have them they're pretty essential to building a house.


Hammer and nail still works, it’s just not as fast and strains the builders.

Problem with the analogy is that the strain in software engineering is necessary for an in depth understanding of the code.

The question is whether that depth of knowledge is ultimately more helpful than the speed that we can build with AI.


Sadly many managers decided to do so and the damage is done

I love to say that

  Some managers didn't pass the Turing test


Have you looked at the machine instructions your compiler produces?

No? Why?

Because software languages are a pretty good abstraction.

To the extent that good abstractions are in place, you can avoid looking at code specifically.

Those don't perfectly well exist, so it takes a lot of self discipline and the right tools/methods, but invariably, AI will produce better systems.

That said, its very easy to produce slop, so well see much more of it.

But mostly, it will be AI from here on in, as a matter of productivity. There are some arguments on the margins but those will fade over the next few years.

'At minimum' - the 'power tools' are here to stay.


LLMs are pretty much the exact opposite of a reliable compiler-like abstraction.

This is true to such an extent that I have to question the overall competence of anybody who makes the comparison. It's an enormous red flag.

I'd recommend reading Joel spolsky's leaky abstractions essay coz while it applies less and less 20 years later to things like kernel abstractions it explains very well why treating the LLM as a compiler sets you up for abject failures.


A compiler translating high-level code to machine code is a predictable and repeatable process.

An LLM translating a prompt to to high-level code has a much lower degree of predictability. To say an LLM prompt is a comparable abstraction is unfair, though I admit it's getting very close.


The LLM will never produce the same output each time, it doesn't have to do that to have very strong level of abstraction.

But yes, it has to fulfill some kind of contract defined by the absraction.

It's less a problem of the LLM, and more so how we use them, and the inherent tooling around it.


I don't get the use of "abstraction" in this context, I must admit.

Programming abstractions offer interfaces to functionality that are both simplified in use and restricted in capability. (e.g. any API or compiler.) I don't see how LLMs meet that definition.

It seems more like we're talking about offloading or delegation, here. And that's a valid business tactic, certainly, but it's not a software abstraction any more than a CTO is an abstraction of a tech lead, no?

> But yes, it has to fulfill some kind of contract defined by the absraction.

I don't follow. Is the contact here the design specification for the system? If so, again, I'd argue that's not an abstraction.


An abstraction could be a design requirement, expressed in some way.

That's definitely an abstraction.

IDLs are a form of abstraction, they're a requirement somewhat more formally described.

Remember UML? That was an attempt to go 1/2 layer above the code, that was an abstraction.

There were tons of tools like that.

APIs are an abstraction - maybe the best example. We write code to match exactly the behaviour defined by an APU - as long as it meets the requirement of that contract, then 'it's good'. And there could be many ways of doing that.


Higher level languages are still formal languages. I think there's a conceptual difference between moving from one formal language to another (machine instructions to asm or asm to C) and moving from a formal language to natural language. So yes, developing, looking at and understanding a formal description of your system has benefits for an engineer compared to handing off this step completely.


Anyone who is involved in any sort of performance critical work looks at compiler output on a regular, if not daily basis.


Sure but you only look at it when optimizing some performance critical code, usually the hot path. That is usually a tiny fraction of the codebase. I also use AI to generate large amounts of code but I only inspect the actual code when critical, delicate or architecturally important stuff is involved.


Yes, but even HFT traders use Java and don't look at the compiler output.

Looking at the compiler output is a totally valid concept, but it's definitely a niche case.


If you're doing high performance Java you're definitely looking at the compiler output. At least you should be.

It's arguably more important with Java than with the compiler output for something like C++, as C2 is much more unpredictable and dependent on runtime circumstances. You also want to be real certain that bounds and null checks are omitted as those come at a pretty big performance premium.


> Have you looked at the machine instructions your compiler produces?

> No? Why?

> Because software languages are a pretty good abstraction.

No, it’s because compilers produce deterministic output. I am so tired of this argument.

If I’m not concerned with the performance of my code, I can be 100% confident that that exact code will produce the correct assembly every time. That’s why I don’t read it. Not because I don’t care.


No - perfect determinism is absolutely not required.

It's entirely the nature of the abstraction.

You want it to work as expected, it does not have to produce the same thing each time.


No, determinism is actually required. If compilers changed between producing decent assembly and crap assembly from run to run, we would be reading the generated assembly every single time.


Yall modern compilers do not produce the same thing every time. Compilers have had decades to get really good at what they do. LLMs have been functional for maybe 3 years?

Source: I work on an operating system.


AI is a technology for removing nines from uptime, and adding them to Sturgeon's law.


ACM agrees I think: https://dl.acm.org/openaccess

> Beginning January 2026, all ACM publications and related artifacts in the ACM Digital Library will be made open access.


Wait, so did this already happen and it just didn’t get attention?


It was a front page story here on HN back in December 2025:

https://news.ycombinator.com/item?id=46313991


It got a lot of discussion here when it happened and before as they phased it in.


Determinism isn't the main hurdle. It would be a moderate effort to engineer a deterministic claude that would be no more useful than the current one.

The key characteristic of a compiler is that it takes a source language with a well-defined meaning to a target language with a well-defined meaning.

The reason claude fails to be a compiler is that its input language (english) can't be precisely defined. (And even if that were possible, it would very often fail to preserve the meaning when "compiling")


You may have been thinking of this one instead https://what-if.xkcd.com/141/ . Maybe we should put Randall on the supervillain watchlist.


This is a case of lethal trifecta. This particular one can be fixed by either not giving the AI private data, or by removing the exfiltration opportunity. Why does the comment-summary bot need access to your private video ids? Why does it need to be able to output links?

Most cases of prompt injection are harder to fix, and the success of the products they occur in relies on engineers who should know better sticking their heads in the sand about security risks.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: