Comment by layer8

1 year ago

My experience is likely colored by the fact that I tend to turn to LLMs for problems I have trouble solving by myself. I typically don't use them for the low-hanging fruits.

That's the frustrating thing. LLMs don't materially reduce the set of problems where I'm running against a wall or have trouble finding information.

25 comments

layer8

Reply
tptacek  1 year ago

I use LLMs for three things:

* To catch passive voice and nominalizations in my writing.

* To convert Linux kernel subsystems into Python so I can quickly understand them (I'm a C programmer but everyone reads Python faster).

* To write dumb programs using languages and libraries I haven't used much before; for instance, I'm an ActiveRecord person and needed to do some SQLAlchemy stuff today, and GPT 4o (and o1) kept me away from the SQLAlchemy documentation.

OpenAI talks about o1 going head to head with PhDs. I could care less. But for the specific problem we're talking about on this subthread: o1 seems materially better.

  • throwup238  1 year ago

    > * To convert Linux kernel subsystems into Python so I can quickly understand them (I'm a C programmer but everyone reads Python faster).

    Do you have an example chat of this output? Sounds interesting. Do you just dump the C source code into the prompt and ask it to convert to Python?

    • tptacek  1 year ago

      No, ChatGPT is way cooler than that. It's already read every line of kernel code ever written. I start with a subsystem: the device mapper is a good recent example. I ask things like "explain the linux device mapper. if it was a class in an object-oriented language, what would its interface look like?" and "give me dm_target as a python class". I get stuff like:

          def linear_ctr(target, argc, argv):
        print("Constructor called with args:", argc, argv)
        # Initialize target-specific data here
        return 0
     
    def linear_dtr(target):
        print("Destructor called")
        # Clean up target-specific data here
     
    def linear_map(target, bio):
        print("Mapping I/O request")
        # Perform mapping here
        return 0
     
    linear_target = DmTarget(name="linear", version=(1, 0, 0), module="dm_mod")
    linear_target.set_ctr(linear_ctr)
    linear_target.set_dtr(linear_dtr)
    linear_target.set_map(linear_map)
     
    info = linear_target.get_info()
    print(info)

      (A bunch of stuff elided). I don't care at all about the correctness of this code, because I'm just using it as a roadmap for the real Linux kernel code. The example use case code is an example of something GPT 4o provides that I didn't even know I wanted.

      6 replies →

mensetmanusman  1 year ago

LLMs are not for expanding the sphere of human knowledge, but for speeding up auto-correct of higher order processing to help you more quickly reach the shell of the sphere and make progress with your own mind :)

  • tsunamifury  1 year ago

    Definitely. When we talk about being skilled in a T shape LLMs are all about spreading your top of T and not making the bottom go deeper.

    • ben_w  1 year ago

      Indeed, not much more depth — though even Terence Tao reported useful results from an earlier version, so perhaps the breadth is a depth all of it's own: https://mathstodon.xyz/@tao/110601051375142142

      I think of it as making the top bar of the T thicker, but yes, you're right, it also spreads it much wider.

    • skydhash  1 year ago

      I prefer reading some book. Maybe the LLM was trained on some piece of knowledge not available on the net, but I much prefer the reliability and consistency of a book.

Al-Khwarizmi  1 year ago

It's funny because I'm very happy with the productivity boost from LLMs, but I use them in a way that is pretty much diametrically opposite to yours.

I can't think of many situations where I would use them for a problem that I tried to solve and failed - not only because they would probably fail, but in many cases it would even be difficult to know that it failed.

I use it for things that are not hard, can be solved by someone without a specialized degree that took the effort to learn some knowledge or skill, but would take too much work to do. And there are a lot of those, even in my highly specialized job.

troupo  1 year ago

> That's the frustrating thing. LLMs don't materially reduce the set of problems where I'm running against a wall or have trouble finding information.

As you step outside regular Stack Overflow questions for top-3 languages, you run into limitations of these predictive models.

There's no "reasoning" behind them. They are still, largely, bullshit machines.

  • KoolKat23  1 year ago

    you're both on the wrong wavelength. No one has claimed it is better than an expert human yet. Be glad, for now your jobs are safe, why not use it as a tool to boost your productivity, yes, even though you'll get proportionally less use than others in other perhaps less "expert" jobs.

    • troupo  1 year ago

      In order for it to boost productivity it needs to answer more than the regular questions for the top-3 languages on Stackoverflow, no?

      It often fails even for those questions.

      If I need to babysit it for every line of code, it's not a productivity boost.

      7 replies →