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

481–486 of 486 posts

Re: Reports of code's death are greatly exaggerated

#481

Post by Sateeshm »

moconnor wrote: post #384
abcde666777 wrote: post #178

It seems to be inevitable that with any new technology we go through a phase of super duper excitement about the possibilities, where we try to use it to the extreme, and through that process start to absorb what it actually is and isn't capable of. The hype cycle's distasteful of course, but I've accepted that this is how humans figure out what things are. Like a child we have to abuse it before we learn how to prop…

I’ve been programming professionally for 25 years. Well, 24 really because in the whole last year I barely wrote a line myself but my output increased dramatically. If you can’t see that it’s over, I’m not sure what to tell you. You will, in time.

Okay. Did you think about the code even if you didn't type it out?

Re: Reports of code's death are greatly exaggerated

#482

Post by elgertam »

pylua wrote: post #476
elgertam wrote: post #345

Earlier quoted context omitted.

MCP connects the LLM to the APIs, which can be consulted with "tool calls." I'm talking about integrating the software I produce (with LLM assistance) to APIs. Traditionally, this is a nightmare given poor documentation. LLMs have helped me cut through the noise.

Right, I haven’t used it but thought at a high level it can do that integration on the fly. I also do a lot of software system to system and in the long run I feel like ai will solve this.

I built an MCP server to speak WHOIS/RDAP so I could have Claude give me better domain name suggestions that weren't already taken. It can also be used in LLM-enabled applications (provided that the model is "tool calling" and that there's an orchestrator).

In principle, MCP servers can be created for just about any OAuth-protected API. However, you still need to create the server, and this is where the usage I'm talking about shines: when working on the MCP server, an LLM can be quite helpful in getting the right APIs integrated.

The same goes for other development that doesn't need an LLM context built-in. If I wanted to sync two calendars, for instance, I wouldn't build an MCP that speaks CalDav and Exchange and then let it loose (though this so-called agentic workflow is becoming more popular); I'd want to build software with an LLM's help that can speak both protocols by having it generate code to handle whatever OAuth tokens and scopes are necessary and then help me deploy the thing.

Re: Reports of code's death are greatly exaggerated

#483

Post by moconnor »

Sateeshm wrote: post #481
moconnor wrote: post #384

Earlier quoted context omitted.

I’ve been programming professionally for 25 years. Well, 24 really because in the whole last year I barely wrote a line myself but my output increased dramatically. If you can’t see that it’s over, I’m not sure what to tell you. You will, in time.

Okay. Did you think about the code even if you didn't type it out?

Sometimes yes, sometimes no. A lot of it was “debug this issue and fix it” or “write this small tool to do X”

Re: Reports of code's death are greatly exaggerated

#484

Post by moconnor »

shimman wrote: post #406
moconnor wrote: post #384

Earlier quoted context omitted.

I’ve been programming professionally for 25 years. Well, 24 really because in the whole last year I barely wrote a line myself but my output increased dramatically. If you can’t see that it’s over, I’m not sure what to tell you. You will, in time.

The type of work matters and understanding how capital interacts with labor is something that hasn't really changed over the last 150 years (not the first time productivity tools have been introduced in capitalism). All we are going to get is increased mass surveillance and molding software engineers into more assembly line work. Both things do not sound good or reasonable nor wanted by a majority in our industry. Bu…

I’m not saying I prefer it like this. Just stating that the change is already inevitable.

Re: Reports of code's death are greatly exaggerated

#485

Post by thesz »

vidarh wrote: post #472
thesz wrote: post #443

Earlier quoted context omitted.

The difference is quantum oracles can be constructed [1] and Turing oracle can't be [2]: "An oracle machine or o-machine is a Turing a-machine that pauses its computation at state "o" while, to complete its calculation, it "awaits the decision" of "the oracle"—an entity unspecified by Turing "apart from saying that it cannot be a machine" (Turing (1939)." [1] https://arxiv.org/abs/2303.14959 [2] https://en.wikipedia.…

This is meaningless. A Turing machine is defined in terms of state transitions. Between those state transitions, there is a pause in computation at any point where the operations takes time. Those pauses are just not part of the definition because they are irrelevant to the computational outcome. And given we have no evidence that quantum oracles exceeds the Turing computable, all the evidence we have suggests that t…

  > This is meaningless.
Turing machines grew from the constructive mathematics [1], where proofs are constructions of the objects or, in other words, algorithms to compute them.

  [1] https://en.wikipedia.org/wiki/Constructivism_(philosophy_of_mathematics)#Constructive_mathematics
Saying that there is no difference between things that can be constructed (quantum oracles) and things that are given and cannot be constructed (Turing oracles - they are not even machines of any sort) is a direct refutation of the very base of the Turing machine theoretical base.

Re: Reports of code's death are greatly exaggerated

#486

Post by thesz »

vidarh wrote: post #401
jibal wrote: post #397

Earlier quoted context omitted.

That's an irrelevant strawman. It tells us nothing about how create such a system ... how to pluck it out of the infinity of TMs. It's like saying that bridges are necessarily built from atoms and adhere to the laws of physics--that's of no help to engineers trying to build a bridge. And there's also the other side of the GP's point--Turing completeness not necessary for creativity--not by a long shot. (In fact, huma…

No, twisting ot to be about how to create such a system is the strawman. > Turing completeness not necessary for creativity--not by a long shot. This is by far a more extreme claim than the others in this thread. A system that is not even Turing complete is extremely limited. It's near impossible to construct a system with the ability to loop and branch that isn't Turing complete, for example. >(In fact, humans are n…

  > A system that is not even Turing complete is extremely limited.
Agda is not Turing-complete, yet it is very useful.
Post reply on HN