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

Old and new apps, via modern coding agents

terrytao.wordpress.com

Post reply on HN
Print view View original

151–156 of 156 posts

Re: Old and new apps, via modern coding agents

#151

Post by wffurr »

dahart wrote: post #53
wffurr wrote: post #4

Nice balanced perspective there at the end: "as such [LLM-coded interactive] supplements are not mission-critical to the core of the paper, I again feel that the downside risk of using guided interaction with LLM agents to generate such visualizations is acceptable." It's a tool. Good for some things but not others and generally not to be trusted.

> It’s a tool. Good for some things but not for others and generally not to be trusted. I agree completely you always need to check the work of LLM agents, but it does strike me as a tiny bit funny to anthropomorphize AI by using ‘trust’ while warning against anthropomorphizing the AI by using unchecked output. ;) Generally speaking, “trust” in AI has been going up very quickly as the models & harnesses improve, and…

I don't see how "trust" is anthropomorphizing. Do I trust this bridge to hold my weight? Do I trust that this tool in my hand will perform as expected?

Re: Old and new apps, via modern coding agents

#152

Post by lagrange77 »

lanstin wrote: post #145
lagrange77 wrote: post #118

Earlier quoted context omitted.

> Metamathematics, by Kleene, is programming in maths. Ookay. Back in the day i was confused by 'Linear programming', which is optimisation and has nothing to do with coding. > every feature is ultimately filled in and the underlying beauty is obscured by a fractal of complexity required by the ever growing requirements. Right. I would say Mathematics tries to unobscure (patterns in) nature. Engineering is creating t…

The * in regular expressions is from that book by Kleene; it used to be called the Kleene star. And the book is all building up the apparatus of functional programs, recursion, implementations of arithmetic and logic, etc. it is a great book for programmers. But it is for basic computability theory, the Gödel incompleteness theorem, results on regular languages and so on.

Interesting.

Yes, functional programming feels a lot more mathy than procedural or OOP.

Re: Old and new apps, via modern coding agents

#153

Post by qup »

echelon wrote: post #127
qup wrote: post #109

Earlier quoted context omitted.

In my very small business, the supply of software has gone up (I'm building things), and they're custom to my business--so highly useful. Moreso than any off the shelf product could hope to be.

SaaS is dead. Everything is going to be brought in house.

Not everything, but a lot.

I don't anticipate replacing my payroll company, for instance.

Re: Old and new apps, via modern coding agents

#155

Post by falcor84 »

wffurr wrote: post #150
falcor84 wrote: post #65

Earlier quoted context omitted.

I don't understand what trust means in this context. Even if I were able to hire Donald Knuth to write all my code, I wouldn't "trust" it to be bug-free, let alone to be the right fit for my needs.

"Trust" - what level of review does the output need to meet your standards of correctness? Donald Knuth's code would be much more likely to meet my standards during a code review than some LLM output.

> Donald Knuth's code would be much more likely to meet my standards during a code review than some LLM output.

Just to nitpick - will it actually? I don't know what your relationship with Donald Knuth is, but to the extent I'm familiar with him and his approach to work, I would expect that even if I could afford him, I would not be able to get him to agree to accept my coding standards, whereas I found that LLMs (although flawed in many ways) can be cajoled relatively effectively to adopt my particular standards.

Re: Old and new apps, via modern coding agents

#156

Post by tough »

koe123 wrote: post #81
lioeters wrote: post #43

Earlier quoted context omitted.

It may be a question of perspective, but in my mind mathematics is upstream to everything else, including physics, biology, etc. And it doesn't just exist in the human mind or the "world of forms", as in Platon's realm of ideas. It's more fundamental than that, closer to the foundation from which all existence emerges. Our reality is like a shadow of a shadow, a fleeting illusion, compared to the eternal reality that…

Interesting point, I think you are right about it being upstream!

[flagged]
Post reply on HN