Hacker Newsnew | past | comments | ask | show | jobs | submit | dist-epoch's commentslogin

I think it depends.

I regularly ask both GPT and Gemini to give me options - programming libraries to do X, architecture suggestions, names for projects/services/classes

After they answer I ask each model what does it think of the other answer, and to give me a final suggestion considering both answers.

Both GPT and Gemini would frequently say "that other answer is much better than my one, it considered X factor that I missed".


Try telling it the answer came from a small local LLM..the condescension can become palpable.

The kind of exploration that would require a massive one-month of full-time investment before LLMs. Now doable in days.

(I don't know on which side of this author was)


I've seen such explorations done over a couple of days during weekend hackathons or gamejams.

Have we gotten so addicted to our daily token fix that we can't even fathom focusing for 48h?


Not me, but I would produce a much larger output with 48h focus on my token fix.

> Since we started it in 2005 we've funded about 6500 companies.

> I've spent the last 21 years training people to become billionaires. So far about 30 of them have

Since it's a post about math, let's do it.

6500 companies with 2 founders each - 13000 founders.

30 of them became billionaires - 0.2% of them.

So being a tech founder at the most famous startup accelerator in the world give you about 0.2% chance of becoming a billionaire.

Or put another way, only 1 out of every 500 YC-combinator founded startup makes one of it's founders a billionaire.


So, like string theory?

Exactly like string theory.

Really? I was under the assumption that there are 1-2 constants that could help falsify string theory?

String theory is in fact falsifiable contrary to popular belief. It's just not practically falsifiable with current (and likely future, for a while) technology as the energy scales we need to probe to falsify it are astronomically large.

As the joke goes, there are more GUI frameworks (game engines) for Rust than apps (games) written in them.

It's a lost battle.

Everything will need to be run in a VM separated from your main desktop which should have your data and a minimal amount of apps.

Qubes OS was ahead of it's time.


"linux has a central package manager with every app that you need, so you don't need to install random apps from random websites like on windows"

> central

That will end badly at some point


The vast majority of jobs are not full-filling or enjoyable. Because there were way more job seekers than jobs.

Programming was one of the ones which was, because there were fewer programmers than openings. Now that's flipping, thus naturally, the enjoyment is going to be sucked out of it.


It's not unmaintainable if you have 1000 agents maintain it.

It is unmaintainable even if you spend 100k per month on tokens to have LLMs pretend they are maintaining it, if they slow down and make little ACTUAL progress. Sadly real progress is impossible to measure, if all you have is an overexcited """engineer""", a credit card, and so much cash spent you could hire all the best engineers you know and still have money for a porsche.

Well, software presumably has a goal of accomplishing something for some end-user, so the progress should be trivial to measure: are features/changes being completed?

The marketing ploys of OpenAI/Anthropic where agents build something that nobody uses might be hard to track given that there are zero users. But what about everyone using agents for real software? It's trivial to prove that agents make progress.


Yes that is the entire point. Measure features deployed in production and their value in gaining and retaining customers or users, cost reductions, reduced incidents and outages, etc.

Lines of code is completely irrelevant as a metric.


It's not unmaintainable if most of it is tests. Just have it write tests until it becomes safe for AI.

I hate I can't tell if you're joking without checking posting history lol

…and then the CEO sees the token bill…


Chrome is basically reinventing each OS API and libraries. One day they’ll have their own tcp stack and packet filter.

It kinda makes sense given that one of their major products is a computer that runs an operating system literally called ChromeOS.

Arguably with QUIC it already does.

Chrome still has a way to go until Zawinski's Law is satisfied natively.

http://www.catb.org/jargon/html/Z/Zawinskis-Law.html


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

Search: