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

What it feels like to work with Mythos

oneusefulthing.org

Post reply on HN
Print view View original

11–20 of 337 posts

Re: What it feels like to work with Mythos

#11

Post by matneyx »

gopalv wrote: post #9

> It worked for nine and a half hours. > Again, it wasn’t perfect. As an expert, I was able to spot some errors and omissions (some as a result of the design I had asked for) that I had the AI correct That's the bit that stuck out to me - that's longer than I would expect to work on a problem in a day or even expect to go back & fix the output of something that has a core reward loop of hours. My customers are curren…

In Claude's defense (and I cannot believe I'm defending it), I know no single dev who could create what it did (Concord), from a 19-page design document, in 9.5 working hours.

We're gonna go back to the days where our bosses ask why we're just sitting around, but instead of saying "compiling," we'll just say, "waiting for Claude."

Re: What it feels like to work with Mythos

#13

Post by PeterStuer »

gopalv wrote: post #9

> It worked for nine and a half hours. > Again, it wasn’t perfect. As an expert, I was able to spot some errors and omissions (some as a result of the design I had asked for) that I had the AI correct That's the bit that stuck out to me - that's longer than I would expect to work on a problem in a day or even expect to go back & fix the output of something that has a core reward loop of hours. My customers are curren…

My Opus 4.8 regularly works for 10+minutes on a single non-trivial coding request.

Re: What it feels like to work with Mythos

#14

Post by neogodless »

matneyx wrote: post #11
gopalv wrote: post #9

> It worked for nine and a half hours. > Again, it wasn’t perfect. As an expert, I was able to spot some errors and omissions (some as a result of the design I had asked for) that I had the AI correct That's the bit that stuck out to me - that's longer than I would expect to work on a problem in a day or even expect to go back & fix the output of something that has a core reward loop of hours. My customers are curren…

In Claude's defense (and I cannot believe I'm defending it), I know no single dev who could create what it did (Concord), from a 19-page design document, in 9.5 working hours. We're gonna go back to the days where our bosses ask why we're just sitting around, but instead of saying "compiling," we'll just say, "waiting for Claude."

For the rare uninitiated:

https://xkcd.com/303/

Re: What it feels like to work with Mythos

#15

Post by whyenot »

asdK120 wrote: post #3

Mollick runs the Generative AI Lab at Wharton, with all the corporate sponsors. He is a professor but sadly also an AI shill. He should switch to advertising washing power.

Instead of attacking the author, please respond to the content of the article. That is the HN way, and it leads to more substantive and interesting discussions.

Re: What it feels like to work with Mythos

#17

Post by hedgehog »

gopalv wrote: post #9

> It worked for nine and a half hours. > Again, it wasn’t perfect. As an expert, I was able to spot some errors and omissions (some as a result of the design I had asked for) that I had the AI correct That's the bit that stuck out to me - that's longer than I would expect to work on a problem in a day or even expect to go back & fix the output of something that has a core reward loop of hours. My customers are curren…

Work duration is also not that valuable of a measure, you're usually better off defining the process yourself in code and having that delegate chunks of work to the models. The only real issue there is that it's harder to take advantage of the providers' subscription discounts, but on the other hand it's easier to do your own model routing, and there's no way I've seen for the normal chatbots to maintain coherence on streams of work measured in days and weeks.

Re: What it feels like to work with Mythos

#18

Post by lijok »

dthread3 wrote: post #7
MostlyStable wrote: post #4

Earlier quoted context omitted.

So...no engagement with the substance? Not even to explain why it is that this is not a useful description or test of capabilities? Ok.

I would like to see it do something useful, like converting pytorch to golang.

Hot damn - is that the floor of what you consider useful?

Re: What it feels like to work with Mythos

#20

Post by cadamsdotcom »

dthread3 wrote: post #7
MostlyStable wrote: post #4

Earlier quoted context omitted.

So...no engagement with the substance? Not even to explain why it is that this is not a useful description or test of capabilities? Ok.

I would like to see it do something useful, like converting pytorch to golang.

Why not get a plan from Anthropic and get that done yourself? Probably is going to cost you as much as a coffee.
Post reply on HN