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

/architect: Reduce Fable tokens by 80%, Fable orchestrates/reviews, Codex builds

github.com

Post reply on HN
Print view View original

31–40 of 47 posts

Re: /architect: Reduce Fable tokens by 80%, Fable orchestrates/reviews, Codex builds

#33

Post by AlphaSite »

smoe wrote: post #18
Eridrus wrote: post #15

Earlier quoted context omitted.

The problem is that there are a bunch of benchmarks, the model providers often don't even use the same benchmarks, a bunch of them have known problems, and it's expensive to do your own benchmarks. I am a GPT 5.x booster since to me it just feels smarter, and I generally felt like the benchmarks backed me up, but it's not every benchmark, so sadly we're mostly arguing about vibes. SWEBench-Pro was a big one, though a…

I find it fascinating that every time this kind of discussion comes up, people talk about night and day experiences between Claude and Codex, in both directions. I’m really wondering what people are doing to get such different outcomes. I’m currently working on two projects/clients one using Claude, one using Codex. I have a strong preference for the latter, but not because I think it is much more intelligent or writ…

It probably means they’re close enough that there’s no observable difference. Or better at every different things.

Re: /architect: Reduce Fable tokens by 80%, Fable orchestrates/reviews, Codex builds

#36

Post by colechristensen »

malshe wrote: post #9
colechristensen wrote: post #3

Last night I switched back to Codex for a minute having burned through my tokens for the week with Fable and oh boy I had a terrible experience. Running in circles over simple problems (which I ended up solving myself, like a peasant) and running "terraform apply" several times despite several instructions all over the place to never do that. The performance difference was stark.

I had a similar experience. So far Fable has been a game changer, at least for the work I used it for. Having said that, I think its writing is definitely worse than GPT 5.5. Ethan Mollick also observed the same. He called it more "Claudy." It generates worse academic prose than other frontier models.

I think the claude code harness made up a significant part of the improvements co-released with Fable, the nested agent capabilities seem to be much better even with opus (which I guess we're stuck with for a while).

Re: /architect: Reduce Fable tokens by 80%, Fable orchestrates/reviews, Codex builds

#37

Post by testfrequency »

analogpixel wrote: post #27

I know how to reduce Fable tokens by 100% ; https://www.anthropic.com/news/fable-mythos-access

I ran this and seem to have good results with a 100% reduction also: curl -fsSL https://chatgpt.com/codex/install.sh | sh

Re: /architect: Reduce Fable tokens by 80%, Fable orchestrates/reviews, Codex builds

#38

Post by nostrebored »

everforward wrote: post #26
Denvercoder9 wrote: post #16

DESIGN.md: > Each rule below is enforced mechanically by the skill, not left to vibes. > R1. Repo docs are the memory; not in HANDOFF.md = didn't happen SKILL.md: > Not in docs/HANDOFF.md = didn't happen. Refuse to judge results that exist only in conversation or builder chat output. "Mechnical enforcement" just means "prompting the LLM a bit extra" these days? It (still) amazes me how much effort and tokens we expen…

Agents are in a wacky state, which makes projects like this fall into a weird spot. Eg I vaguely expect my agent to do two disparate things: manage dependency injection for tools, prompt modifications, etc, but also be the sort of “brain trust” that controls the flow of execution (can we stop now, do we keep going, etc). This project is meant to be the latter, but there’s not a clean way to integrate that into Claude…

But why does your agent control doneness? It seems to me the most odd part to delegate. All LLMs are terrible at it. Most LLM tasks can be expressed as a DAG or DAG of DAGs. Why delegate that to a random point in context instead of enforcing the flow?

Re: /architect: Reduce Fable tokens by 80%, Fable orchestrates/reviews, Codex builds

#39

Post by nostrebored »

Retr0id wrote: post #32

> freezes the gates LLM-written readmes love to use inscrutable jargon that means nothing outside of the context window that birthed it.

LLMs are obsessed with “gates”. Freezing the gates here is intuitive to me as this point — don’t let validation drift.
Post reply on HN