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.
> Not because it is aesthetically pleasing. Because every other shape eventually runs into the same boring failures: context rot, self-grading, goalpost drift, and merge chaos.
Actual failure isn't boring. But struggling through a generated software project that celebrates its own genius and doesn't have a single self-critical or genuinely reflective thing to say...at least watching paint dry I might get giddy off the fumes.
I'm not interested in critiquing the project itself, either, you'll just run that through a model, too.
I don't disagree with any of this. It is generated software, and it's not a novel idea. I didn't mean for it to come off like that. It's just solving an itch that I couldn't find a solution to and I'm getting a lot of personal utility out of it. I do have a lot of experience with agentic memory, multi-agent systems and harnesses and wasn't super impressed by the workflow of Fable calling opus subagents so I figured I'd apply best practices to what already exists to make it a teensy bit better and easier to use.
Cheers. Absent explanation, I do think it's reasonable to assume that you stood by the wording/claims of the README when you posted it, but I appreciate the patch you made to the docs.
FWIW, re: best practices, your install script potentially runs `rm -rf` on the user's global skills whose names shadow your project's.
> 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 expend on what could and should be a two line script...
yes I'm using Fable to inspect, generate plan and architectural docs then using Gemini to implement then have Fable review, find bugs. saving lots of usage.
Reducing token usage is this year's "one weird trick". It doesn't make sense on the face of it.
Even if one discovered something that millions (billions?) of dollars of AI compute and the best statisticians in the world was not able to find via exhaustive research, domain search and training... what do you think are the chances this won't be folded into the next update of every model, making the rigmarole moot?
Extraordinary claims require extraordinary evidence and technology-shattering innovations in AI are not know to come from a markdown.
I actually just started doing this by having Fable roleplay as Jeff Dean and to use Codex as Sanjay driving the implementation and have them go back and forth. Works really well and it’s cool to see AI pair program
@DanMcInerney Thank you for sharing this! Using a larger model for planning and a cheaper, smaller model for execution is a smart way to save tokens and seems like the way to go in general.
I wanted to see what would happen if Claude delegated work to pi wiht a model like Deepseek, so I forked your repo and tried it out. It's working really well so far.
https://github.com/pcomans/architect-loop-pi
22 comments
[ 1.7 ms ] story [ 43.9 ms ] thread> I am fairly convinced this is the shape serious agent work keeps converging toward.
"this" being "plan with expensive model, implement with cheap model".
Anyone who follows HN would be hard-pressed to disagree; this architecture is re-invented twice monthly.
https://www.facebook.com/groups/vibecodinglife/posts/1946207... https://github.com/openai/codex/discussions/10628 https://build5nines.com/stop-burning-premium-requests-how-to...
> Not because it is aesthetically pleasing. Because every other shape eventually runs into the same boring failures: context rot, self-grading, goalpost drift, and merge chaos.
Actual failure isn't boring. But struggling through a generated software project that celebrates its own genius and doesn't have a single self-critical or genuinely reflective thing to say...at least watching paint dry I might get giddy off the fumes.
I'm not interested in critiquing the project itself, either, you'll just run that through a model, too.
wow linking a facebook groups post might actually be worse than x, is there an xcancel alternative for facebook?
FWIW, re: best practices, your install script potentially runs `rm -rf` on the user's global skills whose names shadow your project's.
> 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 expend on what could and should be a two line script...
Even if one discovered something that millions (billions?) of dollars of AI compute and the best statisticians in the world was not able to find via exhaustive research, domain search and training... what do you think are the chances this won't be folded into the next update of every model, making the rigmarole moot?
Extraordinary claims require extraordinary evidence and technology-shattering innovations in AI are not know to come from a markdown.
You can use any agent and/or model for each step and share context between them.
LLM-written readmes love to use inscrutable jargon that means nothing outside of the context window that birthed it.
I wanted to see what would happen if Claude delegated work to pi wiht a model like Deepseek, so I forked your repo and tried it out. It's working really well so far. https://github.com/pcomans/architect-loop-pi