You should basically never use Fable for coding, but instead use it as a planner/orchestrator.
Most of today's advanced models can implement a spec perfectly, and once done you can send the work to Fable to review.
This has been my most powerful flow so far.
@PatrickMoorhead@AnthropicAI Have u tried it in code not Cowork or chat? While using ultra code effort and saying use a workflow for what ever task ur doing? I’d set up a new local or cloud environment setting up a simple Claude.md, instructions etc and trying it out.
@PhiloGroves I feel the same way with Netflix and most streaming platforms, thankfully I have kinda figured out that I only want documentaries on some movies on another and shows are just shows.
@RonaldReich5@DarioCpx@edzitron Demand is proven but it’s proven at substantially subsidized prices. I use ai like a mf but I wouldn’t pay api costs over sub costs for 90% of what I do.
I've got an agent in a loop optimizing a renderer with the goal to minimize frame times (and tests to measure). It got times down from 88ms to 2ms and allocations down from ~150K to 500. Sounds good, right? Wrong. This is exactly why agent psychosis is a big fucking problem.
As an experiment, I rewrote the Ghostty core render state in Go, with access to identically laid out data structures as Ghostty and the exact same validation tests. I made a purposely naive renderer (simple, correct, but slow). 88ms per frame with 150,000 allocations (horrendous, lol)!
I then kickstarted a Ralph loop to bring the frame times down. I told it it can't modify input data structures or the public API or tests (they're correct), but it can do anything else it wants. It got to work.
It has worked for about 4 hours. I've spent around $350 on this experiment so far. The results?
88ms => 1.5ms
150K allocs => ~500 allocs
Incredible right? Nope.
My hand-written renderer I ported has frame times (same benchmark) of ~20us (0.020ms) and 0 allocations in the update path.
This is the problem with psychosis and lacking systems understanding. If you don't understand the system, you're going to accept that this is an incredible result. If you understand the system, you'll see better solutions immediately and can do roughly 75x better on throughput.
The people who blindly trust agent output are in the former camp. They're sheeple, overdrinking from a fountain of mediocrity.
Standard disclaimer: I use AI all the time. I like AI. The point I'm making is to not blindly accept results. Think. Analyze. Learn.
@CWDenizen@iamgingertrash Brother it’s been 3 years from dog shit water guzzlers to OS on 1k machines pushing last years top models. Need to figure out energy first