Okay, we spent the past night all playing with Fable (didn’t sleep, lol).
If you’re using Fable like you used Opus, you’re probably using it wrong.
Opus was a break through because you could give it a task and its generation of the answer was probably pretty good. So if you knew what you were doing (let’s say frontend design) then it can get really good outputs with some tasteful prompts.
Fable is really good if you don’t know what you’re doing. The best way to use it is to essentially give it a problem, such as a major refactor or optimization problem, and just tell it to spawn up N-number of agents on different work trees to solve the problem. Have one Fable agent act as the reviewer and when the agents finish their work, whatever emerges as the best answer wins.
The reason this is powerful is you’re essentially having 50+ 150 IQ people try and solve the same problem. If 49/50 are unable to solve it, but 1/50 comes up with the solution, then you have accomplished what you set out to do — which is have a novel insight or breakthrough that you, as the prompter, were not privy to.
This is essentially what the Anthropic team is trying to codify with “/loop” and “/goal” but the way they communicated it was a bit overcomplicated.
Hard problem -> spawn agents to solve -> have other agent pick best answer -> repeat.
If you do this, you’ll see the full power of Fable.
Happy hacking!
the talon documentation is live.
the full system in one place: the mechanics, the math, the token, the thesis. the source of truth for $TALON.
most launchpads optimize for volume. talon optimizes for one thing: the cost of attacking the launch.
if sybil is cheap, you get sybil. if sniping is free, you get sniped. if the rules are social, they break the moment real money arrives.
here's exactly how talon works:
https://t.co/fNbQA73H9g
privacy is for everyone.
the first wave is closed.
125 wallets selected. identities verified, the list is final.
check yours now.
https://t.co/Y4dGspDQw9
selection was never a popularity contest. we optimized for one thing: honest hands. conviction, real understanding of what we build, no farmers.
the first wave drew far more serious applications than 125 seats could hold. we read every single one, and cutting the list down meant turning away wallets that clearly understood talon and showed real conviction. the constraint was never the quality of the applicants. it was the size of the door.
so we widen it, once. this is the last wave. wave two opens 75 seats, for the deserving the first cap could not hold. more honest hands also means a larger anonymity set, and a launch no single actor can bend.
after this, the list is sealed for good.
https://t.co/FLipJh1xcW
the token is close. when it moves, it moves fast.
this is the last access before launch. it does not reopen.
https://t.co/Crw7MrnrzW
privacy is for everyone. the first hands are earned. ⬡