My thoughts and my twitter’s feeds thoughts
This week was all about the ‘loop’ and Fable. The best way I can describe it is: design the flowchart. Think of the deterministic flowchart on how you want your agents to work.
Aim to have:
more deterministic bits - this keeps things more predictable
more verification bits - this is agent feedback
more useful tool calls - tests, logs, screenshots, repo inspection etc. - this gives the agent feedback.
The ‘loop’ is essentially:
goal -> agent acts -> verifier checks -> state/memory updates -> policy decides next action -> repeat/stop/escalate
now the specific implementation of this - will differ based on what you’re working on.
If you notice you are repeating a certain workflow manually - time to DAG it up. The claude code dynamic workflows feature let the model write that DAG for you. That is fine for exploratory, reversible work.
For production software, the DAG is the product: you should write the stages, checks, stop conditions, retries, and review gates yourself. Fable capabilities are absolutely insane, I tried it myself and it is entirely worth it for you to spend 2 minutes looking at this.
There are a few projects that I fire up a new model into to see what’s it gonna do.
A project I wanted to build was a way to teach and demonstrate ‘spin’ in table tennis, every frontier model before Fable fumbled hard. But Fable outshined them with ease: https://srijanshukla.com/artifacts/spin-lab/
If you personally did not experience a big shift in capability, you are probably not asking it a complex enough or ambitious enough task.
Fable came, and Fable was taken away. The United States Government(USG) was reported with a jailbreak
- which Anthropic considers not significant. The USG anyway banned Fable just after few days of release. Big drama.
Fable was very pricey $$$$
Hence, people developed some patterns of work on those few golden days of Fable being available.
-
use Fable as planner/architect/taste/spatial/front-end judge.
-
use GPT-5.5/DeepSeek/Kimi as executor/worker.
OpenRouter released their Fusion
feature as a model on their platform, accessible via API. Fusion is basically council-of-LLMs pattern - providing results that they claim can rival the frontier Fable 5 solo.
Google Open Knowledge Format - https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md - the next iteration I think of LLMWiki.
This is “curated reusable context”
I seem to have forgotten where I saved this from, but a great way to think about how much trust can be given out to your friendly neighbourhood model,