Ex-surgeon. PM in finance & aviation, building with AI
Joined March 2011
- Tweets 50
- Following 411
- Followers 260
- Likes 761
5 Photos and videos
Shipped unified learner memory to the /durable-learning skill. Topics used to be islands - separate ledgers with separate review queues. Now one root folder holds every mission: a single due queue across all topics, ordered by how many other capabilities depend on each item, and cross-topic prerequisites. github.com/musi27/durable-le…
39
I wrote about durable learning with a model in the loop: once a model sits inside, output stops being a signal of understanding, and what actually matters is whether the capability transfers to the learner. I wanted to test @claudeai Fable, so I tried turning that into a skill.
1
1
2,592
It's 7 markdown files and one Python script, portable to any agent that reads skills. I'm now using it to learn about post-trade settlement - would love your feedback if you give it a go. github.com/musi27/durable-le…
26
I'm 10 months post-ACL surgery - so the final stage of recovery (thankfully!), working on pivoting for tennis and padel. This needs un-cued training, because the hard part of those sports is reacting to things you didn't plan for. Cued, predictable drills do not help with this.
2
1
96
Live at musi.live/reactive-trainer. Excited to test this over the next few weeks as I get ready for returning to sport!
60
Published the spec for Prism's HTTP API and JSON log format in a SPEC.md at the project root, so anyone can build an SDK in any language against the same UI server. Python is today's official SDK; the TypeScript port is next on the list. Interested to hear feedback on the spec, especially from anyone wanting to take a swing at a community SDK before I get to TS. github.com/musi27/prism
1
162
I audited the 9 running versions of my @polymarket weather trading bot. A 285:1 longshot that resolved yes hit every version, skewing the PnL by 75%. A trade that every version catches cannot rank them - I found that the comparison was more valuable in areas of disagreement.
1
178
With @BrainbankSpace I've tried to design for this: AI generates & explains, the spaced repetition loop forces internalisation. The capability should live in the user, not in the tool. This handles the retrieval side, but it does not solve or measure the transfer of capability.
1
96