Scotter

MCP is great but I’ve found a fully fleshed out CLI with a Claude skill is fast and token efficient when doing lots of calls.

sharedskills/asana at main · dmoskov/sharedskills Contribute to dmoskov/sharedskills development by creating an account on GitHub.

Fellow alum Scott Carleton and I built an Asana client designed for AI coding agents like Claude Code. It's a fast, reliable alternative to MCP tools.
→ Search/create/update/comment on tasks
→ Manage goals, custom fields, dependecies, and more

github.com/dmoskov/sharedskills/tree/main/asana

Do you expect 'value engineering' to need to happen at the foundational layers or to be easier via post-training methods?

My latest blog. An open discussion on changing healthcare

Blogmaverick.com

It’s a big leap - every announcement over the last two years has stunned me. As the dust in my mind settles, these very smart models still can’t solve the core challenges when applying them, which is to ensure they have the right context to work with. Which ultimately is a user problem now.

Putting aside agentic approaches, the current transformer design doesn’t seem to allow an LLM to have an internal model to decide prioritization of new instructions. It has no concept of a pyramid of clarity. Which is also why it’s not good at poking holes in abstract concepts - is X incomplete?

The deep goal of bluesky is to decentralize the social internet so that every individual controls their experience of it rather than having it be controlled by 5 random billionaires. Everyone thinks they signed up for a demuskified twitter...we actually signed an exciting and bizarre experiment.

Egoless Engineering It turns out misery is a shitty proxy metric.

Hello, I wrote a new talk that is ultimately about how misery is a dumb strategy

egoless.engineering