What’s especially unfortunate is we need to keep pulling more of the industry here, but there just isn’t a critical mass (or even near one) that would justify most folks only being here. Contributes to Twitter’s perpetual motion machine.

Thanks! This is the same realization I’ve had over the last 1-2 months too, starting with realizing that agents (with the right combo of prompt and tools, like memory and filesystem) are generalizable (i.e. “deep agents,” but bad term). And then agent skills was like a bolt of lightning

Those spirits can be given identities which are persistent. Under the hood, there is no “agent,” just an orchestrator, but you can operate with the fiction of them being a tangible persistent thing

(Thinking out loud), where I’m ending up is an agent ecosystem (say, within an enterprise) benefits from an “orchestrator” primitive, whereas with 1:1 spirit:body pairing wasn’t req’d. Orchestrator executes a spirit, whatever complexity it has (ranging in analogy from single agent to multi-agent).

In that sense, the “body” is infinitely copyable, and is more an actuator in an env for the spirit. But we still need the spirit+body to reason about what are the actors within an environment (I think). But it feels weird given that separation of spirit and body to recreate “agent” for that purpose

imo this distinction is relatively new and really important. “Agent” before was usually a singular combo of what you refer to as the spirit and body; now the spirit is separately definable and loadable. I am still struggling tbh with what is the primary unit to reason about, spirit or body

They hit on this in a post a few weeks ago: www.anthropic.com/engineering/... Skills really does feel like a durable phase change on top of model+tools

Yeah, that’s what’s captured my thoughts for the last few weeks. I’ve been experimenting with having Claude write skills for various things using primary source documents and it’s done a quite good job. A model doing that to formalize a task path seems very doable, and yeah, it is continual learning

Any new takeaways from this talk re skills? I’ve been pretty fascinated with their concept of “tool” being a script the model retrieves (rather than a function call) and runs in a sandbox, with the model able to also formalize paths it takes to solve tasks as skills in its sandbox

That makes sense. Knowledgebase/sources might be relevant to some fiction writing as well (to ground it, or even to create a knowledgebase for the fictional world to maintain consistency beyond context window horizon). Maybe. This would be a fun thing to play with with Claude

Kind of curious how much overlap there ends up being in process for writing of different types. Fiction, nonfiction, technical analysis, memos, etc. There’s probably a good agent skills angle to generalizing it

The library means we can add stuff over time to it and control what goes in our meal plans, while the meal plan list also creates a history of what we’ve cooked, so each week’s meal plan has variety. Quite useful, if boring.

For example, I use Reminders for a Grocery list. I have a weekly meal plan list, and is the basis for updating the grocery list. I also created a Recipe Library list. Using these, each week, and I can have Claude create a meal plan using the library and update the grocery list.

Yes! We’ve created very rich, expressive, deep ways of working together as individuals who have different knowledge and capability and fallibility, but still getting to a good outcome (and probably most important iteratively getting better together over time). Why not use those constructs

I think this framing is even more fundamental and profound than is even apparent now. We’ve already got very mature, robust processes and tools for collaborating with people (collaboration tools, team hierarchies, organizations, economies, cultures,…). I think these all apply in concrete ways.

Generally I think we’re at a point where conceptualizing an agent as a person vs some stateless things actually clarifies a ton on direction on the technical side, the what’s possible side, and the UX side

I think you guys more than others are hitting on something fundamental, which is an agent with some core set of tools and a flexible but deep memory makes an “agent” more like a person: able to apply to many tasks, and learn over time and adapt (or be taught), vs a glorified stateless micro service

Before it was not only a pain to re-up context but for sufficiently dense or subtle things, risky, because if I forget something or phrase it differently, the new conversation isn’t bounded to the previous one (though it might be in my mind). Current memory implementations reduce that somewhat