3,346 karma · joined February 17, 2018
"Trump to be locked in the pillory for mocking and pelting" citizens say
Skill is a great sleight of hand for Anthropic to get people to think Claude Code is a platform. There is no there there. Orgs will figure this out.
Cheers.
I do like the idea of a home made book workflow but no one needs a new bookstore. There are plenty of these.
I think a related area is incorporating tts for interviews esp of older family members. Support photos and audio and have some ai magic around those. Produce a family member history. That is a pdf or richer media artifact, and does not go into any bookstore. Absolutely needs local ai in that case too.
I would pay $50 for an oss fully local authoring tool (and I do pay for others like zettlr).
You can have the most capable human available to you, a supreme executive assistant. You still have to convey your intent and needs to them, your preferences, etc, with as high a degree of specificity as necessary.
And you need to provide them with access and mechanisms to do things on your behalf.
Agentic definitions are the former, and they will evolve and grow. I like the metaphor of deal terms in financial contracts- benchmarkers document billions of these now. The "deal terms" governing the work any given entity does for you will be rich and bespoke and specific, like any valuable relationship. Even if the agent is learning about you, your governance is still needed.
MCP is the latter. It is the protocol by which a thing does things for you. It will get extensions. Skill-like directives and instructions will get delivered over it.
Skills themselves are near term scaffold that will soon disappear.
The same thing is going to happen with all of the human language artifacts present in the agentic coding universe. Role definitions, skills, agentic loop prompts....the specific language, choice of words, sequence, etc really matters and will continue to evolve really rapidly, and there will be benchmarkers, I am sure of it, because quite a lot of orgs will consider their prompt artifacts to be IP.
I have personally found that a very high precision prompt will mean a smaller model on personal hardware will outperform a lazy prompt given to a foundation model. These word calculators are very very (very) sensitive. There will be gradations of quality among those who drive them best.
The best law firms are the best because they hire the best with (legal) language and are able to retain the reputation and pricing of the best. That is the moat. Same will be the case here.
Pluribus is a more interesting meditation.
"We found strong correlations between greater consumption of fat and protein to lower anxiety and depression, while consuming higher percentages of carbohydrates was associated with increased stress, anxiety, and depression"
and
"We have shown that changing diet affects mood and happiness, that greater fat and carbohydrate intake is directly associated with anxiety and depression"
I am sure it is a fine paper and it is a preprint but a direct inconsistency in the abstract...
https://docs.stripe.com/payments/ach-direct-debit/accept-a-p...
MSN going NYPost with the fanciful headlines.