@HamelHusain Most orgs aren‘t set up to provide their employees with a second, always-on computer they can provision, despite an agent computer in the cloud.
@mattpocockuk An ontology gets you a shared knowledge model with entities, relationships between them, and rules. UL on the other hand is terms and meanings, though more a shared language, not a knowledge model. Ontologies can help agents make sense of big code bases much more token-efficient.
You may have been told to watch this video about the OpenAI AI hack. You really should, even if you don't usually care about tech stuff.
If nothing else, click this link to the 18 minutes in & see how the agents spoke with each other. Its eye opening. https://t.co/G12N4FKfHG
@AndrewYNg Hey Andrew, the three loop sizes remind me of my book on the subject and the mental framework behind it: „The Elastic Loop“. It also has a skill that can assess a team‘s readiness for certain loop sizes. https://t.co/T6SHkixQ6w
@petergyang Things it does well for me:
- It keeps updating me while it‘s on a long running task, no falling asleep at the wheel, it responds when its done
- automatic skill extraction works good for me
- crons are much less brittle