Also want to advertise a little about my work: https://arxiv.org/pdf/2305.00061.pdf, it allows the agent to generate symbolic operators and allows the agent to decompose the problem in a very flexible manner.
The nice thing about autonomous AI agents might be that compared to self-driving cars, the false positive effects aren't that disastrous. There could be a lot of opportunities to try things that are time cumbersome but isn't the worst if let's say the AI fails at making a reservation at a restaurant the first 10 times.
https://twitter.com/mcraddock/status/1645779894670950400/photo/1
A bit bigger map of LLM + Prompt Enginnering
Great deconstruction plus love the wordplay on anatomy of autonomy
Self-driving cars, the future is not so close: https://techcrunch.com/2023/08/18/cruise-told-by-regulators-to-immediately-reduce-robotaxi-fleet-50-following-crash/
Thanks for sharing! Very nice review!
Also want to advertise a little about my work: https://arxiv.org/pdf/2305.00061.pdf, it allows the agent to generate symbolic operators and allows the agent to decompose the problem in a very flexible manner.
Great piece. Fantastic talk last night at the Github event
as soon as I read the title, i knew i was gonna love the article.
A valuable, extensive, insightful overview. Thanks!
The nice thing about autonomous AI agents might be that compared to self-driving cars, the false positive effects aren't that disastrous. There could be a lot of opportunities to try things that are time cumbersome but isn't the worst if let's say the AI fails at making a reservation at a restaurant the first 10 times.