One intuitive way to think about how AI models (Large Language Models) can are used as an "agent" is to consider using the model to predict what actions to take, given a particular state of the world. This approach some times go by the name "Large Action Model". For example, you
@jiquanngiam
-
State Management for AI Agents: Side Effects and UX
By
–
state management is hard! we've been thinking a lot along the lines of staged side effects, io monads, and how to represent real world state changes as well. doing this right, with the right ux, will unlock a lot more user comfort with agents.
-
Lutra AI Gains Self-Reflection and Faster Capabilities
By
–
@Lutra_AI is getting easier to use and more capable! We've been hard at work bringing in more capabilities for it to self-reflect, self-debug, and run even faster — so that users can just give it high level directions and it'll figure it out. As models accelerate in
-
AI Boosts Productivity: Happy Ramp Customer Shares Success
By
–
Love it when AI significantly improves productivity, and happy @tryramp customer here too!
-
Lutra AI email drafting tool integration and context features
By
–
I’m using @Lutra_AI for email drafting. You could give it more context by asking it to draft based on say instructions from a Google doc, and also find recent emails from that sender
-
Creating Workflows Using Natural Language Only
By
–
We're making it possible to create these kind of workflows using only language! DM me if you'd like early access to @Lutra_AI
-
Lutra AI Product Update from Camp Hustle
By
–
@ericbahn and @dunkhippo33 are amazing! Super excited to be at camp hustle — we'll be sharing more around the next version of the Lutra (coming soon!) and we've learned building AI products.
-
Claude 3 Haiku Outperforms GPT-4 on HumanEval Coding Benchmark
By
–
Claude 3 Haiku’s reported coding performance on HumanEval exceeds GPT-4 & Claude 3 Sonnet while being way cheaper, faster… @AnthropicAI @OpenAI
-
Task Completion Time and AI Guidance Requirements
By
–
How long do these tasks take to complete / how much guidance do you need to give it?
-
AI Raises Floor and Ceiling for Software Engineers
By
–
AI raises both the ceiling and the floor; much easier to be an entry level engineer (just prompt), but also much more effective as an experienced SWE that leverages models well