Standardized tool calling **tl;dr;** we've made some big improvements to working with tools across model providers! A new `tool_calls` field directly on messages with the same schema for all providers. A new `ToolCallingAgent`. Supports any model with tool calling
AGENTS
-
Eco GPT: AI-powered tool to help solve environmental disaster
By
–
Our planet is suffering from an ecological disaster.
— God of Prompt (@godofprompt) 11 avril 2024
But AI can definitely help us solve this issue.
So I created Eco GPT! Learn, research, explore all the topics relevant to saving our environment.
🔗Try it out here: https://t.co/ufUfamFijp#chatgptplus #ChatGPT4 pic.twitter.com/xv0OxChy5NOur planet is suffering from an ecological disaster. But AI can definitely help us solve this issue. So I created Eco GPT! Learn, research, explore all the topics relevant to saving our environment. Try it out here: https://
godofprompt.ai/gpts/eco-gpt #chatgptplus #ChatGPT4 -
AI Agents for Personal Use via Simplified Chat Interface
By
–
For personal use yeah , definitely. My guess is that these agents will be available through chat interface as you have now, it will be even more simplified as I'm guessing and you'll only need to press a few buttons. The difference is: Agents go around internet for you and
-
Custom Mixtral 8x22B Integrated into HyperWrite Platform
By
–
I've hacked a custom Mixtral 8x22B into the @HyperWriteAI platform. With access to real-time info. Will spend some time iterating and improving it, then we'll roll it out to our user base!
-
Sociology of Three Body Problem: AI Ethics Discussion
By
–
Yesterday, Adam Ford recorded an extensive discussion between Anders Sandberg, Colin Hanson, James Hughes and me on the sociology of the 3 body problem, I expect he will publish it soon
-
Building AI Tools: Managing Model Mistakes and Reliability
By
–
Not at all. I'm building tools that work against multiple models, I'm happy to leave the detailed evals to other people. I'm going to tell my users that they should assume that AI makes mistakes all the time, because that's a pretty good rule of thumb for everything!
-
Model Scale Determines Agent Brain Performance and Capability
By
–
This is a key point on AI agents "Brains" matter for agents. As long as the scaling law holds, you get much better results out of using bigger frontier models as the main brains of your agent, though it might be able to delegate to lesser AIs Labs with the best model get the
-
Fair Testing: Providing Devin with Complete Files and Guidance
By
–
realized the last 2 days have been completely unfair to devin – i didnt reupload the .py thing it is supposed to clone so it was just churning around. now i gave it both files + gave a methodological hint.
-
Choosing the Right AI Agent Framework: Key Considerations
By
–
Choosing the Right AI Agent Framework
– Popular frameworks include AutoGPT, Baby AGI, Crew AI, Autogen, Multion, ChatDev, and MetaGPT – The best framework depends on your skill level and goals – Prioritize frameworks with deep documentation, lots of tutorials, and a low barrier -
Agents as First Step to System 2 Thinking in AI
By
–
System 1 and System 2 Thinking in AI Agents – LLMs like ChatGPT are only capable of System 1 thinking (fast, impulsive, automatic decisions) – Agents are the first step towards giving AI the ability to form long-term plans and execute upon them (System 2 thinking)