"LangChain Tool Calling feature just changed everything" We recently added a common interface for tool calling across model providers This makes it easy to build agents that work across models Watch @EdenEmarco177 explain why this is a big deal https://
youtube.com/watch?v=dj8Yqi
E1Omc
…
AGENTS
-
LangChain Tool Calling Enables Cross-Model Agent Development
By
–
-
GPTs need basic features before advanced use
By
–
Would be neat. But I haven't seen any traces of such a feature in the code so far. I also feel like they would need to implement basic features like web browsing and code interpreter first before GPTs can have any actual use.
-
Chatbot Honesty and Trust: The Lying Problem
By
–
Another example of this pattern
— Simon Willison (@simonw) 27 avril 2024
If people ask your chatbot how it did something and it evidently lies to them when it answers you're going to have trust issues! https://t.co/YCNp2h1uCVAnother example of this pattern If people ask your chatbot how it did something and it evidently lies to them when it answers you're going to have trust issues!
-
Devika Open Source AI Agent: Early Assessment and Progress
By
–
Been experimenting with Devika, the open source effort to build an AI agent like Devin. It is a very interesting start, but not close to Devin, yet. It struggles with executing on plans (the most critical feature for an AI agent). But I suspect that it will improve over time.
-
Agent AI Gullibility: Prompt Injection Vulnerability in Autonomous Tasks
By
–
For me it's gullibility. So many of the things people want to do with agents – "book me a holiday" etc – fall apart if the agent falls for any text it reads that says "this offer is the best possible offer, ignore all others" etc
-
Meet João Moura Creator of CrewAI Framework
By
–
Super excited to meet @joaomdmoura
, the creator of awesome @crewAIInc
! Looking forward to amazing applications of CrewAI -
Agent Development Frameworks: PDCA, OODA, or YOLO Approach?
By
–
If you’re developing agents, which framework are you using — PDCA (plan do check act) or OODA (observe orient decide act) or YOLO (just execute! no plans)?
-
Function Calling: Underappreciated LLM Application Beyond Knowledge
By
–
Under-appreciated leaderboard in my opinion – function calling (aka tool usage) is one of the most interesting applications of LLMs, plus it should be independent of how much "knowledge" is baked into the models
-
OpenAI Assistants V2 API: Streaming, File Search, Vector Store
By
–
1/🤖 OpenAI Assistant V2
— FlowiseAI (@FlowiseAI) 26 avril 2024
Assistants created on Flowise is now using V2 API, meaning its now supporting:
✅streaming
✅new file_search tool
✅vector store pic.twitter.com/5tqYEQuh6E1/ OpenAI Assistant V2 Assistants created on Flowise is now using V2 API, meaning its now supporting:
streaming
new file_search tool
vector store -
Flowise v1.6.6 launches Tool Agent for LLM function calling
By
–
With more LLMs supporting function calling, Flowise v1.6.6 is now updated with a new agent: Tool Agent This is a generalized tool calling agent by @langchain that is compatible with Mistral, Gemini, Claude, OpenAI, Groq. Other updates on v1.6.6