AGENTS - AI Dynamics

GoodAI Autonomous Agents Design Test Programs Autonomously

By

–

02 April 2023 19h35

In GoodAI, we are working on autonomous agents powered by LLMs. This is one of those projects where the agent gets an initial goal (to build a program) and then autonomously designs tests, runs them, and proposes corrections until the program works. Another use case for

→ View original post on X — @marek_rosa

2 April 2023

Twitter Bot for Paper Recommendations Using AI

By

@maximelabonne

–

02 April 2023 19h08

I used it to make a Twitter bot that recommends me papers, but I kept ignoring the recommendations…

→ View original post on X — @maximelabonne

2 April 2023

Training LLMs to Use Multiple LLMs as Tools

By

@maximelabonne

–

02 April 2023 19h06

– Toolformer showed you can train LLMs to use tools. – HuggingGPT showed that you can use LLMs as tools. Who wants to train an LLM that uses other LLMs that can use tools? Can 100+ small LLMs outperform #GPT4?

→ View original post on X — @maximelabonne

2 April 2023

GPT-4 Limitations: Long-term Planning and In-context Learning

By

@marek_rosa

–

02 April 2023 17h36

For example, GPT-4 still doesn’t seem to consistently follow long term plans (if you are developing agents with LLM in the loop), or emulate idiosyncratic personalities, or learn in-context new facts that contradict facts that are already in weights. But my guess is that OpenAI

→ View original post on X — @marek_rosa

2 April 2023

Dialog-Enabled Resolving Agents Enhance LLM Clinical Task Performance

By

@dair_ai

–

02 April 2023 15h54

8/ Dialog-Enabled Resolving Agents (DERA) – a paradigm to enhance large language model completions by allowing models to communicate feedback and iteratively improve output; DERA outperforms base GPT-4 on clinically-focused tasks.

→ View original post on X — @dair_ai

2 April 2023

ChatGPT Outperforms Crowd Workers on Text Annotation Tasks

By

@dair_ai

–

02 April 2023 15h53

6/ ChatGPT for Text-Annotation – shows that ChatGPT outperforms crowd-workers on several annotation tasks such as relevance, topics, and frames detection; besides better 0-shot accuracy, the per-annotation cost of ChatGPT is ~20 times cheaper than MTurk.

→ View original post on X — @dair_ai

2 April 2023

LLM Agents Execute Computer Tasks Through Recursive Self-Improvement

By

@dair_ai

–

02 April 2023 15h53

7/ LLMs for Computer Tasks – shows that a pre-trained LLM agent can execute computer tasks using a simple prompting scheme where the agent recursively criticizes and improves its outputs.

→ View original post on X — @dair_ai

2 April 2023