All of that is just one agent/thread. People coalesce into organizations so they can specialize and parallelize work towards shared goals. Imo this is likely to happen to AutoGPTs and for the same reasons, strung into AutoOrgs, with AutoCEO, AutoCFO, AutoICs, etc.
AGENTS
-
GPT Calls as Thoughts: Building Agents with Reflection and Memory
By
–
1 GPT call is a bit like 1 thought. Stringing them together in loops creates agents that can perceive, think, and act, their goals defined in English in prompts. For feedback / learning, one path is to have a "reflect" phase that evaluates outcomes, saves rollouts to memory,
-
Is AI Really Recursively Self-Improving Its Own Code?
By
–
Is it really recursively self-improving? So not just generating code, but also modifying its own code?
-
AutoGPTs: The Next Frontier of Prompt Engineering and AI Systems
By
–
Next frontier of prompt engineering imo: "AutoGPTs" . 1 GPT call is just like 1 instruction on a computer. They can be strung together into programs. Use prompt to define I/O device and tool specs, define the cognitive loop, page data in and out of context window, .run(). https://t.co/EKy84pa5bB
— Andrej Karpathy (@karpathy) 2 avril 2023Next frontier of prompt engineering imo: "AutoGPTs" . 1 GPT call is just like 1 instruction on a computer. They can be strung together into programs. Use prompt to define I/O device and tool specs, define the cognitive loop, page data in and out of context window, .run().
-
Agent AI Corrects Generated Programs Using Test Feedback
By
–
By patching you mean how the agent corrects the generated program? We get the feedback from the tests and feed it back to LLM, to make an intelligent decision on what needs to get fixed.
-
GoodAI Autonomous Agents Design Test Programs Autonomously
By
–
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
-
Twitter Bot for Paper Recommendations Using AI
By
–
I used it to make a Twitter bot that recommends me papers, but I kept ignoring the recommendations…
-
Training LLMs to Use Multiple LLMs as Tools
By
–
– 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?
-
GPT-4 Limitations: Long-term Planning and In-context Learning
By
–
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
-
Dialog-Enabled Resolving Agents Enhance LLM Clinical Task Performance
By
–
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.