Conversation

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().
Quote Tweet
Massive Update for Auto-GPT: Code Execution! 🤖💻 Auto-GPT is now able to write it's own code using #gpt4 and execute python scripts! This allows it to recursively debug, develop and self-improve... 🤯 👇
Show this thread
Embedded video
1:13
1.3M views
102
5,041
Interesting non-obvious note on GPT psychology is that unlike people they are completely unaware of their own strengths and limitations. E.g. that they have finite context window. That they can just barely do mental math. That samples can get unlucky and go off the rails. Etc.
8
480
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,… Show more
18
698
Show replies
We have barely scratched the surface of what GPT 4 can do. Iterative Multi-Agent Train-of-Thought systems are coming.
1
We are LLMs (Living Language Models) that evolved plug-ins for memory, sensory input, voice and motor skills. What stopped the cats?
1
1
Show replies
talked about 'Universal remote employees 10 years' from now, where how you can spin up AI-workers on cloud and give it task. I am guessing we will be there in 10 months from now??
Image