This experiment built a GPT-4 powered agent to play Red Dead Redemption 2, learning the gameplay from the initial tutorials. It does pretty well on the first couple of missions, the main limitation seems to be the GPT-4V vision system, which can struggle to understand everything
PROMPT ENGINEERING
-
Using Large Language Models: A Practical Series Guide
By
–
I have a series of posts about how I use them myself that might be useful https://
simonwillison.net/series/using-l
lms/
… -
Greatest Misconception: LLMs Complexity and Usability
By
–
That's my general view on all of this stuff now: the greatest misconception in LLMs is that the resulting tools are easy to use and to figure out
-
Copilot Training and Documentation Effectiveness in Organizations
By
–
Did your company spend any time teaching people how to use it effectively? (If they did I'd love to hear details – training and documentation on Copilot is incredibly rare in my experience – which is bad because the tool is very unintuitive to use well)
-
Aligning LLMs to Quote from Pre-Training Data
By
–
9/ Aligning LLMs to Quote from Pre-Training Data – proposes techniques to align LLMs to leverage memorized information quotes directly from pre-training data.
-
Iterative Self-Revision and Search for LLM Reasoning Tasks
By
–
6/ Reasoning with Intermediate Revision and Search – presents an approach for general reasoning and search on tasks that can be decomposed into components; incorporates iterative self-revision capabilities and allows an LLM to build an interwoven network of thoughts.
-
LM-Guided Chain-of-Thought Knowledge Distillation Technique
By
–
4/ LM-Guided Chain-of-Thought – applies knowledge distillation to a small LM with rationales generated by the large LM; the rationale is then generated by the lightweight LM and the answer prediction is done by the frozen large LM.
-
Using Large Language Models: A Year-Long Series Guide
By
–
A year later here's my series of posts about this https://
simonwillison.net/series/using-l
lms/
… -
Rethinking the Mental Model of AI Agents Today
By
–
I think people have the wrong mental model for what an agent does at this stage.
-
Creating Workflows Using Natural Language Only
By
–
We're making it possible to create these kind of workflows using only language! DM me if you'd like early access to @Lutra_AI