GPT literally generates perfect code for me in languages that do not exist anywhere in its training set, so I’m not sure how you’ve achieved this level of failure.
Ever since the first Davinci model of GPT-3 ive literally been using LLMs daily. It was an indispensable tool for me from the very beginning and despite 10,000+ hours of usage and research, I still feel like ive barely cracked the surface of whats possible with current genai tech.
When I use AI to produce a work, it’s human-made, just the same as when I use a computer to synthesize digital works using human-developed automation tools like word processors. All built on top of operating systems that manipulate bytes of all natural human-made data.
It really sounds like you’re doing it wrong (using multi-agent patterns of yesteryear).
The proper way is to use multiple agents for work involving very large context, and splitting the context amongst them. It effectively enables encapsulation and separation of concerns, which yields much clearer benefits when working at scale.
This is my experience. Though ice been writing LLM harnesses, agents, tooling, etc for 5 years now and believe it requires several hundred hours of experience before understanding how to consistently outperform at scale.
What would you even need to see? I struggle to find things that I cant do at scale with AI, and it’s dumbfounding to read posts about people that are unconvinced.