TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Spawning AGI Systems

2 pointsby dalyover 1 year ago
There was a story that came around about someone who &quot;cloned&quot; the Angry Birds game just by interacting with a GPT system. The GPT system spit out the code, the person would run it and then interact with the GPT to improve it. I presume the GPT was using a language like Python or other traditional text-based language for the implementation. Humans could understand the code.<p>Now lets assume that the GPT system created a &quot;spawn of GPT&quot; system that was a newly formed neural network. The user interacts with the &quot;parent GPT&quot; giving feedback. The parent creates input to the spawn and uses reinforcement learning to &quot;fix&quot; the spawns behavior to match the required output.<p>Note that, while the goal was achieved, a human could not understand the result.<p>This is the most likely future.<p>I&#x27;ll have to play with this idea.

1 comment

smoldesuover 1 year ago
A few thoughts. For starters, multiple AIs working together (or even against each other) to create an output is not a new thing. Adversarial networks are already pretty common in image-generation to discriminate against ugly or incorrect outputs. In those systems, the generation model competes with a discriminator model that demands higher-quality output.<p>That being said, my understanding is that this approach is quickly being obsoleted by zero-shot solutions instead. Running multiple models is extremely undesirable because it potentially doubles the scope, latency and cost of your system. In your example, I&#x27;d imagine such a system would be outperformed by a single model that does both the parent and the spawn&#x27;s job.
评论 #38247538 未加载