| ▲ | dttze 2 days ago |
| How is it supposed to learn to automate development by watching us not do things? Which is what the LLMs are used for currently. |
|
| ▲ | falcor84 2 days ago | parent [-] |
| Reinforcement learning - with vibe coding, it just needs us to give it the reward signal. |
| |
| ▲ | dttze 2 days ago | parent [-] | | So a bunch of people who can't code are going to train it? Or, rather, how will you know it is the right reward? Doesn't seem like a good way to train. | | |
| ▲ | falcor84 2 days ago | parent [-] | | Essentially they have paying customers upvoting the results they like and downvoting the ones they don't like. This is economics 101 for continuous improvement. | | |
| ▲ | bcoates 2 days ago | parent [-] | | That's a recipe for a tool that impresses the hell out of new/casual users but doesn’t work. It’s the same reason you should never choose an oncologist using yelp reviews. | | |
| ▲ | falcor84 2 days ago | parent [-] | | I don't understand the argument you're making. I'm grateful to have not had a need for an oncologist, but I would assume that honest reviews from patients whose cancer is either in remission or not should be relevant. What am I missing? | | |
| ▲ | bcoates a day ago | parent [-] | | Yelp reviews for doctors are all about how nice the doctors act and how much they tell the patients what they want to hear. It's not like people leave an "I died, 1 star" review. |
|
|
|
|
|
