|
| ▲ | mr_toad 4 minutes ago | parent | next [-] |
| > LLMs in general just love to hear themselves talk! Because that’s what’s in the training set. Reticent humans don’t have blogs. |
|
| ▲ | arjie 2 hours ago | parent | prev | next [-] |
| They do, and I want to encourage them to do so because they think through talking. What I don’t want to do is spend time reading all that. We will probably just get reader-side affordances for this like auto-folded justification and introduction sections and so on. Doubtless some chat interface will add this the way they’ve added reasoning folding. |
| |
| ▲ | bcrosby95 2 hours ago | parent [-] | | Thinking models think through talking, don't reveal that talking, then answer by again thinking through talking. It's kinda funny in a way. |
|
|
| ▲ | jimbokun 2 hours ago | parent | prev [-] |
| Is it just a coincidence that the companies creating them charge by the token? |
| |
| ▲ | pizzafeelsright 2 hours ago | parent [-] | | The aligned incentive appears to be realigning in favor of the corporation. Pray they do not realign them further. There are times I require single word answers. I will use whatever model responds as I desire and at this point those models are just a few. | | |
| ▲ | minimaxir an hour ago | parent [-] | | The cost-per-task benchmarks align incentives toward more efficient output and those are the ones gaining steam. |
|
|
