alt Hacker NewsThere are ways around this. You can push the success rate close to 100% if you use chain of thought and a quorum selection. It isn't great, and it slows response times, but if 85% isn't good enough, you just need to flip the coin about 5 times to get nearly(!) guaranteed results.
Replies
spoj • yesterday at 6:04 AM
Coin flipping works only if the fails are roughly independent. More important is the complexity ceiling above which they fail all the time.
Good insight here, we actually did not include thinking into this model partly because we saw how incredibly fast it was to just get the minimum amount of tokens to output an answer.
Thinking helps performance scores but we'll leave it up to users to add additional tokens if they want. Our goal here was the leanest weight and token base for blazing fast performance for you all.