top | item 46932687 (no title) imdsm | 22 days ago If we're able to produce an LLM which takes a seed and produces the same output per input, then we'd be able to do this discuss order hn newest layer8|21 days ago There must be good reasons why we don’t have this. I suspect one reason is that the SOTA providers are constantly changing the harness around the core model, so you’d need to version that harness as well.
layer8|21 days ago There must be good reasons why we don’t have this. I suspect one reason is that the SOTA providers are constantly changing the harness around the core model, so you’d need to version that harness as well.
layer8|21 days ago