Re:LLMs as the new high level language
by imdsm on Sunday February 08, 2026 @04:12AM
(#46932687)
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
[ Parent
| on HN ]
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.