TaskSpecific
-
Hackers News
Task-Specific LLM Evals that Do & Don’t Work
If you’ve ran off-the-shelf evals for your tasks, you may have found that most don’t work. They barely correlate with…
Read More »
If you’ve ran off-the-shelf evals for your tasks, you may have found that most don’t work. They barely correlate with…
Read More »