-
Notifications
You must be signed in to change notification settings - Fork 0
All issues
Issue creation is restricted in this repository
Issues
is:issue state:open
is:issue state:open
Search results
Retire the fixture-only eval model
enhancementNew feature or requestNew feature or requestStatus: Open.#266 In slowdini/eval-magic;Default codebase fixtures and shipped docs
documentationImprovements or additions to documentationImprovements or additions to documentationenhancementNew feature or requestNew feature or requestStatus: Open.#265 In slowdini/eval-magic;Skill sets as the treatment (multi-skill evals)
enhancementNew feature or requestNew feature or requestStatus: Open.#264 In slowdini/eval-magic;compare: paired evidence for interactive judging
enhancementNew feature or requestNew feature or requestStatus: Open.#263 In slowdini/eval-magic;Multi-sample judging (pass^k)
enhancementNew feature or requestNew feature or requestStatus: Open.#262 In slowdini/eval-magic;Bounded, diff-aware judge evidence bundle
enhancementNew feature or requestNew feature or requestStatus: Open.#261 In slowdini/eval-magic;- Status: Open.#245 In slowdini/eval-magic;
More realistic eval environment - full codebase testbed, multi-skill workflows
enhancementNew feature or requestNew feature or requestStatus: Open.#244 In slowdini/eval-magic;