I asked both Fable and Sol to work on the same code base. Then I had both Fable and Sol review each other's code blindly. The results may surprise you. t.co/4xn6XVGkpY
Methodology for comparing LLM output quality blindly
🔖 0♥ 3↩ 0👁 501mo ago
170170 of 1000 · Under 1k followersReach3×0 bookmarks + 2×0 quotes + 1.5×0 replies + 3 likes = 3, against a cap of 300 for this league146/600Per viewer0.3% of 50 viewers did something; 5% is full marks25/400Bookmarks weigh most because people save what they intend to reuse. Every part saturates.hide
Bookmarks0
Likes3
Replies0
Quotes0
Views50
LeagueUnder 1k followers
Open on X · Boost ♥ · Permanent page
Filed under AI by the model because: Methodology for comparing LLM output quality blindly. The rules.