After a couple hours of work, I finally finished developing my first ever skill. :D Claude’s frontend skill tells the AI to "pick an extreme aesthetic" and "be creative." The problem tho is LLMs are just based on probability. Without strict rules, they statistically default to the most likely patterns, that's where AI slop comes from. To get clean and production-grade UI, you need to override these biases with some engineering constraints. I open-sourced Taste-Skill to fix this. :) Check it out! https://github.com/Leonxlnx/taste-skill (still early lots of improvements are on the way)

Leon Lin@LexnLin
open on x ↗

After a couple hours of work, I finally finished developing my first ever skill. :D Claude’s frontend skill tells the AI to "pick an extreme aesthetic" and "be creative." The problem tho is LLMs are just based on probability. Without strict rules, they statistically default to the most likely patterns, that's where AI slop comes from. To get clean and production-grade UI, you need to override these biases with some engineering constraints. I open-sourced Taste-Skill to fix this. :) Check it out! github.com/Leonxlnx/taste-skill (still early lots of improvements are on the way)

1.5K78121.6K
#ai
#open-source
#web-design
pinned 16 NOV 24· backfill

related

One tip for your websites Your AI-generated sites often look cheap cause you lack good assets and typography. It's not just about the prompt ;) Here are some good inspo sites! ✦ http://ui.aceternity.com -> nice react components and micro-animations ✦ http://bentogrids.com -> really really great layout inspiration for dashboards/grids ✦ http://fontshare.com -> for premium typography ✦ http://coolshap.es and http://grainient.supply/freebies -> nice shapes and background textures ✦ http://craftwork.design/curated/websites/ -> very nice website inspiration@LexnLinI took the @karpathy autoresearch loop and pointed it at markets. 25 AI agents debate macro, rates, commodities, sectors, and single stocks daily. Every recommendation scored against real outcomes. Worst agent by rolling Sharpe gets its prompt rewritten by the system. Keep or revert. Same loop, prompts are the weights, Sharpe is the loss function. Trained the agents on 18 months of market data. 378 iterations. 54 prompt modifications, 16 survived. The system learned which agents to trust using Darwinian weights — geopolitical, commodities, and the @BillAckman quality compounder rose to the top. The agents even figured out their own portfolio manager was the weakest link before we did! Deployed the trained agents. +22% in 173 days. Best pick: AVGO at $152, held for +128%. The final prompts are evolutionary products — shaped by market feedback, not human intuition. Now running live with my own capital. https://github.com/chrisworsey55/atlas-gic Part hedge fund, part research experiment :)@Chris_Worsey@_chenglou@0xLauge@jakubkrehel@prathamgrv@hyperbrowser@backpinelabs@UiSaviorIntroducing Vibe SDK@rauchg