@aryaan_sheth · X

- LLM security for small teams

doantam · HN

I built a chat client that uses embeddings to cluster messages by topic

dkhcyx · V2EX

欢迎大家体验我做的发人深省，劝人向善的精品游戏 https://cassiangroup.uk/sewing/ https://cassiangroup.uk/salvate/ 最近 codex 重置太多了，蹬不完的 token 拿来蹬游戏了 期待大家荣登排行榜

loldle — 英雄联盟猜谜小游戏

@TRICKSTER_GAME3 · X

@asgujjuasitgets · X

@prof_safezone · X

Gambling on debate rounds with AI judges.

niklio · HN

You write 8 text completions and open models score how predictable each word was too them. Predictable => clanker. You can share results with your friends. The scoring checks every word you write against the model's logprobs. Right now I'm using Llama3.1, Deepseek v3 and Qwen3 to keep costs low. I tried to calibrate it so other models (chatgpt/claude) score 100% and interesting human responses score in the 10-30% range. Totally free, no signup

fcten · V2EX

做了一个大模型 leaderboard 网站 最近一个月 CodeX 疯狂送重置，token 根本用不完，顺手做点东西。 地址：[知行录]( https://leaderboard.cn/) 排行依据主要为模型官方基准测试成绩。非主观排名。 数据会持续更新。如果有点用，欢迎各位 v 友收藏～

@0xNftLegend · X

I built a game for $JAMES lovers. The Busy bull of Monad. Thanks @buildanythingso for inspiring me. My first Vibe Coded game. with no coding knowledge at all.

apoorvumang · HN

TokenPath – token-level citations for LLM output, read from attention

@GeorgeGognadze · X

Hi, I’m building the new chess version where mini games decide the capture @dualchess