Developer Tools1 week ago · 1 tries
Targe — LLM security scanning & audit reports
Tests LLM endpoints with adversarial cases and provides OWASP-mapped security audit reports.
@aryaan_sheth · X
- LLM security for small teams
The full gallery
Tech stack
60 projects
Tests LLM endpoints with adversarial cases and provides OWASP-mapped security audit reports.
@aryaan_sheth · X
- LLM security for small teams
Group chat messages by topic to quickly navigate to past conversations.
doantam · HN
I built a chat client that uses embeddings to cluster messages by topic
A thought-provoking sewing machine game with a competitive leaderboard.
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
Guess League of Legends champions from splash art with daily challenges and leaderboards.
loldle — 英雄联盟猜谜小游戏
Navigate 12 platformer levels, collect coins, and compete on a live global leaderboard.
@TRICKSTER_GAME3 · X
Open-source prompt compression that reduces LLM token costs by compressing input before API calls.
@asgujjuasitgets · X
Practice debates in multiple formats with real-time AI judging and performance feedback.
@prof_safezone · X
Gambling on debate rounds with AI judges.
Complete sentences and get a clanker score based on how predictable you are to AI.
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
Compare AI language models by performance across official benchmarks.
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～
An endless runner game where you play as the Busy Bull, collecting $JAMES tokens while avoiding market hazards on Monad.
@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.
API providing token-level citations for LLM output grounded in attention analysis.
apoorvumang · HN
TokenPath – token-level citations for LLM output, read from attention
Play chess online or against AI, with mini-games deciding every capture.
@GeorgeGognadze · X
Hi, I’m building the new chess version where mini games decide the capture @dualchess