
TikTok Influencer Fake Views Audit: Build a Vetting Agent
Build a TikTok influencer fake views audit agent: pull a creator's recent posts, score each with a fake-view detector, aggregate in Python, then write a memo.
Read
Build a TikTok influencer fake views audit agent: pull a creator's recent posts, score each with a fake-view detector, aggregate in Python, then write a memo.
Read
Claude Code with other models benchmark: 11 models on SandBase, 6 Python repo tasks, 2 runs each, hidden tests. Pass rate, turns, time and list-price cost.
Read
Cheap LLM for AI agents benchmark: 22 models in 7 tier families, 17 tool tasks, 3 runs each. GPT-6 Luna scored 51/51 at about 1/20 of GPT-6.1 Sol's cost.
Read
Build a product review analysis agent for TikTok Shop and Xiaohongshu, then check its labels against 40 hand-labeled reviews: GPT-6 Luna vs GPT-6.1 Sol.
Read
Build a public opinion monitoring agent for Weibo, Zhihu and Bilibili, then test GPT-6 Luna vs GPT-6.1 Sol on 50 hand-labeled posts for accuracy and cost.
Read