ExploitGym
1 statements across 1 episodes · 0 bullish · 0 bearish · 1 people on the record · first statement Jul 23, 2026 by Jordi Hays · said 1 times in 1 episodes since 2026 · across every show →
Mentions by year
brought up most by Jordi Hays (1)
tap a year for its mentions
Everything said about ExploitGym, oldest first
Jul 23, 2026 neutral
Claude Mythos and GPT-5.5 score 20% and 15% on ExploitGym benchmark
“Claude Mythos preview successfully exploited a 157 of the 898 instances, and OpenAI's GPT 5.5 exploited one 20 within, ah, 120 of the eight 98, so you have, like, roughly 20% performance for Mythos, and 5.5 got, like, 15% or something like that, but whenever y…”