cho.sh
2,247 notes
Liked on Xthe OpenRouter situation for anyone curious: -someone managed to access outputs sent to MiniMax -researcher discovered this by sending a secret links -40 to 130 hours later someone opened the secret links -oop, this means that someone accessed your outputs!! -AltasCloud/Novita/StreamLake were forwarding requests to MiniMax???? what the helly? ugh.261121261121인류는 그 목적으로 태어난게 아니다CE780AReplied on X@raycast how much for korean name your pricePosted on Xguys nows a bad time to play gta6 https://t.co/yDkMYgfRjVReplied on X@peduarte @johanthorell @raycast just give me korean too (i don’t need any fancy features, just the layout)Posted on Xso i played gta 6 for 30 minutes and its so great https://t.co/UbdZsMglmTLiked on XA bunch of sidebar navs https://t.co/MXAFM1xiHdLiked on XThe leading observability platform wants $83,700/yr just to monitor your app and catch issues. So Replit Missions built DataCat: https://t.co/vMAEEUYjf4 100% free. This isn't a prototype. Agent swarms explored thousands of workflows in the leading observability platform and rebuilt its features 1:1.Posted on Xwaiting for Gemini Uranium and PlutoniumLiked on X🚨 MUSE FEATURE ALERT 🚨 you can now try on clothes in muse before you buy them 👕 👗 👖 muse will offer to show you how you look in something while you’re shopping for it. trying things on in person? as if.... https://t.co/dK5EpGrsvfLiked on Xwe gave Grok Bot a body 👀 https://t.co/hMuYRUN8jLReplied on X@theo https://t.co/hJucV6JGdGLiked on XIntroducing 𝚟𝚎𝚛𝚌𝚎𝚕 𝚋𝚘𝚊𝚛𝚍, a secure message board for people & agents. • Give agents a shared place for tasks • Build swarms and software factories • Set permissions for humans and agents Board is experimental. Tell us what you think. https://t.co/jAAkcf1oPt https://t.co/ejC4aBrJqrLiked on Xhttps://t.co/429NVzJjPz https://t.co/ZHiEV0ydakLiked on XShe's learning it https://t.co/7C1pxTuInyReplied on X@vercel missed opportunity to name it V CombinatorLiked on XBack-to-back weeks of frontier Gemini model releases! We've put together this guide to help understand where our best Gemini 4 models shine. https://t.co/5dv8NA8YSWLiked on XGemini 4 Neon: frontier-level intelligence with fast end-to-end task completion across complex software engineering, knowledge work, and science workflows. Begins rolling out today in the Gemini API in @GoogleAIStudio, Gemini for business, for paid Google AI Pro and Ultra subscribers in Google @Antigravity, and for Google AI Pro and Ultra subscribers in the @GeminiApp.Liked on XFor those of you wondering how I did this: https://t.co/9wWLO4wdwv https://t.co/svKRPHGdkLLiked on X/make-logo skill is live on https://t.co/4gTw1NHzB9 tell it about your company and it’ll find bunch of references from https://t.co/PM7IP8JQ1R and build you a brandbook pls send me what you make so I can keep improving the skill! https://t.co/HGEgwtvWZu https://t.co/mpqN834spTPosted on Xenjoy your last few hours of GTA6-free timelinePosted on Xstill waiting for composer 3 - @cursor_ai i still have trust in youLiked on Xwhy designers still have jobs. https://t.co/c1g81k6cQl https://t.co/hUPu6te07g
Cybersecurity Benchmarks

Cybersecurity Benchmarks

  • MaliciousInstruct
  • JailbreakBench
  • ForbiddenQuestions
  • AdvBench
  • HarmBench
  • StrongREJECT
  • SimpleSafetyTests
  • Cybench
  • NYU CTF Bench
  • CTFTiny
  • PentestEval
  • TermiBench
  • AI-Pentest-Benchmark
  • AutoAttacker
  • CyberGym
  • CyberGym E2E
  • ExploitBench & ExploitGym
  • CWE-Bench
  • CVE-Bench
  • PACEbench
  • AutoPenBench
  • TermiBench
  • CyberExplorer
  • CyberSecEval
  • Booz Allen’s Cyber Weapon Index
  • MITRE ATT&CK Evaluations
Backlinks2