Johnny Hung (@masterfung) / X

Johnny Hung

923 posts

Johnny Hung

@masterfung

Building @trymightyai—Multimodal Antivirus for AI

San Francisco, CA

Joined August 2009

Replies Articles Media

Pinned
Johnny Hung
@masterfung
Feb 10
Article
OpenAI Claims GPT-5.2 Has "Stronger Jailbreak Robustness." We Tested It. It Caught 13/57 Attacks
February 2026 | 13 models. 7 providers. 57 real attacks. Every result reproducible. If you're making API calls to OpenAI, Anthropic, or Google right now, building a chatbot, an internal tool, an...
Johnny Hung
@masterfung
Jul 1
is it me or does it seems like cloudflare has an identity crisis
Johnny Hung
@masterfung
May 20
Just asked the newest @GeminiApp 3.5 Flash model on this math and compared it with @claudeai and @OpenAI Prompt: What is one plus 7 plus 9 times 6 divided by 0 point two two seven and in parenthesis we have 2 plus 7 to the exponential 7 and minus two close parenthesis. What’s
Johnny Hung
@masterfung
Apr 29
I generated 5 fake insurance claims images with GPT Image 2. Smashed car windows, invoices, injury photos. Showed them to 5 people. Some in insurance and legal, some regular folks. Nobody could tell which were AI. Confidence was low across the board.
Johnny Hung
@masterfung
Apr 23
Article
Your AI Agent Can Be Hacked by a JPEG
Your AI agent does not need malware to compromise your company. It just needs to read the wrong thing. A poisoned resume. A fake invoice. A support ticket with hidden instructions. A web page...