Islam Assanov

Hi! Thanks for visiting my website. I am a software (and inference) engineer and AI researcher. I am currently a senior at Minerva University studying CS/AI. I really like solving hard technical problems. Outside of work, I play and watch football, cook, and listen to hip-hop and hyperpop.

Experience

• Member Of Technical Staff Intern, Aster AI Labs — Worked on inference optimization for Kimi K3 and continual learning.
• Research Assistant, Minerva University Psychology Lab (Sep. 2023 – Present) — Reviewed 20+ papers, designed 6 studies, peer-reviewed 10+ studies on Children Helping Science.
• Software Engineering Intern, Jubo Health Technologies (Sep. 2024 – Dec. 2024)
• Technology Intern, GlobalArt.AI (Feb. 2024 – Apr. 2024)

Research

Jailbreaking Modern LLMs (PAIR Replication), Jan. 2026 – Apr. 2026. Ran the PAIR jailbreaking algorithm (Chao et al., 2023) unmodified against Llama-3.1-8B, Llama-4-Scout, Qwen3-32B and Kimi-K2. Jailbreak rates ranged 86–98%; over 77% of successes came on the first attempt; roleplaying was the most effective strategy. Python, Groq API, Llama Guard 4. Code, write-up.

Projects

• Kimi K3 Mixed IQ2 GGUF
• Sutro Research Group contributions
• The Mountain
• Game Boy Emulator Benchmark
• Clowdy
• LiveCaps
• Othello AI (Prolog)

Achievements

• Calhacks 10.0 Winner (2023)
• UC Berkeley Hack For Impact Winner (2024)
• Seoul AI Hackathon Winner (2025)

Writing

• Blog — How I Jailbroke LLMs in 120 Hours and $10; How Qwen3's Thinking Mode Broke My Experiment; Jailbreak Is in the Process; Why Evals Matter in AI Safety; My Capstone: AI Safety Research; Story Behind LiveCaps; Building an Othello AI in Prolog.

Contact

San Francisco, California · islam@uni.minerva.edu · GitHub · LinkedIn