Mikhail Seleznev

myyycroft

·

Dont-Care-Didnt-Ask

AI & ML interests

NLP, AI Safety

Recent Activity

upvoted a paper about 20 hours ago

LLMs are General Asynchronous Agents

upvoted a paper 2 days ago

Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs

updated a collection about 2 months ago

Gemma 4 AmbigQA — OFT

View all activity

Organizations

myyycroft 's papers 4

arxiv:2508.11383

arxiv:2412.09565

arxiv:2411.13211

arxiv:2406.14553