Dongyoon Hahm

Hahmdong

https://hahmdy.github.io

HahmDY

AI & ML interests

AI Safety

Recent Activity

upvoted an article 7 days ago

Security incident disclosure — July 2026

upvoted a paper 13 days ago

Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases

updated a model about 1 month ago

Hahmdong/SPUPER-qwen3-8b-sequowl-add-5ep

View all activity

Organizations

None yet

New activity in Qwen/Qwen2.5-7B 9 months ago

Update tokenizer_config.json

#11 opened 9 months ago by

Update tokenizer_config.json

#11 opened 9 months ago by