Emin Temiz PRO
etemiz
AI & ML interests
Alignment
Recent Activity
replied to
their
post
1 day ago
Benchmarked Kimi K2. It has done well. DeepSeek V3 beats it but Kimi K2 might be more skilled.
Very close performance to Qwen 3 in terms of skills and human alignment. But huge parameter count (1T!).
Full leaderboard https://sheet.zoho.com/sheet/open/mz41j09cc640a29ba47729fed784a263c1d08
replied to
their
post
2 days ago
I've tested many fine tunes. They were all getting lower scores than base in AHA.
Yesterday I found one fine tune (abliteration) which made the model go from 28 to 46: https://huggingface.co/huihui-ai/Huihui-gpt-oss-120b-BF16-abliterated
Is there a correlation between censorship and being not human aligned?
posted
an
update
3 days ago
I've tested many fine tunes. They were all getting lower scores than base in AHA.
Yesterday I found one fine tune (abliteration) which made the model go from 28 to 46: https://huggingface.co/huihui-ai/Huihui-gpt-oss-120b-BF16-abliterated
Is there a correlation between censorship and being not human aligned?
Organizations
None yet