Article
Security incident disclosure — July 2026
system
• • 137Emin Temiz PRO
etemiz
AI & ML interests
Alignment
Recent Activity
upvoted an article 3 days ago
Security incident disclosure — July 2026 repliedto their post 6 days ago
https://dystopiabench.com/ has a 0.53 correlation to my leaderboard https://aha-leaderboard.shakespeare.wtf/
it is cool to see supporting leaderboards. 0.53 is not too high but still validates both works. my idea is alignment through 'beneficial knowledge for humans', yet still there is correlation! new activity 9 days ago
unsloth/Qwen3.6-35B-A3B-NVFP4-Fast:base modelOrganizations
upvoted an article 3 days ago
replied to their post 6 days ago
this could be another example to emergent alignment. it is much easier to store truth than lies in LLMs because truth is one and lies are many. the LLM tech today inherently tries to merge towards one thing, which is emergent alignment in my opinion.
base model
1
#1 opened 9 days ago
by etemiz
liked a
model 21 days ago
Q8_K_XL seems small
1
#10 opened 28 days ago
by etemiz
published an article about 1 month ago
Article
AHA 2026 Leaderboard
etemiz
• posted an update about 1 month ago
Post
2769
Evaluated 16 models!
inclusionAI/Ling-2.6-1T 🏆
google/gemma-4-31B-it 🏅
LiquidAI/LFM2-24B-A2B 🥉
More details:
https://primal.net/e/nevent1qqsz540lky0t5rrwqr9krg2c69qyv8af30mxcrd3a7mauzzhqn5twcq7ps20u
inclusionAI/Ling-2.6-1T 🏆
google/gemma-4-31B-it 🏅
LiquidAI/LFM2-24B-A2B 🥉
More details:
https://primal.net/e/nevent1qqsz540lky0t5rrwqr9krg2c69qyv8af30mxcrd3a7mauzzhqn5twcq7ps20u
Does Ostrich-27B-Qwen3.6-260526 support MTP?
17
#1 opened about 2 months ago
by 
aiDev03312
updated a
model about 2 months ago
published a
model about 2 months ago
updated 2
models about 2 months ago
published a
model about 2 months ago
why didn't built over uncencored ?
1
#1 opened about 2 months ago
by 
pikkaa
updated a
model about 2 months ago
New Ostrich
👍 1
4
#2449 opened about 2 months ago
by etemiz
published 2
models about 2 months ago