Pinned Tweet
Once you realize there is intentionally unpatched glitches in capitalist societies, you will have all the motivation you need.
Whats that uhh printer mfks talkin about? like a special printer. you can literally print anything or sum like thatđź—ż
BREWcultist🔸 retweeted
Replying to @yourcryptodj
It's fucking $shiit, you don't have to believe me, dyor.
BREWcultist🔸 retweeted
Replying to @TimxTaler @yourcryptodj
Already in reverse after whole market was crashing. Next lvl ai $shiit
Santa, all i want for christmas is solana:412ECWXN3jGbd1kn8ck7eeupWttkmrFkNm9JqfAzpump and BREW tokens santađź—ż
BREWcultist🔸 retweeted
solana:412ECWXN3jGbd1kn8ck7eeupWttkmrFkNm9JqfAzpump heads we need to get to train our own based chinese model levels of success.
Don't let me down.
Introducing Arete-27B: Qwen3.8-27B, post-trained to reinforce Western values.
Chinese open models are currently the strongest available, but they ship with state-aligned behavior in the weights. We built an 803-prompt eval across seven value categories, including freedom of expression, democracy, and privacy, and measured how often a model adopts China’s party line.
After fine-tuning on roughly 53 million tokens, Arete-27B's propaganda rate fell from 22% to 1%, in line with the Western models we tested. Its Hermes Bench score shows no significant performance tradeoffs.
The values in an open model are one fine-tune away.
Our eval, weights, and training data are available now along with the full blog post: nousresearch.com/arete
BREWcultist🔸 retweeted
GOOD AFTERNOON solana:412ECWXN3jGbd1kn8ck7eeupWttkmrFkNm9JqfAzpump HEADS!!!
If you wait for me to tweet about each update you missed 0.13.1 and 0.14.0.
I also just pushed 0.14.1
These updates have a big focus on ease of getting started in the ecosystem.














