Benjamin Dover π€π€π΄ββ οΈπ§ retweeted
Want to see the difference in answers between a Qwen model as is, and with its Chinese-state alignment removed?
I recorded this quick video to see how the two models answer questions about Taiwan and the Tiananmen Square incident, and the difference is stark
What is Arete-27B?
A post-train of Qwen3.8-27B by Nous Research aimed at stripping out Chinese state-aligned bias
They trained it on ~20k prompts across 7 value categories (free expression, democracy, surveillance, etc.) with Inkling as the teacher model. Plain SFT, 2 epochs, ~53M tokens. No RL, no preference tuning
The result? Answers containing propaganda dropped from 22% to 1%. Factual recall went from 2.32 to 2.98 out of 5. Hermes Bench was basically unchanged (65.6% vs 65.8%)
The big insight is how shallow the bias layer turned out to be, and how late it is applied in the training. About 50M tokens of supervision removed most of it without hurting capability
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 Chinaβs 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
Benjamin Dover π€π€π΄ββ οΈπ§ retweeted
Last quarter I rolled out Microsoft Copilot to 4,000 employees.
$30 per seat per month.
$1.4 million annually.
I called it "digital transformation."
The board loved that phrase.
They approved it in eleven minutes.
No one asked what it would actually do.
Including me.
I told everyone it would "10x productivity."
That's not a real number.
But it sounds like one.
HR asked how we'd measure the 10x.
I said we'd "leverage analytics dashboards."
They stopped asking.
Three months later I checked the usage reports.
47 people had opened it.
12 had used it more than once.
One of them was me.
I used it to summarize an email I could have read in 30 seconds.
It took 45 seconds.
Plus the time it took to fix the hallucinations.
But I called it a "pilot success."
Success means the pilot didn't visibly fail.
The CFO asked about ROI.
I showed him a graph.
The graph went up and to the right.
It measured "AI enablement."
I made that metric up.
He nodded approvingly.
We're "AI-enabled" now.
I don't know what that means.
But it's in our investor deck.
A senior developer asked why we didn't use Claude or ChatGPT.
I said we needed "enterprise-grade security."
He asked what that meant.
I said "compliance."
He asked which compliance.
I said "all of them."
He looked skeptical.
I scheduled him for a "career development conversation."
He stopped asking questions.
Microsoft sent a case study team.
They wanted to feature us as a success story.
I told them we "saved 40,000 hours."
I calculated that number by multiplying employees by a number I made up.
They didn't verify it.
They never do.
Now we're on Microsoft's website.
"Global enterprise achieves 40,000 hours of productivity gains with Copilot."
The CEO shared it on LinkedIn.
He got 3,000 likes.
He's never used Copilot.
None of the executives have.
We have an exemption.
"Strategic focus requires minimal digital distraction."
I wrote that policy.
The licenses renew next month.
I'm requesting an expansion.
5,000 more seats.
We haven't used the first 4,000.
But this time we'll "drive adoption."
Adoption means mandatory training.
Training means a 45-minute webinar no one watches.
But completion will be tracked.
Completion is a metric.
Metrics go in dashboards.
Dashboards go in board presentations.
Board presentations get me promoted.
I'll be SVP by Q3.
I still don't know what Copilot does.
But I know what it's for.
It's for showing we're "investing in AI."
Investment means spending.
Spending means commitment.
Commitment means we're serious about the future.
The future is whatever I say it is.
As long as the graph goes up and to the right.
Benjamin Dover π€π€π΄ββ οΈπ§ retweeted
The Premier League table if it was based on how many minutes walk to the nearest strip club
Konstaterer at #nff ikke akkurat legger opp til at folk fra distriktene skal fΓ₯ se landskamp. Kampene er utsolgt fΓΈr billettsalget starter.
28
Benjamin Dover π€π€π΄ββ οΈπ§ retweeted
π¨BREAKING: Trumpβs voter fraud speech is BACKFIRING as Americans flood social media with the recording of Trump demanding Georgia βfind 11,780 votesβ after he lost the 2020 election.
Trump is the last person on Earth who should be talking about election fraud.
UEFA statement on the Balogun case: β¬οΈ
uefa.com/news-media/news/02aβ¦
NΓ₯ folk begynne Γ₯ puste med magan. Det bΓ₯let her trenger ikke mer bensin nΓ₯. β½οΈπ€π€
1
2
60





















