Mika Ackermann retweeted
bymanan.com/blog/adaptive-…
A while ago, someone shared the Adaptive Patch Transformers paper in a group chat. The paper uses different patch sizes within the same image making the process dynamic. I genuinely could not stop thinking about it.
A while ago, someone shared the Adaptive Patch Transformers paper in a group chat. The paper uses different patch sizes within the same image making the process dynamic. I genuinely could not stop thinking about it.
1
1
5
416
Mika Ackermann retweeted
sharing an essay on the relation between compression and intelligence, in commemoration of Ray Solomonoff's 100th birthday greene.sh/compression-an…
8
41
383
43,020
Mika Ackermann retweeted
The Joy of Cryptography is now available for free online, in its entirety. joyofcryptography.com
Thanks to @mitpress for supporting open access.
Thanks to @mitpress for supporting open access.
2
108
379
22,670
Mika Ackermann retweeted
My first blog post in over a year is a deep dive on flow maps🗺️, or how to learn the integral of a diffusion model to enable faster sampling and several other cool tricks.
It's the longest one yet👀 Let me know what you think!
sander.ai/2026/05/06/flo…
It's the longest one yet👀 Let me know what you think!
sander.ai/2026/05/06/flo…
10
176
804
112,782
Mika Ackermann retweeted
From Qubit to Qubit: A Graduate Course in Quantum Mechanics arxiv.org/abs/2605.01585
6
60
375
24,848
Mika Ackermann retweeted
I am almost halfway through the semester, and this term I am teaching two heavy courses (60 hours each). One is about cryptanalysis: all the way from classical cryptology of substitution ciphers, through block ciphers, up to post-quantum cryptography.
The second course is a ro" introduction to neural networks, starting from the classic topics of the 1940s up to the transformer revolution.
I have decided to rely heavily on agentic tools to help me write lecture notes, slides, and interactive applets. It's a very systematic process where I give lectures, do exercises with students, and fine-tune the materials. I have noticed that the boost is incredible. Now we can really dive deep into the topics, adding a lot of custom-made help and examples (full Enigma breaking or high-level implementations in JAX). I see that the students enjoy having such complete notes.
I put a lot of effort into the structure and scaffolding of those notes. Many texts are generated from good sources, but I read every single page and apply corrections. I think I have saved a lot of hours on the tedious fine-tuning of pictures and examples. I also had the courage to test and cover much more experimental content that I had never explored before.
We spend three active hours each week with the students, and the work is very intense. But at the same time, the courses feel very rewarding, and I should admit that I have learned a ton (especially about the classic papers on AI). I will definitely keep building complete lecture notes for future courses, but I already see that the main issue is proper internalization of the knowledge, both by the students and by me. Overall, the process is much smoother because we can always ask an LLM to provide a more accurate answer.
The second course is a ro" introduction to neural networks, starting from the classic topics of the 1940s up to the transformer revolution.
I have decided to rely heavily on agentic tools to help me write lecture notes, slides, and interactive applets. It's a very systematic process where I give lectures, do exercises with students, and fine-tune the materials. I have noticed that the boost is incredible. Now we can really dive deep into the topics, adding a lot of custom-made help and examples (full Enigma breaking or high-level implementations in JAX). I see that the students enjoy having such complete notes.
I put a lot of effort into the structure and scaffolding of those notes. Many texts are generated from good sources, but I read every single page and apply corrections. I think I have saved a lot of hours on the tedious fine-tuning of pictures and examples. I also had the courage to test and cover much more experimental content that I had never explored before.
We spend three active hours each week with the students, and the work is very intense. But at the same time, the courses feel very rewarding, and I should admit that I have learned a ton (especially about the classic papers on AI). I will definitely keep building complete lecture notes for future courses, but I already see that the main issue is proper internalization of the knowledge, both by the students and by me. Overall, the process is much smoother because we can always ask an LLM to provide a more accurate answer.
17
54
697
121,862
Mika Ackermann retweeted
Boys play video games to let there inner child out
Girls do abortion
Girls do abortion
245
1,178
11,705
188,958
Mika Ackermann retweeted
100,000+ models trained with Unsloth have now been open-sourced on Hugging Face!
Popular fine-tuned LLMs you can run locally:
1. TeichAI - GLM-4.7-Flash distilled from Claude 4.5 Opus (high)
2. Zed - Qwen Coder 7B fine-tuned for stronger coding
3. DavidAU - Llama-3.3-8B .5 Opus (high)
4. huihui - gpt-oss made “abliberated”
Links to models:
1. TeichAI: huggingface.co/TeichAI/GLM-4.…
2. Zed: huggingface.co/zed-industries…
3. DavidAU: huggingface.co/DavidAU/Llama3…
4. huihui: huggingface.co/huihui-ai/Huih…
See all the 100K latest models fine-tuned with Unsloth here: huggingface.co/models?other=u…
Popular fine-tuned LLMs you can run locally:
1. TeichAI - GLM-4.7-Flash distilled from Claude 4.5 Opus (high)
2. Zed - Qwen Coder 7B fine-tuned for stronger coding
3. DavidAU - Llama-3.3-8B .5 Opus (high)
4. huihui - gpt-oss made “abliberated”
Links to models:
1. TeichAI: huggingface.co/TeichAI/GLM-4.…
2. Zed: huggingface.co/zed-industries…
3. DavidAU: huggingface.co/DavidAU/Llama3…
4. huihui: huggingface.co/huihui-ai/Huih…
See all the 100K latest models fine-tuned with Unsloth here: huggingface.co/models?other=u…
14
71
664
39,491
Mika Ackermann retweeted
Do you know that a man is the only mammal who can never be 100% sure his child is his?
A woman knows the baby is hers; it came out of her. A man has to take it on Faith.
This creates a deep, evolutionary anxiety called "Paternity Uncertainty.''
It is why men are so protective over their partners. It is why female infidelity hurts men differently than male infidelity hurts women.
For a woman, cheating is a betrayal of love. For a man, cheating is a betrayal of his legacy, tricking him into spending his life and resources raising another man's DNA. It is the ultimate biological theft.
Paternity fraud should be illegal and should be punishable by the law
A woman knows the baby is hers; it came out of her. A man has to take it on Faith.
This creates a deep, evolutionary anxiety called "Paternity Uncertainty.''
It is why men are so protective over their partners. It is why female infidelity hurts men differently than male infidelity hurts women.
For a woman, cheating is a betrayal of love. For a man, cheating is a betrayal of his legacy, tricking him into spending his life and resources raising another man's DNA. It is the ultimate biological theft.
Paternity fraud should be illegal and should be punishable by the law
419
3,316
32,306
2,669,191
Mika Ackermann retweeted
How to become expert at thing:
1 iteratively take on concrete projects and accomplish them depth wise, learning “on demand” (ie don’t learn bottom up breadth wise)
2 teach/summarize everything you learn in your own words
3 only compare yourself to younger you, never to others
1 iteratively take on concrete projects and accomplish them depth wise, learning “on demand” (ie don’t learn bottom up breadth wise)
2 teach/summarize everything you learn in your own words
3 only compare yourself to younger you, never to others
178
2,760
14,643
Mika Ackermann retweeted
there’s a specific kind of exhaustion that comes from always trying to understand others while no one tries to understand you back. it doesn’t make you angry. it just makes you quieter.
41
4,301
20,379
320,411
