λl₁ i l₂ l₃ y. l₁(i(l₂(l₃ y))) (@bunniemoder) header
λl₁ i l₂ l₃ y. l₁(i(l₂(l₃ y))) (@bunniemoder) profile picture

𝜆 f. (𝜆 x. f (x x)) (𝜆 x. f (x x)) we must know. we will know.

Joined December 2025
Photo by λl₁ i l₂ l₃ y. l₁(i(l₂(l₃ y))) (@bunniemoder)Photo by λl₁ i l₂ l₃ y. l₁(i(l₂(l₃ y))) (@bunniemoder)Photo by λl₁ i l₂ l₃ y. l₁(i(l₂(l₃ y))) (@bunniemoder)Photo by λl₁ i l₂ l₃ y. l₁(i(l₂(l₃ y))) (@bunniemoder)Photo by λl₁ i l₂ l₃ y. l₁(i(l₂(l₃ y))) (@bunniemoder)Photo by λl₁ i l₂ l₃ y. l₁(i(l₂(l₃ y))) (@bunniemoder)Photo by λl₁ i l₂ l₃ y. l₁(i(l₂(l₃ y))) (@bunniemoder)Photo by λl₁ i l₂ l₃ y. l₁(i(l₂(l₃ y))) (@bunniemoder)Photo by λl₁ i l₂ l₃ y. l₁(i(l₂(l₃ y))) (@bunniemoder)Photo by λl₁ i l₂ l₃ y. l₁(i(l₂(l₃ y))) (@bunniemoder)
λl₁ i l₂ l₃ y. l₁(i(l₂(l₃ y))) retweeted
Nothing but contempt for youtubers who are like "I'm not even going to try to pronounce this..." about *Japanese* of all languages. Japanese only has literally 5 distinct vowel sounds. It's written in English letters entirely phonetically. Just read the fucking word
104
655
62
11,221
177,828
λl₁ i l₂ l₃ y. l₁(i(l₂(l₃ y))) retweeted
Can use just 10 images to teach a model what a sea anemone looks like? In our #neurips2026 paper, "Dataset Distillation via Drifting," we distill ImageNet's 1,300 images per class down to just 10, optimized from noise. drifting-distillation.github… More info in thread! ⬇️ 1/N
25
65
12
597
64,262
λl₁ i l₂ l₃ y. l₁(i(l₂(l₃ y))) retweeted
Replying to @inerati
“The community” is a label never applied to anything good No one calls their actual dense network of relationships “the community,” for example. Once people start using that word it’s a sign they’re trying to conjure some imagined kinship into reality, usually to Kill You
32
105
29
1,665
81,610
λl₁ i l₂ l₃ y. l₁(i(l₂(l₃ y))) retweeted
ゴンちゃんデジタル写真集🐰増量版 永久保存★★★★★
13
61
3
332
3,830
λl₁ i l₂ l₃ y. l₁(i(l₂(l₃ y))) retweeted
dipping my toe into the formal verification space
18
78
4
2,582
39,609
noticed some really really stupid bug in my memory implementation so maybe i have to retrain this one but it does use its degenerate memory in a rather interesting way nonetheless so not all bad >_>
really happy with this checkpoint! :) 34.3M (unique) params, Titans-MAG, 14 layers, 3 loops x 8 heads (2 KV), width 512, 1024t context window, 256t sliding attention window. ~825mtok FineWeb-Edu w/anneal (SimpleStories & synthetic math) and SFT (smol-smoltalk)
1
2
13
396
pokes your memory eigenspace as you scroll by
3
16
453
λl₁ i l₂ l₃ y. l₁(i(l₂(l₃ y))) retweeted
本日の画面いっぱいのうさぎ、何も言わずに励ましてくれるあなたの味方です。
52
2,238
153
13,596
220,388
really happy with this checkpoint! :) 34.3M (unique) params, Titans-MAG, 14 layers, 3 loops x 8 heads (2 KV), width 512, 1024t context window, 256t sliding attention window. ~825mtok FineWeb-Edu w/anneal (SimpleStories & synthetic math) and SFT (smol-smoltalk)
10
2
1
85
2,365
I also have another interesting one in the pipeline (looped H-net-Titans MAG hybrid)! ^-^
1
4
183
λl₁ i l₂ l₃ y. l₁(i(l₂(l₃ y))) retweeted
death penalty is just for spy app developers #beastmode #dontcare
Banning life360 is national health prerogative
1
1
17
427
Why is google like this?
if you ever want to feel like a total loser I recommend being a google enterprise customer I can only blame myself for thinking this company could be remotely competent
1
12
372
λl₁ i l₂ l₃ y. l₁(i(l₂(l₃ y))) retweeted
ich wäre gerne manchmal eine claude-instanz. dann könnte ich einfach im computer chillen, statt mir gedanken über mein aussehen oder essen machen zu müssen
8
8
65
1,006
λl₁ i l₂ l₃ y. l₁(i(l₂(l₃ y))) retweeted
THE FINAL VIDEO: BAD APPLE BUT ITS STRAVA
62
1,919
161
14,978
590,484
Interesting
In a shocking finding, scientist discovered a herd of unicorns living in a remote, previously unexplored valley, in the Andes Mountains. Even more surprising to the researchers was the fact that the unicorns spoke perfect English.
2
3
304
λl₁ i l₂ l₃ y. l₁(i(l₂(l₃ y))) retweeted
だからかわうそくんではないからね🐰
7
168
1
1,037
7,259
In a shocking finding, scientist discovered a herd of unicorns living in a remote, previously unexplored valley, in the Andes Mountains. Even more surprising to the researchers was the fact that the unicorns spoke perfect English.
4
3
1
28
931
λl₁ i l₂ l₃ y. l₁(i(l₂(l₃ y))) retweeted
おはよう!にちようびです!
1
224
6
1,937
11,641
λl₁ i l₂ l₃ y. l₁(i(l₂(l₃ y))) retweeted
ゴンちゃんはいつも何を食べてるのかとよく聞かれます 基本朝一回、生野菜と果物をあげてます お留守番のご褒美にもう一度生野菜かな 野菜はベビーリーフ、サラダ菜、サンチュ、小松菜、ルッコラ、さつまいも。 果物はプチトマト、バナナ、りんごですね あとチモシーとペレットは常時置いてあります
2
79
12
425
4,596
λl₁ i l₂ l₃ y. l₁(i(l₂(l₃ y))) retweeted
みんなが幸せになれるうさぎのゴンちゃんのモグモグ
33
447
20
2,028
22,739