papee (@wethmedaddy) header
papee (@wethmedaddy) profile picture

📌 list of videos I watch while I poop at work .

Joined January 2021
Photo by papee (@wethmedaddy)Photo by papee (@wethmedaddy)Photo by papee (@wethmedaddy)Photo by papee (@wethmedaddy)Photo by papee (@wethmedaddy)Photo by papee (@wethmedaddy)Photo by papee (@wethmedaddy)Photo by papee (@wethmedaddy)Photo by papee (@wethmedaddy)Photo by papee (@wethmedaddy)
Boondocks Pin📌
The Вооndосkѕ (a thread of the complete series)
19
2
31
24,148
i just started watching The Bear, I love it .
22
papee retweeted
34
101
6
4,573
69,183
papee retweeted
Local AI is for everyone 🚀
I think we might have something cooking here 🚀 optimize it a little more for faster processing. M3 Ultra GLM-5.3 8-bit
3
1
34
2,212
Replying to @rawsalerts
Mathematicians "just watching" from the chair in the corner.
8
25
2,525
75,289
papee retweeted
Replying to @rawsalerts
8
24
3
446
36,506
papee retweeted
"Cuckulus" "Cuckulations" "Cuckulator" "According to my cuckulations"
🚨 #BREAKING: Mathematicians conflicted over the emerging field of “cuckulus” whereby mathematicians prompt AI to solve unsolved problems while they just sit back and watch.
91
5,344
68
61,845
772,687
papee retweeted
We worked with @thinkymachines to make Inkling 2 Mini run fast locally: - 210 tok/sec decode, 3620 tok/sec prefill on 96GB M5 Ultra Mac Studio - 125 tok/sec decode, 1750 tok/sec prefill on 48GB M5 Max MacBook Pro It built a native weather app 1.8x faster than Claude Sonnet 5.5 on an M5 Ultra Mac Studio and 11x cheaper (API pricing). The looping architecture is ideal for local devices like MacBooks, which are memory constrained. Looping layers of the model increases inference-time compute (and intelligence) without increasing the size of the model.
Some of you thought that Inkling 2 Small was too big at 594B parameters. We heard you: Inkling 2 Mini is a looped transformer with just 26B parameters, small enough to run on your laptop, powerful enough for agentic work with a score of 20.1 on AA Index. thinkingmachines.ai/news/ink…
126
219
78
2,792
431,990
bak bu doğruysa 1 sene içinde opus 5.5 seviyesi modeller m5 ultra baz modelde mümkün olacak test ediyorum benim m5 pro 48gb ramde
We worked with @thinkymachines to make Inkling 2 Mini run fast locally: - 210 tok/sec decode, 3620 tok/sec prefill on 96GB M5 Ultra Mac Studio - 125 tok/sec decode, 1750 tok/sec prefill on 48GB M5 Max MacBook Pro It built a native weather app 1.8x faster than Claude Sonnet 5.5 on an M5 Ultra Mac Studio and 11x cheaper (API pricing). The looping architecture is ideal for local devices like MacBooks, which are memory constrained. Looping layers of the model increases inference-time compute (and intelligence) without increasing the size of the model.
11
1
154
18,462
Google Maps on iPhone vs Android Absolutely EMBARRASSING…
216
259
67
14,019
5,045,072
papee retweeted
Inkling 2 Mini from @ThinkyMachines 🇺🇸 is now on Ollama with 0.40.17 (available in pre-release) Small enough to run on a Mac with 32GB+ memory. Each token loops through its middle layers three times so it reasons deeper at just 5.4B active parameters. Built for coding, agentic workflows such as, computer use, design with strong visual reasoning, and finance tasks. Here’s Inkling 2 Mini playing 2048 by making decisions in real-time 💨 Run it with Ollama fully locally: ollama run inkling-2-mini Run it in Pi: ollama launch pi --model inkling-2-mini
49
57
15
763
69,889
We took Inkling 2 Mini with us on a plane with no wifi and had it build a flight simulator, running entirely locally on my Mac. ✈️ Try Inkling 2 Mini on your laptop!
Some of you thought that Inkling 2 Small was too big at 594B parameters. We heard you: Inkling 2 Mini is a looped transformer with just 26B parameters, small enough to run on your laptop, powerful enough for agentic work with a score of 20.1 on AA Index. thinkingmachines.ai/news/ink…
41
67
28
1,276
159,148
Just went from Max to Pro plan.
35
Inkling 2 on Macbook 24GB soon. Let's test real coding capabilities.
11
2
114
4,867
SAN FRANCISCO: For The First Time In Years, The City Is Putting Up A REAL Christmas Tree @ Union Square A beautiful Silvertip Christmas Tree fresh from the forests of Mt. Shasta in Northern California 🎄🌁
87
221
35
2,689
74,575
papee retweeted
fuck this is the coolest thing i have seen this entire year
Playing GTA VI with a Neuralink
2
1
156
9,477
A lot of these games run a whole lot better on my studio than my mini. It’s pushing the mini . I’m happy I got the studio
56
papee retweeted
111
710
34
32,078
207,831
Sigh
JUST IN: Bitcoin falls under $57,000 for the first time in over 2 years. $385 million liquidated from the crypto market in the past 5 minutes.
9
2
47
2,305
JUST IN: Crypto continues to crash $BTC falls under $56,000 $ETH falls under $1,550 $XRP falls under $0.88 $SOL falls under $66 $650,000,000 in leveraged cryptocurrency positions liquidated in the past 60 minutes.
557
777
287
5,981
476,914