leo (@leoshimo) header
leo (@leoshimo) profile picture

leo

@leoshimo

Keep computing personal. Cats are my own. CUA & Frontier Interfaces @openai Prev: @skybysoftware, Recurse, Humane,  tenured homesteader @ https://nitter.cf/t.co/Mb98VdwGQO

 sf
leoshimo.com
Joined April 2015
  • Tweets878
  • Following4.8K
  • Followers1.4K
82Media
Photo by leo (@leoshimo)Photo by leo (@leoshimo)Photo by leo (@leoshimo)Photo by leo (@leoshimo)Photo by leo (@leoshimo)Photo by leo (@leoshimo)Photo by leo (@leoshimo)Photo by leo (@leoshimo)Photo by leo (@leoshimo)
in my software homesteading arc
1
2
1
49
15,602
the duo folio with front cut off is *exactly* what I need
Federico Viticci (@viticci) profile pictureFederico Viticci
@viticciOct 24
I did it: I cut Apple's kickstand case for iPhone Duo and assembled my portable Duo writing setup for travel. It's absurd that I had to do this, but I just wanted the back cover and kickstand. I kinda love this 👀
Image from Federico Viticci (@viticci)
Image from Federico Viticci (@viticci)
Image from Federico Viticci (@viticci)
Image from Federico Viticci (@viticci)
7
605
Ok I’m in
Nat Friedman (@natfriedman) profile pictureNat Friedman
@natfriedmanOct 2
🚨 side project alert 🚨 Announcing Muse Gadgets, an open source ESP32 firmware and Linux sdk so that you can make hardware devices that work with Muse. Grab an API token from gadgets.muse.ai and point your favorite coding agent at the github repo to build your own peripherals for Muse.
Image from Nat Friedman (@natfriedman)
4
376
This was almost way too easy, @natfriedman @alexandr_wang 😮 I turned my Xteink eReader into an always-on Muse pocket display for Calliope (my Muse) to display itself and show status updates. And this attaches with MagSafe to my phone, so I can always see relevant updates from Muse by just turning my phone around. The setup flow in the Muse app was super smooth and you can just ask Muse to load or automate content on the display. I genuinely love the hacker-friendly aspect of this. Well done.
Image from Federico Viticci (@viticci)
Image from Federico Viticci (@viticci)
Image from Federico Viticci (@viticci)
67
51
21
1,100
184,487
Mac VM support is so fun. Uploaded some baby pictures and converted them to video game sprites for Devin to make Flappy Asher. Live in TestFlight. My wife is thrilled.
Cognition (@cognition) profile pictureCognition
@cognitionSep 15
Special delivery: Devin just got a Mac 🍎 Now Devin can: 1. Build & test apps on its own Mac VM with iOS simulator 2. Send a screen recording via Slack 3. Send a TestFlight link so you can start using it 📲
13
6
2
120
14,286
leo retweeted
Hank (@h4nkdog) profile picture
Hank
@h4nkdogSep 9
We've entered the golden era of gaming. I had GPT-6 Astra reverse engineer Super Smash Bros Melee to work on my Meta Quest 3 with VR controls. I'll post my first real battle in the replies
banteg (@banteg) profile picturebanteg
@bantegSep 7
super smash bros melee is fully decompiled, this project started in july 2020, so it took over 6 years. the progress was hugely accelerated by llms and finished off with astra. it's a very large game with 3.88mb of compiled code. github.com/doldecomp/melee
Image from banteg (@banteg)
47
131
35
1,956
212,732
need the duo now
1
1
1
15
886
Astra was able to get Super Smash Bros Melee compiled for Mac OS, running at 120 FPS with higher resolutions and upscalable textures. Took about 6 hours in a loop. We live in wild times.
banteg (@banteg) profile picturebanteg
@bantegSep 7
super smash bros melee is fully decompiled, this project started in july 2020, so it took over 6 years. the progress was hugely accelerated by llms and finished off with astra. it's a very large game with 3.88mb of compiled code. github.com/doldecomp/melee
Image from banteg (@banteg)
156
238
55
5,941
673,692
delicious details in chatgpt composer 😋
OpenAI (@OpenAI) profile pictureOpenAI
@OpenAISep 8
Replying to @OpenAI
Some ideas are easier to draw than describe. Use Sketch to draw right in ChatGPT and show it exactly what you have in mind. Just type “@ Sketch” in ChatGPT.
2
20
1,048
Astra, make this photo interactive and find the books
193
889
152
11,217
1,245,454
is this the new Will Smith eating spaghetti benchmark
Peter Gostev (@petergostev) profile picturePeter Gostev
@petergostevSep 5
Astra - recreate the original Craig Federighi in Blender.
54
628
11
27,751
2,249,677
With Astra, ChatGPT is nearly 2x faster at computer use than before. In addition to the amazing new model, we’ve optimized the harness to make computer use run much faster. These optimizations work in existing models too, so tasks are sped up by ~60% in GPT-5.6 Sol. Try it!
98
83
33
1,797
293,689
fun chatgpt power user feature - press cmd+enter to send your prompt in the background queue up a ton of tasks at once and let the model notify you when it's done 🧑‍🍳
37
31
10
645
85,065
Today we're releasing Computer History in ChatGPT. It lets ChatGPT learn from everything you do on your computer, so it can better understand how you work, finish tasks that you're in the middle of, and suggest skills and automations based on how you use your computer.
189
160
158
2,426
822,661
leo retweeted
max (@maxbittker) profile picture
max@maxbittkerJul 17
Beautiful short film celebrating 15 years of the @recursecenter I love this community, always excited to chat with people about applying or re-applying!
8
47
4,489
leo retweeted
OpenAI (@OpenAI) profile picture
OpenAI
@OpenAIJul 9
Meet Hiroki (@tomiyasu16). A broccoli farmer running his farm with GPT-5.6.
226
700
249
6,901
1,194,495
この帽子をサンフランシスコで被ろうとしてたら、SFではAIヘイトがあるらしく真剣に止められた。 ChatGPTをチャッピーと呼んだりして、親しんで使う日本人とのAIへの価値観の異なりを感じた。AIへの不安は日本人でもあるけど、ロボはドラえもんや鉄腕アトムみたく人と共存するイメージ。アメリカはターミネーターやマトリックスみたいな人に反逆する感じで描かれるイメージがある。神道とキリスト教、宗教の違いまで遡ってAIへの受け止め方の違いあるのかなと思った。 また日本は人口減少最先端の国だから、労働力不足解決への期待もあって受け入れられやすいんだろうな。僕自身は農業でAIやロボができることはどんどんやってもらって、人は人間にしかできないことするのがいいと考えて活用している。
Image from とみやす｜北海道の農家🇯🇵 (@tomiyasu16)
14
114
32
697
116,636
leo retweeted
USGC (@usgraphics) profile picture
USGC
@usgraphicsJul 11
omfg the whimsymaxxing, individual glyphs in the logo are being hoovered.
Image from USGC (@usgraphics)
HARDEST FIT PICS (@HardestFitPics) profile pictureHARDEST FIT PICS
@HardestFitPicsJul 11
Vintage Hermes Ties 👔
Image from HARDEST FIT PICS (@HardestFitPics)
Image from HARDEST FIT PICS (@HardestFitPics)
Image from HARDEST FIT PICS (@HardestFitPics)
Image from HARDEST FIT PICS (@HardestFitPics)
26
307
17
6,226
293,385
The new ChatGPT Work comes with a new Computer Use experience. It's faster and introduces picture-in-picture, so you can keep an eye on Computer Use while it works!
54
44
35
844
198,467
leo retweeted
Sam Altman (@sama) profile picture
Sam Altman
@samaJun 26
oh and also...750 token/sec coming to 5.6 sol in july!
322
178
340
4,847
2,426,492
leo retweeted
nolen (@itseieio) profile picture
nolen
@itseieioJun 23
the internet has lost *legibility of effort* - the ability to easily whether something took meaningful human work It's why we all catalogue vibe-code tells. And I bet that we'll find new ways to show our humanity through our work eieio.games/blog/legibility-…
Screenshot of blog. Full text: So: Lots of work is easier because of LLMs, and Lots of heuristics we used to gauge effort are broken because of LLMs, so Conveying effort to others is harder because of LLMs And: “Someone spent time on this” is a proxy for “this is worth engaging with” and I appreciate projects that take a lot of effort and I like it when people appreciate that I spent effort on something But also: Making a good thing still requires making lots of decisions, and Making lots of decisions is still very hard, despite LLMs, so Making good things is still very hard As a creative technologist I’ve found this paralyzing. And as someone who loves novel internet projects I’ve found it frustrating. I’ve heard similar things from many of my friends. What software (and writing, to an extent) is missing now is legibility of effort - the ability to tell at a glance whether something took a human meaningful work.

ALT Screenshot of blog. Full text: So: Lots of work is easier because of LLMs, and Lots of heuristics we used to gauge effort are broken because of LLMs, so Conveying effort to others is harder because of LLMs And: “Someone spent time on this” is a proxy for “this is worth engaging with” and I appreciate projects that take a lot of effort and I like it when people appreciate that I spent effort on something But also: Making a good thing still requires making lots of decisions, and Making lots of decisions is still very hard, despite LLMs, so Making good things is still very hard As a creative technologist I’ve found this paralyzing. And as someone who loves novel internet projects I’ve found it frustrating. I’ve heard similar things from many of my friends. What software (and writing, to an extent) is missing now is legibility of effort - the ability to tell at a glance whether something took a human meaningful work.

4
20
2
124
5,781
Load more