Video Annotation: https://xitter.cf/t.co/Hz7yA9w4tb Smart Cropper: https://xitter.cf/t.co/k9LWkfvhsW
Earth
Joined March 2009
- Tweets4.7K
- Following3.2K
- Followers1.9K
- Likes4.9K
Pretype: system-wide AI autocomplete for macOS. Open Source and based on MLX
github.com/nikiomori/Pretype
It's time of the year to join other iOS fellows in Singapore again
S$60. Not a typo. 🎟️
iOS Conf SG 2027 tickets are on sale. Foundation Models, App Intents, AI agents in Xcode and plenty of Swift. 20–22 Jan, Singapore.
The whole region is invited for Swift, coffee and friendship 🧡
iosconf.sg/#tickets
I'd expect this kind of interaction from Google Gemini. Somehow other companies can do it before @GeminiApp
A few big upgrades for Chrome users today! We’re bringing the power of computer use to anyone who uses Chrome.
First up: ChatGPT can now use your tabs in Chrome to make answers more useful and get things done for you.
If you’re in Chat, it can look across your open tabs and gather info.
If you’re in Work, ChatGPT can control your Chrome tabs to get things, like sending messages, filling out forms, or downloading files. It can even help you organize and group that pile of tabs you have open.
Should I buy stocks from all companies listed here 😁. Local AI is the future
To help make advanced models more accessible, Muse Spark Open is optimized to run on two Apple M5 Ultra Mac Studios with the latest MLX framework.
It also runs on leading inference engines like SGLang, vLLM, TensorRT-LLM, Hugging Face Transformers, llama.cpp, and Unsloth with optimizations for AMD, Apple, Intel, and NVIDIA silicon.
Developers can further customize the model with PyTorch, including TorchTitan for fine-tuning.
Between Code dots and Claude Projects, I like Claude Projects more. It is like I have a dots bot for each project with separate context. My dots bot is jumping between different context and me too
One more year I missed Shipaton because I'm too busy at work. The quality of the submitted apps is incredible 🤯
Promised to rate and review your #Shipaton apps. You should be able to follow them in this blog post (once I get started)
perttu.dev/articles/shipaton…
I like this kind of test. It's visual, easy to compare capabilities between models. And the prompt is also provided for verification, and maybe future recheck.
Opus 5.5 made gummy bears. Gemini 4 Argon made gummy statues
Same prompt. Opus on top, Gemini below
I put both through the same moves - pull a paw, yank the head, squish it flat, throw it, then pour a whole bag on top
Opus bears are actual jelly. Pull a paw and it stretches into a thin rubbery strand, then snaps back and wobbles. Squash one and it pancakes, then launches itself back up. Throw it and it bounces off the floor and shoves its friends out of the way
Gemini bears are solid plastic. The arm turns into a stick, the bear flies straight through its neighbor, and the pile at the end just clips into itself
And Opus nailed the look too - translucent, glossy, light passing right through them
Opus: $7.2
Gemini: $22
Readers added context they thought people might want to know
Multiple users reproducing the prompt with Gemini 4 Argon (medium/high) obtained soft deformable jelly physics like the top panel, not rigid statues.
x.com/caxvalencia/st…
x.com/Alxander1024/s…
x.com/Ufdcqg/status/…
what a great attitude. This is exactly how I teach my son how to improve in football. Whenever he loses a game, he shouldn't find any excuses but looks directly what mistakes he made and how to improve instead
