UX Matthew (@uxmatthew) header
UX Matthew (@uxmatthew) profile picture

Let's make things awesome for people.

Immersed in Computing
Joined March 2009
Photo by UX Matthew (@uxmatthew)Photo by UX Matthew (@uxmatthew)Photo by UX Matthew (@uxmatthew)Photo by UX Matthew (@uxmatthew)Photo by UX Matthew (@uxmatthew)Photo by UX Matthew (@uxmatthew)Photo by UX Matthew (@uxmatthew)Photo by UX Matthew (@uxmatthew)Photo by UX Matthew (@uxmatthew)Photo by UX Matthew (@uxmatthew)
Man, product managers are always supposed to just magically know what users want, and half the time, they don't even get the damn resources they need. It's a bit of a mess, honestly. I spent 6 years learning how to run discovery solo. You’ll learn it in 60 seconds.
4
2
1
9
2,839
“AI is amazing. You just tell it what you want and hit go.” It’s wild watching this happen in real-time—success after success, even with a few bugs. Just enough knowledge of code, and AI handles the heavy lifting.
1
26
Momentum is intense. Merge conflicts? Forgetting code we barely skimmed? Learning the code after it’s built. Welcome to the fast-paced AI workflow 😂
19
Day 2 of goofing around: took a vacation this week to work on a fun side project with @uxmatthew. the idea is to create a Slack-style app for startups where ai agents and tools execute specific tasks aligned with your company goals, offer insights, create documents etc. we have a react app / node server with firebase auth, db and local llm (llama 3). tomorrow we will add named agents & DMs, additional channels, styling and whatever else sounds fun. #buildinpublic
1
1
4
251
UX Matthew retweeted
The truth [✏️ Visualize Value]
55
321
21
2,457
238,664
NotebookLlama: An Open Source version of NotebookLM 🙏 A complete tutorial on building a PDF to Podcast flow using Llama: - 1B to pre-process PDF - 70B to convert it to a podcast Transcript - 8B to make it more dramatic - Parler and Suno models for TTS github.com/meta-llama/llama-…
28
256
17
1,457
125,218
UX Matthew retweeted
Amazing graphical representation of a neural net, never seen anything like it.
47
3,355
230
19,620
1,642,415
My prediction/wishlist: Siri is rebranded to “Finder” and lives seamlessly across platforms as the main way to navigate through data on your devices.
Mac (😉) your calendars! We have an exciting week of announcements ahead, starting on Monday morning. Stay tuned…
5
2
120
13,433
Knowing what’s possible and deciding to execute is rapidly becoming more valuable than knowing how to execute. #AI
1
23
Wow, an agent that uses your computer for you.
Anthropic just announced Computer Use It allows Claude to control your computer screen based on a prompt and take actions on your behalf The use cases in agentic coding with automated debugging, customer support, and education are going to be INSANE
1
1
40
Soon the only thing you will have to do is decide what you want to exist.
Using Cursor + Claude to make fullstack SaaS apps and bring in the money. --- 0:08 - what stack I use 1:32 - cursor settings 2:34 - adding chat w/ websockets to app 4:00 - debugging app 5:18 - testing app
2
94
9,000 species in a pair of binoculars Say WHAT? 🤯🤩 Capture and share nature's wonders 💚 with the new #AXVisio – the world’s first smart binoculars. Easily identify more than 9,000 birds and animals at a simple touch of a button 😍. Intrigued? ➡️ swarop.tk/5ub
30
62
78
358
444,252
Another animation made with #LumaDreamMachine and #midjourney
2
4
81
Been experimenting with #LumaDreamMachine and #midjourney Takes some refinement, but I’m seeing some pretty impressive results
2
44
I started a company! Introducing Melty, an open source AI code editor for 10x engineers. It's the first editor that understands what you’re doing from the terminal to GitHub and collaborates with you to write production-ready code.
118
208
43
2,139
582,857
UX Matthew retweeted
i think people are misunderstanding gpt-4o. it isn't a text model with a voice or image attachment. it's a natively multimodal token in, multimodal token out model. you want it to talk fast? just prompt it to. need to translate into whale noises? just use few shot examples.
Can the voice be turned on 2x speed?
106
301
114
2,828
541,423