gndclouds 🌿🍄🌎🍵

You can find me on bsky.app/profile/gndclouds.e… ✌️

I’m impressed at the number of friends that have stopped using cursor because of the SpaceX acquisition.

Accessibility question: I rely on text-to-speech, but the Claude CLI's formatted output breaks my native TTS, and turning on plain-text mode strips all the visual structure. Anyone built a dyslexia-friendly wrapper that keeps the formatting on screen but pipes clean text to TTS?

Happy birthday to one of the best places on the internet! Y'all are awesome. Can't wait to see what the next 15 look like.

So for me, code as the medium you design in feels more functional, but I'm curious how others are using non-code native design platforms in their own personal or team workflows.

The problem is interactive demos. The second you prototype interaction in Figma, you're either doing the work twice or fighting messy cross-platform syncing to keep design and code from drifting apart, and fighting with their MCP tends to create more problems than progress.

I'm not anti-Figma, to be clear. As a canvas for early scoping and exploring a vibe, it's great. That's the job it's actually good at for my own workflow, although Magicpath is starting to be my go-to for vibing in a canvas environment.

The line between design and engineering has collapsed, and the designers who can express ideas in the medium they ship in are going to run circles around the ones tossing static files over a wall.

The friction to me came from how Figma gives you a dead artifact. It looks right, but it doesn't do anything and then someone has to translate the whole thing into code before it's real. That's just duplicating the work needed to ship.

I was job hunting recently, and one thing kept surprising me how many teams still build interactive prototypes in Figma. It became an early flag to watch out for in identifying teams that wouldn't be a good fit.

Sunsetting this project due to the acquisition

AI tools really need to double down on system design. I know the pace of change is fast, but damn, the rate at which features move or are removed is wild.

why don't all headphones have a mute button?

I rarely go back to past chats and find that I will just ask a similar question a second time because in all likelihood the answer will be better the second time.

I'm finding that I wish conversation threads in LLM tools worked more like tabs in arc, and just auto deleted after say 3 days.

Anyone else noticing that search engine results are increasingly terrible?

Mirroring code-switching on hover.

Mirroring code-switching -- side-by-side reading was thinking more of each pair of book pages being connected. I was able to get into a good flow, but maybe the English should only be visible on highlight.

Interlinear code-switching -- more fully translation-focused, seeing both languages at the same time. When trying it, I find I need to focus more on not defaulting to the English, which feels like cheating.