i'm building an app inspired by traveler's journals. it uses open data (iNaturalist, Wikipedia, OSM, Xeno-Canto) to show you what's immediately around you then* and there
the hope is that it makes it a bit more fun to explore your immediate surroundings
what if you add some noise or randomness to the stroke so even the LLM can't "see" how the stroke they planned actually looks like until it's painted? I'd imagine it would look more organic in some ways.
it's also almost like forcing the model to rethink the next step https://t.co/3A8L2j4Mpb
Last week-end I built a watercolor simulator based on real physics (as much as possible).
A lot of you asked to play with it so i improved it and it's now live.
New since the prototype:
- More pigments (52), based on the best research out there to predict color mixes (Kubelka-Munk).
- More luminous / glassy feel
- Some fun experimental stuff like the salt and alcohol techniques to alter the texture, a backlight effect and a few more.
- I also added a Code mode where the simulator prints its real function calls next to the sheet while you paint 🤓♥️
It's still largely based on the same physics model as my prototype: Curtis et al.'s "Computer-Generated Watercolor".
All in the browser.
Current status: building and implementing a kid-friendly version for @withmarbleapp. Plenty of awesome things to learn with watercolor painting!
since my claude limits aren't enough and i have a bunch of cursor tokens i dont really use now i just have codex Sol drive Cursor to a PR that Claude can code/design review and merge and deploy
My “is engineering a valuable pursuit” math.
An outcome-oriented, creative engineer is now a 1000x engineer.
A tabs-vs-spaces-debating, miss-forest-for-trees engineer is now a -10x engineer.
The regular knowledge worker is now a 2x engineer.
This is also backed by the distribution of token consumption we see in both our startups and enterprise base. Engineers and software factories will consume exponentially more tokens.
If there’s a takeaway from Anthropic’s success, it’s that coding is the #1 killer app of AI.
y esta bien chido que llegas, describes que quieres aprender o mejorar y diseña tu propia ruta de aprendizaje, no basada en cursos sino en habilidades.
como profesionales o entusiastas de esto de los datos hacemos muchas cosas sin darnos cuenta. darles nombre ayuda.
de los detallitos de heymaestro.app que no son 100% necesarios pero agregan algo chido es crear tu foto de perfil
y en tu compu tu foto siempre voltea a ver hacia tu cursor como las fotos de harry potter
https://t.co/EofSDKIeVK
@bran_don_gell vercel ! ai gateway, token pass, just general credits I don't know but more and more of my infra ends up running on vercel and cloudflare (cloudflare would also be cool but my $5 month covers pretty much everything i need from them lol)
@alejandrozepe algo que me gusta mucho ahora es que los MCP tienen interactive tools asi puedes tener la UI también por ahí (cuando tenga sentido hacerlo)
Got to experience the magic of @uisdk.
Two prompts of fx + Gemini Argon. Pure Web Components. No framework.
The agent reused 14 UI SDK behaviors out of the box 🤯: window resizing, drag, menubar hover-switching, typeahead, roving toolbar focus, 10-band EQ sliders, scoped hotkeys, ARIA, and WebMCP agent control.
https://t.co/1Ol3xqKWJz (source linked)
Music by @suno.
Casi nada de lo que compras en el Buen Fin va a estar tan bien como el día que lo estrenas. Lo que aprendes te sirve más entre más lo usas.
Este Buen Fin, nueve de mis cursos de datos en https://t.co/pEEdy5doED tienen 30% de descuento, hasta el martes 17: https://t.co/0xTNMapGNz
actually didnt even send the link i downloaded and sent the video and codex just used ffmpeg and a local transcription model to get what the video said and looked like
i saw a tiktok of a guy explaining how he took this particular format for his reels from this other creator and made it a little better for his own content
i sent the link to codex and ask it if it could make me the same thing using Everycut and 6minutes later i got a branded POC
This is why I've been freaking out - kieran made professional software we actually use internally (I do all my video recording and meetings with this now instead of descript loom and zoom). My favorite feature is is multimodal jev-based scene detection.