Ray Villalobos ✝️
9.9K posts

Ray Villalobos ✝️
@planetoftheweb
Helping the smartest people thrive past the Age of AI. LinkedIn and Stanford University. Humans will never be abstracted.
iPhone: 28.459488,-81.306122 Katılım Mayıs 2007
273 Takip Edilen6.7K Takipçiler

I really liked Claude Design, but it does have issues since it burns so many tokens. That should improve (same with memory prices) over time, but it will take a bit. Meanwhile I made a nice collection with all kids of design resources including some of my own vibe coded projects like Vibe Glossary, Claude Design competitors like Stitch and Open Design and tons of inspiration sites.
vibeit.work/groups/planeto…
English

I had been running GLM-5 for a while and it was decent, but still made some errors I wasn't pleased with. Mainly misunderstandings managing my Content Pipeline Kanban Board.
Been on Mimo 2.5 Pro for almost half a month now and I gotta say, the problems went away. I was expecting more savings, but as you can see, there was virtually no difference.
As a teacher, I have to try different models all the time, but it's working so good, I really don't want to. I'll give Grok and Kimi 2.6 (I was on 2.5 before which I remember being pretty good). I would really love to run Gemma 4 locally for free...crossing fingers that my machine can handle it).
Will report l8r

English

You know...I really liked @Comet and had been recommending it for years, but I'm out. I don't know why anyone would think of removing slash commands in their assistant and making any skills that I create virtually unusable.
When some idiot thinks that removing the most useful feature they've ever had for no reason whatsoever, it means the company is not thinking straight. I have to wait for a while since I made the mistake of paying for a year subscription, but I'm uninstalling it and finding a different solution.
There was a time when this was the best option, but now the Claude Extension is better, I had even started using that Claude Extension in Comet since it had gotten so bad.
I'm out and uninstalling this disgrace.
English

I gotta say @comet, removing slash commands from the sidebar assistant is just dumb. Easily my most used feature, now totally gone...and for what? Now I have to find a browser that doesn't do ridiculous things like that.
English

@leohuynh139 Thats the thing, for more aliveness I have to go with Image2
English

@planetoftheweb Mind-blowing side-by-side showdown These tests make me question which model actually feels more alive. Which one's wilder vibe wins for you?
English

I've been running tests all night between the new GPT Image 2 and Nano Banana Pro and I'm sort of undecided. The one with the wilder tittle font are Image 2. Google's look a little more corporate and less 'fun', but the fidelity is great. I do like the larger resolution of I2.
The interface is from my own website/open source project called BrandoIt. Besides adding the new models, I added a comparison slider, etc. It's probably the most used thing I've ever built. Go check it out or give it a star on GitHub or clone it or whatever.
Sorry, you're going to need to provide your own keys until Google buys me out or I hit the Lotto or something.
Website: brandoit.onrender.com
Repo: github.com/planetoftheweb…



English

@RichKleinAI For what I do, which is create these illustrations yes. I can’t decide which I like better, but I think I might actually stick with NB2.
English

@planetoftheweb Nice project! Both outputs look good. Do you think NB 2 holds up well compared to GPT Image 2?
English

@perplexity_ai Why you remove commands from the browser assistant. I had a few critical skill commands and now they’re worthless
English

@testingcatalog Can't wait for Google Deep Max Ultra Pro Times Infinity
English


My beginner students in my Stanford Vibe Coding class were having some trouble learning some of the terminology for things they needed to build, so I created this Vibe Glossary, which has now expanded with learning paths, scaffolding code, progress, quiz mode, etc.
I gotta take a break until my tokens renew or go use Cursor for a while. Claude Code for Desktop is a Blast.
vibe-glossary.web.app
github.com/planetoftheweb…
Stars always welcome, MIT licensed open-source. I've got 44 items and once I get more tokens, I'll add some more. It's actually a lot of fun.

English

Okay, I'm not Anthropic, but I keep shipping. I use this tool to help me generate images for my slides/projects. Open Source...stars welcome. Enjoy.
brandoit.onrender.com
github.com/planetoftheweb…
Updates/Changes
--------------------
Batch generation: one Generate can run multiple images at once (quantity + brace-style prompt combos).
Smarter runs: rough size/time estimate
Cleaner history: batch results land on one tile as Mark I / II / III instead of spamming the gallery.
Faster browsing: a thumbnail rail on the main preview to flip between marks without losing context.
Simpler exports: one Download flow for PNG / WebP / SVG / HTML, including download all and ZIP selected items from Recent Generations.

English

I gotta admit it, I was wrong about the new Claude Code for the Web (@ClaudeDevs). I thought it was just a clone or Cursor 3/Codex, but it's something...different.
Claude has been breaking the internet with releases lately and you gotta ask yourself...why?
Is it their great model...sure. Is it their developers are better? Ok, they're great, but no better than others...or are they (see theories below)
It's because they have a better Agent Harness, the framework that allows them to ship without getting stuck in the virtual Straits of Hormuz. Everything they've been building has been focused on improving this, dispatch, btw, cron, routines and tons of other improvements.
Those aren't cute plugins, they are deliberate infrastructure to build around one thing...shipping. But so far, there's been one thing that's holding them back...The Claude Code CLI.
Sure it's nerdy and it's got like a VIM flair and all, but there's a reason we don't run DOS anymore (showing my age aren't I)...Integrated browser, interfaces that show you those MCPs nuking tokens, multiple agent processes, worktrees...Everything is right there tucked away in little cubby holes, behind a beautiful interface.
By this time, the Claude Devs are either aliens, or they're probably running like Claude 10. Well played Claude. I take my propeller cap off to you.
linkedin.com/learning/ai-tr…
English



