Blake Yoder
1.4K posts

Blake Yoder
@blakeyoder
Building Something New™
Brooklyn, NY Katılım Eylül 2009
123 Takip Edilen395 Takipçiler

Introducing Slop.md...
A 80,000+ Character .MD File that removes all common AI Slop design language.
- A general guideline, use it anywhere.
- Not a "website maker" but prevents slop design.
- Made by weeks of consistent additions to the .MD of common slop structure by AI in order to prevent it.
> View the video & the site for detail Before and After.
Hopefully it helps you! it's my first ever public ship so I'm very open for any feedback!
Special thanks to @amianthus_ for the landing page inspiration and the idea that I can do a .md release!
and @leodev / @grimcodes for inspiring me to ship publicly as well!
English

@d1ngbat_ @hthieblot This video is also an amazing example of Poe’s Law
English

This man is 100% the next Steve Jobs
Farza 🇵🇰🇺🇸@FarzaTV
Today we're shipping screen-aware dictation. First, we built a speedy speech-to-text (very fast, ~450ms). But, many products do this! So we went further. Now dictate using your screen as context. In Claude Code, it writes the prompt. In G-Mail, it replies in your voice. Demo:
English

@shardara @vercel_dev Thanks for the reply! Looking forward to multiple to-level eve agents.
btw, killer product, love the momentum at vercel!
English

@blakeyoder @vercel_dev thanks for the feedback! you can't directly call a subagent, but its on the list. for now, I'd recommend having the agent non-deterministically calling the intake subagent, it should get it right
English

@vercel_dev Can I define multiple directly callable agents in one Eve project/runtime?
I have several agentic interfaces in my app, and sometimes I already know which specialized agent should handle the request—like invoking an intake agent directly from an intake form. Can I bypass the root agent’s delegation step while keeping everything colocated with my application code?
English

@vercel_dev Can I define multiple directly callable agents in one Eve project/runtime?
I have several agentic interfaces in my app, and sometimes I already know which specialized agent should handle the request—like invoking an intake agent directly from an intake form. Can I bypass the root agent’s delegation step while keeping everything colocated with my application code?
English

@RhysSullivan An API with a large surface area of parameterized options > MCP
English

who needs an MCP when you can just let your agent call the API
get your agent connected to google search console with executor.sh
Smakosh@smakosh
Hey @Google can you ship an MCP for the Search Console? Thanks
English

@RhysSullivan Database design is the primitive now. Everything else is lossy of your database design.
English

This is an insane Fable 5 UI/UX hack.
This "Taste" skill completely kills generic AI-slop and gives Fable 5 the tools & instructions needed to ship beautiful design.
This might just be the best AI skill I've ever used.
tasteskill.dev
English

I've had to think through agent design with eve by @vercel twice now, so I turned it into a skill.
It interviews you on what you're building, picks the right eve features (tools vs skills vs connections vs subagents), then builds step by step.
github.com/scottschindler…
English

@kieranklaassen Nice! I wish codex would get into remote compute. I have codex ssh’ing into my EC2 server but having that managed would be great. Good move, Cursor!
English

Have been using this for the last month every day! Can’t do without it anymore!
Just simple, functional and clean
Cursor@cursor_ai
Introducing Cursor for iOS. Build from anywhere by launching always-on cloud agents. Or remotely control agents running on your computer from the app. Composer 2.5 is 75% off in the app now through July 5.
English

@bcherny - would love to have `plan` mode also have an exit option that is `Clear context and use /goal to implement plan`
I find myself just exiting, copying the plan path, and then letting `/goal` loop on it.
English





