what is the word “vibe” doing here exactly?
it’s trying to demarcate a new way of building software, where you don’t write or read very much code.
instead, you articulate natural language descriptions, supply screenshots, load in napkin sketches, provide bug reports, and just chat with a model / agent.
“coding” doesn’t work, but don’t think “vibe coding” is it either
There's a new kind of coding I call "vibe coding", where you fully give in to the vibes, embrace exponentials, and forget that the code even exists. It's possible because the LLMs (e.g. Cursor Composer w Sonnet) are getting too good. Also I just talk to Composer with SuperWhisper so I barely even touch the keyboard. I ask for the dumbest things like "decrease the padding on the sidebar by half" because I'm too lazy to find it. I "Accept All" always, I don't read the diffs anymore. When I get error messages I just copy paste them in with no comment, usually that fixes it. The code grows beyond my usual comprehension, I'd have to really read through it for a while. Sometimes the LLMs can't fix a bug so I just work around it or ask for random changes until it goes away. It's not too bad for throwaway weekend projects, but still quite amusing. I'm building a project or webapp, but it's not really coding - I just see stuff, say stuff, run stuff, and copy paste stuff, and it mostly works.
bill retweeted
I have always believed that art is a driving force behind society's evolution. At @betaworks, we’ve long championed not only coders but also artists, designers, and creatives of all kinds. Our demo nights are a celebration of this synergy - a space where art, design, and code stand as equals, shaping the future together.
This Thursday, we invite you to join us for an evening of discovery and inspiration. Meet the visionary artists and engineers who are redefining what’s possible, pushing boundaries, and helping society move forward. Together, let’s explore the ideas that will shape tomorrow. We'll be welcoming some new names to the betaworks stage like @jediahkatz @DayOfLane @juanbfiguera, Octavio Figueroa and welcoming back @willrob4 @yiliu_shenburke - luma in comments!
if you update a prompt based on a bunch of failure cases but it doesn’t beat your old prompt on your custom eval set, you probably need to update your custom eval set too
nyc folks, come to demo night at Betaworks next Thursday where I’ll attempt to convince you that you can improve your sense of taste by playing silly guessing games
Ever since I joined @betaworks I've been eager to gather some of NYCs best creative technologists for art, code and internet demos. I'm pleased to share that we're hosting the creative tech community for demos & talks next thursday eve.
Register here - spots are limited: lu.ma/rmbha83x
Demos By:
@tangle_ar_app @itseieio @WTTDOTM
@willrob4 @yufengzhao_ @winterblooms
@jimmyeatcarbs
me when I eventually set up dspy with enough examples for all my prompts
This quoted post is unavailable.
the new nocode is just code. code an ai system wrote for you.
is telling an llm what you want until its foreign incantations of “jsx” and “framer motion” and “inline css” form an app really coding?
is there a quality ceiling with this approach akin to that of nocode frameworks?
idea: a feed of other user’s chats and projects built into Claude. cut out the AI influencer middle men on Twitter and just surface relevant or high signal chats, prompts, etc via a native recsys. maybe some upvoting, bookmarking, liking to help with ranking
probably not a surprise to heavy users or AI devs, but in this L@S short paper we found that LLMs do a decent job of evaluating free text responses to short answer questions in a variety of K-12 settings
rfp: chrome extension that logs all the stuff Claude teaches me about react and tailwind and then writes me little tests and études for spaced repetition
which search veteran is going to make big bucks with a Maven course that just recasts the stuff they’ve been doing already for 20 years?











