Add Resend skill to your Replit account/org
Resend: Our friends at @Replit enabled skills:
- Upload skills
- Empower your agent
- Immediate expertise
Here's a quick overview 👇
Kevin Blumson
Try out the Blumsons Game Vault - 20 games built with #Replit using #Fable. Multiple parallel agents ran to create all your favourite games!
Fed up of app-store games loaded with apps? Just ask @Replit to build the whole store!
@Andrew_Blumson collab!
https://blumsons-game-vault.replit.app
For next two weeks, refer your friends to Codex, and you'll bank a rate limit reset:
OpenAI: We heard you wanted to use Codex rate limit resets on your own time.
Starting today, we’re rolling out the ability to save rate limit resets to use later.
We’re starting Go, Plus, Pro, and Business users with one free reset:
For the first time, I'm vibecoding with ZERO frustration and in a complete state of flow, so much so that I'm running out of ideas.
Typically, I have so much backlog of things I want to add, but after Fable landed on Replit, I'm almost certain I don't need more IQ for vibecoding, just cheaper and faster models, and we're done here.
This is what building a company looks like on Replit.
One canvas with your web app, mobile app, marketing & App Store material.
Click into any one of those and start building, changing, and generating new things.
Payom Dousti 🦥
feel like weve gotten to the point where if you told someone replit used to be a site where hungover engineers would test out one liners for syntax - they wouldn’t believe you.
Amjad Masad: This is what building a company looks like on Replit.
One canvas with your web app, mobile app, marketing & App Store material.
Click into any one of those and start building, changing, and generating new things.
Re Replit Agent team did a great job making Fable cost stomachable. The lack of mistakes net net makes it more affordable.
the #1 thing that is driving me to build my own vibecoding platform rn is that none of them - and i lov vercel, cloudflare, netlify etc - none of them really close the loop for you in terms of setting you on the right path with errors and pinging you when shit fails (shit always fails)
there's way too much "webmaster" infra to setup for every single project and i just want to do it once and for all, instead i'm being asked to npx posthog wizard here and npx arize skills there and it all just needs to be swallowed up into One Thing.
Randall Balestriero
Our lineup of speakers is growing! Many more to be announced.... and don't forget to submit your papers, deadline is very soon! More info at https://wm-booth.org and submission page at https://openreview.net/group?id=chicagobooth.edu/Chicago_Booth/2026/WM
Naveen Rao
My team loves Claude from @AnthropicAI . But this new policy of retaining prompts and usage is a red line...we simply can't give over our usage. Prompts contain our IP; literally all our design files and docs. Why would this ever have been ok?
It's sad because everyone was looking forward to using the new model. Sigh.
These AI models remind me of RPGs tbh
Peter Yang
These AI models remind me of RPGs tbh
Wow you can play fifa on Netflix now with your phone as the controller.
I just tried it and it’s pretty great.
Play FIFA: It’s game time! FIFA World Cup: Launch Edition is now on Netflix Games.
Choose a team, storm the pitch, and play on your TV or computer with up to four friends!
📲 http://www.netflix.com/fifaworldcup
Kane 謝凱堯
Brutal community note. Journalists should be required to pass a standardized stats test.
New York Magazine: Gifted and Talented, or G&T, programs have long been a perennial subject of debate, particularly in New York City, where it has bedeviled mayors for years. Some parents have already washed their hands of the whole G&T business, refusing to participate in what they view as a
Gavin Newsom came for a @garryslist event at YC and we were proud to talk little tech, YIMBY, how to stop the the asset seizure tax, and how to keep California's innovation wave going while making sure things work for every Californian.
Thank you @GavinNewsom
Randall Balestriero
We extended the deadline until Jun 15th (AOE)!
Randall Balestriero: Our lineup of speakers is growing! Many more to be announced.... and don't forget to submit your papers, deadline is very soon! More info at https://wm-booth.org and submission page at https://openreview.net/group?id=chicagobooth.edu/Chicago_Booth/2026/WM
Ahmad
http://x.com/i/article/2065291569712779264
## On Loopcraft
One might argue the entire game of the next century is to be able to stack loops as effectively as possible.
In the early days of each phase, it will be valuable to know when to go **DOWN** a loop when things go wrong (for reliability)…
but it will probably be more valuable to know how to go **UP** a loop as models improve (for leverage).
If you don’t figure out how to do this, don’t be salty when you lose to those that do.
Latent.Space: [AINews] Loopcraft: The Art of Stacking Loops
@RichardSSutton has his “Bitter Lesson” for models. We now have the Salty Lesson for agents:
Don’t fix things yourself, as you have done historically.
Instead focus on systems that scale with more agents, like goals and
Paul Graham
"... the political left has long had a remarkable lack of interest in how wealth is created. As far as they are concerned, wealth exists somehow and the only interesting question is how to redistribute it."
— Thomas Sowell
Everyone thinks AI coding tools set founders free.
Watch what people actually build with them: rules, approvals, process, layers. The same cage, assembled faster.
The tool that can scaffold anything in an afternoon will scaffold your bureaucracy in an afternoon too.
Speed of construction is speed of calcification. Build the thing that lets you create new things: experiences that didn’t happen before.
I just discovered forceBlockStreamingForReasoning = resolvedReasoningLevel === "on" for OpenClaw and frankly I love it
Seeing the reasoning traces of my claw with Claude Fable 5 is a mind-blowing experience. Seeing the tale of the tape, and being able to engage with ideas at a deeper level has always been my catnip.
AYi
我感觉Garry Tan今天这条帖子有点戳破了AI编程的一些泡沫和幻觉。
很多人都以为AI编码工具会解放创始人，实际呢，规则，审批，流程，层级，同一座牢笼只是搭得更快了。
以前加一层审批要耗两个工程师两周，
成本本身就是免疫系统，不值得的东西自然活不下来，
但现在AI一个下午就能搭完，在构建成本归零的那一刻，复杂度就开始无限制的繁殖了。
因为构建的速度，就是僵化的速度。
AI其实会改变我们的心智模型，
只会把我们已有的东西放大，
控制型团队用它堆出更密的官僚体系，创造型团队用它跑出更多的新体验，这两种工具本身都没有立场，它只是一面带编译器的镜子。
所以我们别忙着用AI把旧流程跑的更快，可以试着去用AI删掉整个旧流程，去重新创造以前从未发生过的体验，不然可能就是赢了效率，输了方向。
Garry Tan: Everyone thinks AI coding tools set founders free.
Watch what people actually build with them: rules, approvals, process, layers. The same cage, assembled faster.
The tool that can scaffold anything in an afternoon will scaffold your bureaucracy in an afternoon too.
Speed of
For me, the best use case for Fable isn't coding.
It’s giving it a ton of context about my business and life, then asking:
→ What opportunities am I missing?
→ What should I stop doing?
→ Where am I lying to myself?
Having a sharper second brain for business strategy has been the real unlock.
Feels like a no-brainer thing to try before June 22.
Should I make a video about this?
I’ve been doing “loops” for a while now. I don’t do much traditional prompting. Most of my prompts are barely a sentence expressing an outcome.
- my orchestrator prompts parallel agents
- my computer use verifier gives it feedback
- my security, production, and SEO agents generate prompts for fixes
The industry is typically 3-6 months behind what we’re doing at Replit.
Andrei Hasna: @amasad do you use loops?
Re Ok I'll make the video.
I have a specific template I use to discuss business strategy and life with AI.
Will publish here in a few days: https://www.youtube.com/@PeterYangYT?subscribe
World Labs
Today we are sharing three new research papers, each exploring a new way to generate 3D content by leveraging large-scale generative models and 2D priors.
These projects were led by our incredible interns @HaoZhang623 @BDuisterhof @DrTunnels
[1/4]
Photoroom
🚀 Meet PRX Pixel.
Our new open-source 7B text-to-image model that generates images directly in pixel space.
After months of pretraining on hundreds of millions of images, supervised fine-tuning, and preference alignment, we're excited to share a first public preview.
The weights are already available, and we're currently working on integrating the model directly into Diffusers 🤗to make the model even easier to use.
Test it yourself in the demo below. And as always, we'll be sharing the full story behind the model through a series of technical blog posts covering the entire training recipe.
Link in the comments 👇
Suraj Sharma
Microsoft and Replit just launched a way to build apps directly on top of enterprise data using prompts.
Imagine telling AI:
1. "Build me a supply-chain dashboard."
2. "Create an internal copilot for sales."
3. "Track inventory across warehouses."
And getting a production-ready app deployed inside your company's data stack.
No exporting data.
No custom auth.
No months of backend work.
Your AI already understands the schema.
Your governance policies are already attached.
Your enterprise data never leaves the system.
We're moving from:
Idea → PRD → Engineering backlog → Development → Deployment
to:
Idea → Prompt → App
The companies that learn this workflow first will move absurdly fast.
Enterprise software is starting to look a lot like vibe coding.
Except now it's connected to the data that actually runs the business.
https://replit.com/partners/microsoft
Y Combinator
At our latest YC Paper Club, researchers and builders presented on self-play for LLMs, AI for biology, formal verification, and agentic coding in production.
Thank you to our presenters:
00:00 — Francois Chaubard (@FrancoisChauba1) | Introduction & Call for Presentations
05:47 — Yasa Baig (@BaigYasa) | A World Model of Protein Biology (https://biohub.ai/esm/protein/about)
25:38 — Luke Bailey (@LukeBailey181) | Scaling Self-Play with Self-Guidance (https://arxiv.org/pdf/2604.20209)
37:51 — Arnab Maiti | Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usage (https://arxiv.org/pdf/2510.02044)
47:40 — Robert Joseph George (@Robertljg) | Lean and the New Era of Verified Intelligence (https://arxiv.org/abs/2602.22631)
58:52 — Lukens Orthwein (@lukensort) | Founder AI Hacks: Programming is an RTS Game Now
1:16:07 — Closing Remarks
Crémieux
And just like that, the entire Ivy League has returned to standardized testing!
The experiment in letting in unqualified students is over!
Steve McGuire: Columbia University has reinstated standardized testing for admissions — the last Ivy League school to do it.
“Through a multi-year faculty review, it was determined that test scores, among other factors, were a useful indicator of potential student success.”
Kane 謝凱堯
The Ivies brought back the SAT. The UCs won’t, on ideological grounds. Decades of hard-won parity with elite privates, sacrificed to a policy fad.
Steve McGuire: Columbia University has reinstated standardized testing for admissions — the last Ivy League school to do it.
“Through a multi-year faculty review, it was determined that test scores, among other factors, were a useful indicator of potential student success.”
Barr Yaron
Last call for the 2026 AI Engineering Survey 👀
https://ntn.so/ai-survey
Excited to be partnering with @NotionHQ and @vercel on this year's report.
Looking forward to sharing the results on the main stage at @aiDotEngineer!
Congrats @elonmusk & @spacex team – one of humanity's most inspiring missions! Excited about what the rest of the century will bring.
In awe of SpaceX and its story - past, present and the future. You can think about it in 10+ different ways and continue re-blowing your mind in circles. Huge congrats to the team! 🚀
HTML is so back.
Drag and http://vercel.com/drop
Vercel Developers: Drop It. It's Live.
Drag a file or folder into your browser and Vercel Drop gives you a production URL in seconds.
https://vercel.com/changelog/vercel-drop
Rork
Introducing Rork Games × Claude Fable 5
Rork can now one-shot 3D & 2D games you can play with friends online. Even Fortnite with voice chat.
Play on Web and iPhone. Generate 3D models from text and photos, 2D Assets, sound effects and music.
Are you buying SpaceX stock today?
Recall Jackie Fielder
Jackie Fielder committed municipal espionage to protect fentanyl dealers.
On February 10, 2026 the Board approved the $14 million RESET sobering center — a law-enforcement facility to divert intoxicated people from jail into treatment. Fielder and one other supervisor were the only NO votes.
That same day a confidential City Attorney memo warning the center posed “very high legal risk” and could be ruled an unlicensed involuntary detention facility was LEAKED to Mission Local. The memo was privileged legal advice. Exposing it gave lawsuits a roadmap to kill the project and keep dealers on the streets.
The LEAK investigation quickly closed in on Fielder’s office. City Attorney David Chiu warned the responsible party could face REMOVAL from office. Supervisor Dorsey threatened censure. This wasn’t politics. This was SABOTAGE against her own city’s public safety effort.
She is so ideologically opposed to cleaning up the streets that she leaked privileged legal secrets to shield fentanyl dealers from enforcement.
Jackie Fielder must resign!
If you make money on Replit, you get free credits!
Daniel Innovate: I’ve switched all my clients over to Replit!
Goodbye Webflow, Wordpress, Framer - see y’all later!
@amasad can I get some residuals 🤔 lol
Does anyone have any tips for prompting ChatGPT Images or Nano Banana to edit YouTube thumbnails?
Both seem terrible at changing my expression. I would share pics but they make me look really bad :)
Replit ⠕
New video is out! You no longer build one thing at a time on Replit.
Run parallel agents to ship a website, mobile app, video, and pitch deck from one project, all at once.
And you can now add multiple artifacts to projects you already have.
Justin Johnson
3D is an exciting area where we are still figuring out the right tasks, problem formulations, architectures, and the best ways to scale.
We're sharing some of our ideas here in our first-ever papers from @theworldlabs, led by an awesome set of interns.
World Labs: Today we are sharing three new research papers, each exploring a new way to generate 3D content by leveraging large-scale generative models and 2D priors.
These projects were led by our incredible interns @HaoZhang623 @BDuisterhof @DrTunnels
[1/4]
Epoch AI
Claude Fable 5 scores very well on FrontierMath: Tiers 1–4 (v2), reaching 87% on Tiers 1–3 and 88% on Tier 4. This continues a streak of Anthropic models improving rapidly at math.
powerful & cool way to navigate a website, makes it feel so much more interactive and intuitive
OpenAI Developers: Ask our developer docs. They’ll show you the way
The new docs agent on 🔗http://developers.openai.com helps you find answers about OpenAI products and takes you directly to the relevant documentation.
Ankit Jain
A couple of months ago @swyx published my take that the traditional code review is dead.
Many people had thoughts. If the topic is still rattling around in your head, or you want to hear where I think this actually goes from here, I'll be speaking at @aiDotEngineer World Fair.
Come if you want to hear how I see code reviews evolving.
Ankit Jain: Code reviews is a battle we cannot win.
Instead we should build frameworks that can handle the AI-generated code.
Read below on how we can blend predictive execution with deterministic verification using a layered approach.
Thank you @swyx for sharing!
We just shipped 𝙷𝚊𝚛𝚗𝚎𝚜𝚜𝙰𝚐𝚎𝚗𝚝, a unified abstraction to orchestrate and integrate any agent’s “brain” into your app.
@aisdk now frees you from both model and agent lock-in. (And it doesn’t just get you portability, it’s also delightful to use ofc!)
Vercel Developers: AI SDK now supports agent harnesses like Claude Code, Codex, and Pi with sandboxed sessions and AI SDK-compatible streams:
𝚌𝚘𝚗𝚜𝚝 𝚊𝚐𝚎𝚗𝚝 = 𝚗𝚎𝚠 𝙷𝚊𝚛𝚗𝚎𝚜𝚜𝙰𝚐𝚎𝚗𝚝({
𝚑𝚊𝚛𝚗𝚎𝚜𝚜: 𝚌𝚕𝚊𝚞𝚍𝚎𝙲𝚘𝚍𝚎,
𝚜𝚊𝚗𝚍𝚋𝚘𝚡:
I haven’t seen many people pushing Fable hard enough.
Will share some mind-blowing demos in the coming days!
Replit ⠕
Even the Mayor knows where the vibes are 👀
http://vibecon.ai
Substack
How this Meta engineer ships up to 40 PRs a day while rarely reviewing code - deep dive with video, from @petergyang's Behind the Craft https://creatoreconomy.so/p/how-this-ex-meta-l8-engineer-ships-40-prs-a-day-with-ai-kun-chen
Kelsey Piper
The UC Board of Regents had to override the faculty in order to strip the tests in the first place and I'm not sure that they won't just override the faculty again. But it's still encouraging to see faculty do the right thing and speak out
OaklandSchoolReport: "Joining STEM faculty, UC humanities faculty endorse use of standardized tests in admissions."
That didn't take long.
https://www.dailycal.org/news/uc/joining-stem-faculty-uc-humanities-faculty-endorse-use-of-standardized-tests-in-admissions-as-academic/article_a90605be-44b9-4d92-9ada-e165b20588bf.html
A clear goal prompt + Fable = MAGIC
Matt Shumer: Fable one-shotted this ENTIRE Hogwarts castle, complete with classrooms, the Great Hall, Quidditch pitch, everything
Tenobrus (→vibecamp)
over the course of adding features to this app, fable found one difficult. it turns out a certain apple API for programmatically moving windows between spaces silently stopped working 2 years ago. it found extensive discussion about this and numerous hacky workarounds other apps had gone with over the years, and told me
basically my options were slow automated mouse dragging or partially disabling system integrity protection.
but this is 2026. we're in a post unit-distance-world so i knew better. i asked it to try to figure a good workaround anyway, even though apparently nobody else had.
about 30 minutes later it discovered that the api did in fact still work to swap *between displays*, and always placed the window on the active space. and switching active spaces was still easy to do programmatically. and that there was a fully functional virtual display API it could use. it composed all of this to "bounce" windows to the virtual display, shift active space, and then bounce back, as a way to quickly and programmatically bulk shift windows between spaces.
this doesn't require any disabling of SIP and relies entirely on existing macOS apis. people know about all of these things individually, but as far as i can tell no one on the internet has figured out how to compose them for programmatic window-space movement. hammerspoon still has an open issue where the best workaround is various forms of window dragging: https://github.com/Hammerspoon/hammerspoon/issues/3698
maybe at this point ur role as an engineer is primarily telling fable to be even more ambitious than it thinks it should be
Tenobrus (→vibecamp): built a small utility macos app this afternoon. fable one-shotted the initial concept quickly. after a few further feature iteration rounds and bug reports it *entirely autonomously* decided to add a custom debugging control + probe + logging channel so it could test end to end
Patrick Skinner - edu/acc
I didn't believe this was real.
@mattshumer_ was in my office, so I had him pull it up on my machine.
It's 10x more detailed and expansive than he showed in his demo.
Just watch this video, in full.
It's almost unbelievable. But, it's very, very real.
Matt Shumer: Fable one-shotted this ENTIRE Hogwarts castle, complete with classrooms, the Great Hall, Quidditch pitch, everything
## The Future Codebase
After the PR dies, after the Code Review dies,
i am seriously wondering if Git needs to die next.
roughly 20-40% of code spend is just managing and updating merge conflicts. necessary evil? or legacy "horseless carriage"? cargo culting the past?
we don't do line by line merge conflicts when we collaborate with human colleagues - instead we chat, suggest edits, do side comments, and an owner ships it.
btw we also don't do CI/CD even collaborating on documents with serious legal/financial implications.
maybe the future codebase looks more like a Notion or Linear database than .git objects. It will be less efficient, but more scalable. exactly the Salty Lesson.
x.com