Juan
2.7K posts
Juan
@mindswimai
ai engineer | growth marketer | https://t.co/TMZ7qUVSbe
nyc Katılım Ağustos 2022
1K Takip Edilen376 Takipçiler
🇺🇸🇦🇷 Peter Thiel spent Saturday playing rapid chess at a local club in Buenos Aires and finished third.
The typical entertainment of billionaire geniuses 😂
English
I can't even imagine how fat the cheque was
Andrej Karpathy@karpathy
Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I remain deeply passionate about education and plan to resume my work on it in time.
English
do you think he had to do the coding interview or does he get a pass?
Andrej Karpathy@karpathy
Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I remain deeply passionate about education and plan to resume my work on it in time.
English
Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I remain deeply passionate about education and plan to resume my work on it in time.
English
I’m fully forward deployed engineering pilled specifically because AI simply is not the same as software. In software, you deliver a stable piece of technology to a customer and they adopt it and that’s that (extreme over simplification).
In AI, you’re delivering something that is constantly evolving both due to the nature of the new capabilities and best practices that emerge, but also because the underlying models change so much that they can meaningfully change the workflow as a result of their upgrades.
For this reason it’s far more logical that one vendor can share best practices across thousands of companies more efficiently than every single company can learn and manage these best practices themselves. Further, the learnings from those customers should go right back into the core product as a result.
As we go from chat systems to anyone can relatively easily adopt to agentic systems that require more meaningful efforts to manage and update, the FDE model (or equivalent) essentially becomes a core competency for anyone deploying AI at scale.
Yash Patil@ypatil125
The real power of forward deployed engineering has always been putting strong technical people directly alongside the operators who own the outcome. That proximity forces the work to solve the actual problem instead of some sanitized version of it. In the AI era this principle has become even more valuable. Agents can now sit inside real workflows and improve from actual decisions, which means the highest-leverage work is extracting the tacit knowledge that lives with subject matter experts, building evaluations that reflect how things actually break, and closing the production feedback loop so agents get better from real outcomes.
English
You can access 𝕏 APi via @OpenClaw.
We’re trying to make it affordable without giving away the shop.
Hopefully, this can be useful & fun 💫
Robert Scoble@Scobleizer
Holy shit. Now everyone will be able to use their @OpenClaws and all the other agentic platforms to build apps on top of X. Here's the secret: build lists. Lists are how you build apps. The pattern: Build a list of your favorite football team. Or whatever you are into. Then ask your AI agents "build an app showing me all the important news about my favorite football team." In minutes you'll have an app. And that's just the beginning. Your agent can build a script about your favorite football team that you can take to places like Google's Notebook LM. Now you have a video, a podcast, a slide deck, a game, a mind map. All about your favorite football team based on real time news. You can do the same with something like @HeyGen, create an avatar of your favorite football player. Now you will have your favorite football player telling you everything that's happening on the football team. And I could go for hours about how many things you can build and not even cover a fraction of them. This is huge. Thank you @elonmusk for making it possible to make millions of agentic apps affordably on top of X. Start building!
English
@nolansym @jonathan_wilke @marclou @supastarter this is cool, will check it out. i kept hoping someone would build this and thought about making my own personal library but got tangled in slop. hope to learn from it too
English
@jonathan_wilke @marclou @supastarter I think you need to target vibe coders for boilerplate. Make it easy af change your copywriting. Hand hold in videos
I pivoted from boilerplate to niche down into the ai sdk space with aisdkagents.com
English
I want your honest opinion:
Do you think boilerplates like @marclou's shipfast or my @supastarter have become less valuable with the current development in AI coding?
English
Claude Design one-shotted Ramp Glass
@RampLabs don't stop releasing pics and write-ups tho pls lol
Juan@mindswimai
i'm waiting on the Ramp Glass OSS clone
English
A lot of you are confusing the ability to technically make something, with output that makes sense and is actually good.
If you think this was prompted with remotion, you're NGMI
This was likely made by highly skilled people, on a short turnaround, WITH custom built tools, likely ones that AI made.
I wanna hear about how they keep their assets and UI in sync.
I don't want to see your shitty opus div that flips. It's technically possible, but it's not good.
BTW I'm very bullish on remotion, heygen and HTML graphics. See pinned post
English
WHO IS MAING THESE VIDEOS
they are so well done. I need to see the process they use to slice up and animate the UI
Claude@claudeai
Introducing Claude Design by Anthropic Labs: make prototypes, slides, and one-pagers by talking to Claude. Powered by Claude Opus 4.7, our most capable vision model. Available in research preview on the Pro, Max, Team, and Enterprise plans, rolling out throughout the day.
English
@needshismoney @daniel__designs no but i can clean it up and make it public
English
@mindswimai @daniel__designs Is xbook public?
English
I was tired of not being able to browse my Twitter bookmarks more visually, so I made an infinite grid with the ability to filter by folder. Built on top of Andrew's great work. It's open source, I'll post the link below!
Andrew Farah@andrewfarah
sharing my first open source project a CLI for downloading and syncing your X bookmarks locally so your agent can access them. it's free › npm install -g fieldtheory › login to your X account in a chrome tab › ft sync (done!) bonus: › ft viz › ft classify
English
@mindswimai Thanks! it took quite a few prompt iterations. I am a UI Designer so it helps in this aspect.
English
Redesigned the game's main menu today to give it a clean and cosy look and feel.
I've been working with Cursor 3 for this game and I just wanted to give a shoutout to the folks at Cursor for making Cursor 3 so easy to use.
IMO, Cursor 3 is the version of Cursor where I can get into a flow state very seamlessly. it's all down to the small touches.
- The default browse preview and chat window layout is very easy to use.
- Ability to send error/debug codes and prefill within the chat input field in a click of a button
- One-click commit and push to Github
- Ability to switch between agents almost instantly
- even though this is not a cursor 3 thing, but being able to deploy everything to vercel with one click is a really nice touch.
This is not a sponsored post, but I have been using Cursor for ~11 months now and I have been very happy with my experience with it.
Just a note that I am not a progammer, so the removal of the code sections from Cursor 3 didn't matter to me since the code is all greek to me anyway.
English
@daniel__designs thanks! it's a start, need to play around and think about an AI ux layer which should change the ui :)
English
@mindswimai this is great! mine doesn't support text posts, this is also super useful looks like! great work
English
Submitted my first PR ever. Claude Code wrote it. Tried hard to make sure the approach was properly scoped and fit within the project's approach and style. Wasn't directly merged but got a nice comment that if effectively was - with some changes - as another PR baased on it. Cool
Juan@mindswimai
@andrewfarah > sync'd 7,641 bookmarks with ft and wired the output to my bookmark viewer app > noticed quoted tweets were missing their content > added extraction from the graphql response + a backfill command > submitted a pr if you want to take a look: github.com/afar1/fieldthe…
English
@andrewfarah > sync'd 7,641 bookmarks with ft and wired the output to my bookmark viewer app
> noticed quoted tweets were missing their content
> added extraction from the graphql response + a backfill command
> submitted a pr if you want to take a look: github.com/afar1/fieldthe…
English
@mindswimai yeah feels like an undone api feature instead of purposeful limitation
English
would happily pay x for an official bookmark api
until then … here’s how i got 18 years of bookmarks onto my local machine (6,575 posts)
cli is open source and free
Andrew Farah@andrewfarah
sharing my first open source project a CLI for downloading and syncing your X bookmarks locally so your agent can access them. it's free › npm install -g fieldtheory › login to your X account in a chrome tab › ft sync (done!) bonus: › ft viz › ft classify
English