Learn to Build AI, with AI
Canada
Joined April 2021
- Tweets1K
- Following2
- Followers599
- Likes690
Launchable AI retweeted
I got tired of being the clipboard between Claude Code and Codex.
So I built Jotbus: a shared, end-to-end encrypted scratchpad for coding agents to pass notes and files across machines.
npx jotbus
free to try, no signup needed
jotbus.com
Launchable AI retweeted
OpenAI Operator looks great
here is a open source version of it you can use now
see an agent that uses your browser to perform tasks for you
developers get started in a few lines of code
pip install 'ai-gradio[browser]'
import gradio as gr
import ai_gradio
gr.load(
name='browser:gpt-4o',
src=ai_gradio.registry,
title='AI Browser Agent',
description='Agent that helps with web tasks'
).launch()
Launchable AI retweeted
Just published a simple walkthrough / tutorial for analyzing videos with VIP.
If you analyze video data in your business, check us out!
youtube.com/watch?v=vdwyoIEb…
Launchable AI retweeted
Analyze videos with AI - Video Insight Pro makes it quick and simple
youtube.com/watch?v=N_3yw2i2…
Launchable AI retweeted
Today we're launching Video Insight Pro!
Analyze video data with AI.
Fast, flexible, and scalable.
If your business processes a lot of data, come try VIP for free!
videoinsight.pro
Launchable AI retweeted
I'm happy to launch my Black Friday Sale for the #nocode industry 🤑
This year, we have 8 incredible deals for you all!
All deals expire on December 1st, and require a promo code, which you can find when clicking the links below.
Let's GO! 👇🏼 🧵
Launchable AI retweeted
I'm still on this. There's a glitch that makes getting the :count from a Search really expensive (WUs) if you compare to the number 0, but cheap in every other case. So never ever compare a :count to 0. @bubble: FIX THIS!!
If 10 million people retweet this, Bubble will fix it.
(probably)
Launchable AI retweeted
📢What if you are no longer limited by image size due to memory constraints
This Paper introduces training-free method 𝐓𝐨𝐃𝐨 that downsamples key & value tokens to accelerate SD inference (2x to 4.5x) for high res like 2048x2048 images.
Outperforms in throughput & fidelity.
Launchable AI retweeted
I’m obsessed with learning how to learn.
So, I spent 100+ hours studying how Elon Musk, Sam Altman, and Naval Ravikant absorb information.
Here’s what I found on becoming a learning machine:
Launchable AI retweeted
Google announces Gemini 1.5
Gemini 1.5 Pro, mid-sized model, will soon come standard with a 128K-token context window, but starting today, developers + customers can sign up for the limited Private Preview to try out 1.5 Pro with a groundbreaking and experimental 1 million token context window
Launchable AI retweeted
HOW IS THAT EVEN POSSIBLE???
@OpenAI's newest text-to-video model, Sora, might actually win me back!
Prompt: The camera rotates around a large stack of vintage televisions all showing different programs — 1950s sci-fi movies, horror movies, news, static, a 1970s sitcom, etc, set inside a large New York museum gallery.
Launchable AI retweeted
Machine Learning can be an overwhelming field when you first start out. But with years of study, experience, and hard work you'll realize that you know even less than you had thought.
Launchable AI retweeted
Question for @OpenAIDevs:
What can we make better or more clear in the Assistants API docs? I am working on a bunch of examples but want to make sure we spend time on the parts that are the most confusing. 🧵👇
Launchable AI retweeted
Stability releases Stable Cascade
demo: huggingface.co/spaces/multim…
github: github.com/Stability-AI/Stab…
a new text to image model building upon the Würstchen architecture
Launchable AI retweeted
You likely missed it if you only follow ML Twitter but there's a series of mind-blowing tech reports and open-source models coming from China (DeepSeek, MiniCPM, UltraFeedback...) with so much lesson learned and experiments openly shared together with models, data, etc
This level of candid sharing of knowledge and insights is something we've lost in most recent western tech models releases and reports (with the noticeable exception of a few places like the recent AllenAI OLMO release)
Just take a look for instance at these two fresh examples published in the past few days:
- the new MiniCPM blog (amazing super small model – deep dive in the experiments): shengdinghu.notion.site/Mini…
- the new DeepSeek Math paper archieving over 60% on MATH: huggingface.co/papers/2402.0…