LSD retweeted
"Rather than looking at AI to eventually become omnipotent or concerning, we should be looking forward to a world where man and machine build a better world together."
The right to code is the right to free speech lsd.so/blog/right-to-code
we made claude do something chat gpt o3-mini with web search can't do, using a custom LSD-MCP server @getlsd (repo in reply)
LSD retweeted
You may have a trip sitting protocol but we gave Claude an LSD-MCP. LSD SQL is a DSL for the web that can self-correct as an LLM traverses the internet.
Here’s what it looks like now that Claude is connected to the internet similar to OpenAI’s Deep Researcher
LSD retweeted
As another treat for the holidays, we have an informal solution for an unsolved math problem in number theory lsd.so/blog/brocard
Happy thanksgiving! To feed into the holiday cheer here's a blog post on how we think Google's currently getting unbundled lsd.so/blog/unbundling
LSD retweeted
Happy thanksgiving! To feed into the holiday cheer here's a blog post on how we think Google's currently getting unbundled lsd.so/blog/unbundling
LSD retweeted
Amazing how many smoking hot non US citizen girls sign up for defense tech events
Love seeing the enthusiasm/interest!
LSD retweeted
If only people could @getlsd without shattering their brains 🤔
LSD retweeted
They say if you're not embarrassed when you ship you're shipping too late so
LSD was rewritten to use |> under the hood so you can run the following query (yes with the pipe operator) in psql to get every artist/genre on everynoise (everynoise.com) with DIVE
LSD retweeted
New drop: Browserbased (serverless headless browsers) github.com/yevbar/browserbas…
LSD retweeted
Replying to @getlsd
@getlsd just open sourced a super cool tool we’ve been building and using called Lusid. It’s a self hosted iMessage interface, basically Twilio with blue bubble support.
Check it out at github.com/yevbar/lusid!
LSD retweeted
How to get stuff off the web in the most expensive way possible
You can Crawl entire website with Claude 3.5 or GPT4-o with this open-sourced tool firecrawl. 💯
Turn entire websites into LLM-ready markdown or structured data. Scrape, crawl and extract with a single API.
Crawls all accessible subpages and give you clean data for each. No sitemap required.
The greatest benefit is that the extracted data is catered for LLM-based pipelines.
















