Urjit retweetledi
ThinkEx is taking the stage at Mokhtarzada Hatchery Demo Day with a digital workspace that helps users organize questions, notes and insights from large language model use into connected idea maps.
English
Urjit
133 posts
THIS 14 YEAR OLD BUILT A $10K/MONTH APP WITHOUT EVEN SPEAKING!!
People are spending $100K on degrees while teenagers are literally building apps from their laptops.
There’s never been more opportunity to make money online than right now.
(he used 10x.app btw)
English
Parents have been convinced, tickets have been acquired
TYSM to everyone offering help, also thank you to @theo and @jxnlco as well :D
Dara A.@daradoescode
Im going to try to convince my parents tmrw, I need y'all to comment reasons for me to go (i need this pls)😭😭 blow this tweet up or smth pls
English
@victorwill__ @nexus__ui @aisdk @claudeai in my exp, most people esp consumers dont care about reasoning text and its more jarring when it collapses when its done. claude actually has pretty good ui for this as they detect and only show the headers of the reasoning trace and then you can click to expand
English
Added a new component to @nexus__ui
Reasoning — Collapsible UI for assistant thinking traces
Here's a quick demo, showing how the Reasoning component is used to render an assistant's thought process, powered by @aisdk and @claudeai's Sonnet 4.5 model
Check out the updated docs and try it out!
English
Azure customers hosting OpenAI models should now be seeing a 10x improvement in latency and throughput
You're welcome :)
English
should I redesign @getpaykit logo?
I'm not sure if 2 is the best,
but 1 just kinda feels overused and basic
English
English
@Parth3083 @nickscamara_ out of curiosity, are you running into issues with llamaparse? we're not active in web scraping but we do want to make sure we provide SOTA accuracy at competitive cost. let us know if you have feedback
English
you can now upload and parse any document with firecrawl
powered by our new rust-based parser
→ layout accuracy awareness
→ smart OCR routing
→ 5x higher speeds
→ supports pdfs, xlsx, docx, html
Firecrawl@firecrawl
Introducing our /parse endpoint 🔥 Convert any document into clean data for AI agents via API. - Turn PDF, DOCX, and XLSX files into Markdown or JSON - Preserves reading order and tables - Zero Data Retention support All powered by our 5x faster Rust-based parser.
English
@urjit_ it's pulling the entire thing locally (and real fast)
English
Introducing webpull
instantly pull any website into a directory of clean, searchable markdown files
npx webpull
English
Exa genuinely sucks, please don’t use it.
Exa@ExaAILabs
Introducing Exa for Claude: Give Claude access to billions of websites, docs, papers, people, companies, and more. Exa turns Claude into a recruiter, a salesperson, a researcher, a reliable engineer, all with one plugin. Run in terminal: claude plugin marketplace update claude-plugins-official && claude plugin i exa@claude-plugins-official && claude "call mcp__plugin_exa_exa__authenticate (a deferred tool available to you, guaranteed)"
English
@urjit_ @supermemory ah shit man, are you up to chat in like 12 hours from now? i had my calendar misconfigured 😔
English
