Follow AI Builders — Not Influencers
Eight years ago, my great friend @darrenjsmith got oneshotted by Ayahuasca He was never the same, trying "LSD, Weed, MDMA, DMT, Peyote, San Pedro, Ketamine, Mushrooms" and to me he became something of a psychonaut "looking through the lens of many portals of perspective in consciousness" as he described it Not completely in a bad way though, he always had very interesting perspectives on things, thinking very out of the box, although I couldn't completely follow him early as he was way way way too far out for me But he's been slowly returning to Earth as I call it and is shipping again, he's set a $100K MRR goal by end of 2026 In a way he's exactly what I mean when I say "become a more original person" so you can get more unique ideas and a more unique execution of building a product or business, he's been in and out of all the portals of consciousness (way more than me, but I did a bit too :D) and is generally just a very interesting "original" person, so it's likely he has an advantage in terms of making products Especially now that the technical part is done by AI! A great friend and a cool follow @darrenjsmith
Now that the word of the year seems to be "oneshotted" by Ayahuasca, this is a very relevant and cool story by my friend @AwakenWithSho I met him 10 years ago in Bangkok when we were both staying in the same hostel He's probably one of the earliest other digital nomads I met
View quoted postRT LlamaIndex 🦙 The @n8n_io node for the LlamaParse Platform is now an officially verified community node, as part of a broader partnership with n8n to bring cutting-edge document intelligence to the low-code and no-code world🚀 The new version of the node brings together document parsing, classification, extraction, splitting, and retrieval in one place, all wired to a single LlamaParse API credential🦙 Each resource can now also act as a callable tool inside an n8n AI Agent: so instead of building static pipelines, you can let the agent decide when to retrieve context, parse a file, or extract structured data based on what the user actually needs🤖 A few workflows worth highlighting: routing documents by type before extracting structured fields, plugging retrieval directly into an agent backed by your own knowledge base, and running parse outputs through different tiers side by side to find the right balance between accuracy and cost🔃 If you're already using n8n, install it directly from your workflow canvas by searching 𝘓𝘭𝘢𝘮𝘢𝘗𝘢𝘳𝘴𝘦 𝘗𝘭𝘢𝘵𝘧𝘰𝘳𝘮 and give it a try!🔧 📚️ Full breakdown in our blog post: https://www.llamaindex.ai/blog/bring-your-document-workflows-to-n8n-with-the-llamaparse-node?utm_medium=socials&utm_source=twitter&utm_campaign=2026-jun-
Nice https://britmonkey.com/2020s-political-compass/
Most political compass tests are stupid and outdated, so I have created a political test that only focuses on REAL ISSUES of the 2020s. 64 questions that score you on four axes, including "Chud v Woke" and "Techbro v Luddite" Reply with your results & tell me if it was accurate
Have been taking different local open-weight LLMs for a test drive in different harnesses (Qwen-Code, Codex, Claude Code). 30B Mixture-of-Expert models are kind of a nice sweet spot and can solve challenging problems. And they get roughly 40 tok/sec on a Mac or DGX Spark, which is similar to GPT 5.5 in a Pro subscription and totally useable for everyday work. More interesting is also the harness choice! Claude Code seems to be using 2x many tokens as Codex. Gemma 4 E2B is here just for reference to show that the tasks can't be trivially solved by smaller models. Just finishing a longer write-up about this and will share soon (likely tomorrow)!
