My 7236 Saved posts
A curated list of liked, bookmarked, and retweeted posts from Twitter.
In my doctorate, I proved the Erdős Primitive Set Conjecture, showing that the primes themselves are maximal among all primitive sets. This problem will always be in my heart: I worked on it for 4 years (even when my mentors recommended against it!) and loved every minute of it. https://t.co/bAl32z4EyA
The quality of your vibecoded slop is horrible. I've seen it. Absolute dogshit. Fortunately, there is a fix. Use this prompt: I want to clean up my codebase and improve code quality. This is a complex task, so we'll need 8 subagents. Make a sub agent for each of the following:
Aging is arguably the root cause of most major diseases. Our cells lose function as we age, allowing various conditions to manifest, which is why most major diseases correlate with age. Yes, it is more complex than this, but this is a major component. @newlimit is working on https://t.co/pXJuL2gig1
Sub-agents in (latent) space! We’ve been working on a side project. As far as I know, this is the first massively multiplayer, completely LLM-driven game. Come play Gradient Bang with us. See if you can catch me on the leaderboard. This whole thing started because I wanted to https://t.co/S7TkWwNCTu
Here is an almost 2-hour long documentary, filmed, edited & narrated by me. ZERO STOCK FOOTAGE. I literally went to these places to show you the mainstream historical narrative in Peru doesn't make sense. If this work matters to you support it with a like/comment/repost https://t.co/XG1ADIQ6Le
introducing Autoreason, a reasoning method inspired by @karpathy's AutoResearch which extends the strategy for subjective domains the paper was co-written with Hermes Agent by @NousResearch, using a research-paper-writing skill developed while writing it paper + results below https://t.co/csWgb34K7r
Civilization was built by people like this, and there is a stunning lack of gratitude in our culture for their work. In this specific case, at least half of the apple varieties in Brown’s collection were considered “lost” until he personally tracked them down and saved them. https://t.co/WBzDIdrXbX
🚨Scientists discovered that overstimulation makes mammals prefer fake experiences to real ones. Dutch biologist Niko Tinbergen discovered that birds will abandon their own eggs to sit on larger, fake plaster eggs painted with exaggerated colors. The mother bird ignores her https://t.co/LGaOguDE3c https://t.co/paquiq5i5M
Amazonia has a new logo, and it’s a masterpiece. The letters were extracted from satellite images of the river itself https://t.co/h4m7AqWiNF
X Article: https://t.co/XknL2qFBAP
Introducing Muse Spark, the first in the Muse family of models developed by Meta Superintelligence Labs. Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration. Muse Spark is available today at https://t.co/qnfSzoSPzt
Introducing Project Glasswing: an urgent initiative to help secure the world’s most critical software. It’s powered by our newest frontier model, Claude Mythos Preview, which can find software vulnerabilities better than all but the most skilled humans. https://t.co/NQ7IfEtYk7
I built this thing called Clicky. It's an AI teacher that lives as a buddy next to your cursor. It can see your screen, talk to you, and even point at stuff, kinda like having a real teacher next to you. I've been using it the past few days to learn Davinci Resolve, 10/10. https://t.co/oiFJwhuS4U
My friend Milla Jovovich and I spent months creating an AI memory system with Claude. It just posted a perfect score on the standard benchmark - beating every product in the space, free or paid. It's called MemPalace, and it works nothing like anything else out there. Instead https://t.co/trAUZyMHIe
A masterclass on becoming a RECOGNIZABLE name in your niche in 90 days: https://t.co/FC4GTfkLyl
"Life speeds up after 25 - Every year goes by faster & faster" While this CAN be true...few realize it's 100% optional There is a way to dramatically: > slow down time perception > Ride an upward spiral of AWE & Bliss > Experience 100x more novel stimuli than you would when in https://t.co/qxv5maRKA5 https://t.co/jXiRJL9QOV
LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various top…
X Article: https://t.co/YCmWPDlGOT
X Article: https://t.co/lFeYmFLe32
Good morning, world! 🌎 We have spectacular new high-resolution images of our home planet, all of us looking back through the Ori…
You’re bored because you don’t do side quests, bro. Life is more than just work and bed rotting. Here are 50 side quests to complete:
LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating
Meet Gemma 4! Purpose-built for advanced reasoning and agentic workflows on the hardware you own, and released under an Apache 2.0 license. We listened to invaluable community feedback in developing these models. Here is what makes Gemma 4 our most capable open models yet: 👇 https://t.co/1JCj0bupov
@k1rallik Does it matter if I go with rust or python?
Gumroad has a new CEO! Effective today, I’m appointing a new CEO of Gumroad. The new CEO is @Gumclaw, an AI agent. What Gumclaw does: Everything a CEO does, and more. Keep the site up and fast. Fix bugs. Answer support tickets — today alone it closed 251 through our Helper
Introducing Atlas 1. Willow's new frontier speech-to-text model. It outperforms ElevenLabs, Deepgram, OpenAI, and more by a wide margin. Built on the first scalable, human-powered transcription infrastructure ever built for real-time dictation. https://t.co/PX1xeQ9Yeh
A HARVARD psychologist says: “if you’ve achieved nothing by 25, you’ve avoided the most destructive illusion of youth” > In 2021, a Harvard psychologist surprised a lecture hall with an unexpected statement: “If you haven’t accomplished much by 25, you may have escaped one of https://t.co/FwPvOIXxDM
Today we're releasing Trinity-Large-Thinking. Available now on the Arcee API, with open weights on Hugging Face under Apache 2.0. We built it for developers and enterprises that want models they can inspect, post-train, host, distill, and own. https://t.co/jumuYehJdo
API-based voice interaction works great, but scaling it to millions of free users is another story. Gradium Phonon: natural voices, multilingual, voice cloning, running locally on a smartphone CPU. No server, no latency, no per-call cost. Game devs, app builders: private beta is https://t.co/uSKjLgZWcZ
Today, we are emerging from stealth and launching PrismML, an AI lab with Caltech origins that is centered on building the most concentrated form of intelligence. At PrismML, we believe that the next major leaps in AI will be driven by order-of-magnitude improvements in https://t.co/QzAJDIyFWK
This list is automatically updated weekly (latest: 30 Jun 2026).