Tim O'Neil

@LasVegasLocally This thread went off the rails, but there really is only one answer.

What is the best advice you could give to someone someone moving to Las Vegas right now?

@elonmusk @aaronburnett Small, close drone footage should be mandatory on launch/land/catch. Just have a few little guys orbiting around. Get so close they get vaporized (but not interfere obv). Footage would be so epic for a tiny cost.

@aaronburnett We strive to entertain

SpaceX (fully aware of an impending IPO) set up drones specifically to capture this fireball and chose to livestream it. Let that sink in.

@dieworkwear There is a Benjamin Button joke in here somewhere.

just realized im the wario to bryan johnson. whereas he's showing how you can reverse aging, im encouraging men to dress like 80 year olds

@karpathy @bryan_johnson It’s as close to the (comic book) experience of “waking up with superpowers” I’ve ever experienced. Every day is just, what other crazy stuff can I do now? And it keeps going the more you try.

@bryan_johnson Yeah I've seen it a few times now, all the Enneagram type fives get one shotted into AI psychosis when they discover LLM knowledge bases :) And an especially a strong fit when you have a lot of pre-existing data to insert into it.

I got C-holed. Suffered sleep consequences. I busted my screens-off rule. Turned down socializing. Fell behind on work. Kate is now upset. AI is preposterous. As close to magic as I’ve experienced (except a seed becoming a tree and a zygote becoming a baby). It started on April 2nd when Karpathy shared LLM Knowledge bases. I wondered if this was the opening to structure the 1.5 billion data points I’ve collected on my body over the past five years. It's the most dynamic n=1 biomarker dataset in history. It was just sitting there. Next thing I knew two weeks had passed and Kate was wondering if she lost her boyfriend to Claude. I’m non-technical. Which honestly makes me sad. I wish I’d grown up with a computer or at least been around engineer culture. I didn’t know anyone technical until my early 20s. I became an entrepreneur at 21 and had my first of three kids at 25. I sold Braintree Venmo at 34. Learning to code stayed on my to-do list through all of it. The timing was never right. I was always on the outside looking in, wishing I had the skills to assemble 0's and 1's into digital structures. The exhilaration I’ve felt in the past two weeks is hard to explain. The 1.5 billion data points became a functional database, queryable, and microscope into my 70 trillion cells. The biological age of my organs updated in real-time like stock tickers. My build morphed from a knowledge base into a breathing organism that was self-learning and in sync with my heartbeat. I did this entirely on my own. It’s buggy, breaks and the data needs to be cleaned, but damn it’s cool. It became a mirror and ledger, one I could ask questions to. About my psyche, behavioral patterns, biology and protocols. Patterns across my life I couldn't previously connect. It’s made me insatiably hungry for more data. I’ve written about Autonomous Health, how cars now drive themselves and software wires itself. Health is next. My build showed me what it looks like in practice. Before Kate started protesting, she joked that she felt relieved for herself, our colleagues, and the world that I’d found something that matches my energy. That they could all express a sigh of relief. It’s true. This experience left me wondering if I’ve been bored my entire life. Never having found something that could match my work ethic, speed, intensity, and build capacity. Something that didn’t have the delays of the real world, human complications, or logistical drag. Two weeks deep in AI and I'm realizing that when people talk about AI, they're not talking about the same thing. Someone using a chat interface has a completely different opinion than someone building with it. And that chasm deepens for the people seeing what's coming next but isn't yet public. Society can't have a coherent conversation about AI because everyone's intuitions are calibrated to a different version of it. Off-the-shelf LLMs are mostly useless beyond narrow tasks. When they get you 80% there, it's often faster to do the whole thing yourself. And they're dangerous because the hallucination is hard to detect. Now you don't know what you don't know. Give them expanded context, memory, and architectures for self-reflection and autonomous learning, and you start to realize that AI is bigger than any of us can fit in our context window. I need to take Kate on a date, turn my screens off on time, and get some work done. And then properly dose C. Note: the image above is my 2021 baseline when starting this longevity project.

I mean, I think it goes without saying offensive capabilities will outstrip defensive ones. Athropic “getting there first” doesn’t exactly preclude any/everyone else from getting there soon. I hope glass wing goes well, but enterprise IT is not gonna “close all the holes” in a month, lol.

Yep!

@karpathy @ycombinator Curious how you manage drift vs ground truth. Or is the linting enough such that internal triangulation “feels good enough”? I guess it depends on the domain and how verifiable / testable any of the content is.

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 knowledge (stored as markdown and images). The latest LLMs are quite good at it. So: Data ingest: I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them. IDE: I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides). Q&A: Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale. Output: Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base. Linting: I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into. Extra tools: I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries. Further explorations: As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows. TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.

i think im the only clothes-related account on here who thinks dressing better will actually ruin your life. don't pay attention to fit and silhouette. don't think about how color intersects with the semiotics of style. don't ask a tailor to hem your pants. go. be free.

@ID_AA_Carmack Gotta add a Murph to your training cycle. Simple but insanely effective.

I tried the “Pete and Bobby Challenge” of 100 push-ups and 50 pull ups in 10 minutes. The push ups aren’t a problem, and I figured I could do 5 pull ups x 10 on a 1 minute cadence, but I crapped out after 25. It turns out I can barely do 5x10 on a two minute cadence, so I have a ways to go.

@balajis I for one am excited to be driving a racecar instead of a rickshaw.

AI is a tool. But you need to provide the goal.

@lexfridman Been enjoying the modality of running Cursor to walk a project, but using a terminal window (inside of cursor) to run clause code for the actual coding. Not sure if it’s quite “best of both worlds”, but it’s much better than I expected.

@TimSweeneyEpic Soft tacos are like intentional tech debt: fewer constraints, higher velocity, and totally fine so long as you don’t stress the edge cases.

Can anyone explain soft tacos? It’s like they made a burrito except you’re supposed to pick it up, and when you do, all the stuff falls out? Am I doing it wrong?

@PalmerLuckey @JTLonsdale @LlorenteJo2611 If a tree falls in the forest and it isn’t clipped into a podcast, does it even make a sound?

@JTLonsdale @LlorenteJo2611 Never mind the people who donated millions of their own dollars and raised hundreds of millions more, the only people in Tech were Sacks and Chamath!

I’m grateful my generation doesn’t have to fight for the USA against violent, totalitarian leaders; I hope our children are never faced with that horror. Yet I also envy the men of Iran at this hour; each, today, can choose to be a hero, fighting for a righteous cause. Godspeed.

@dlevine815 Threading inside a chat. Like slack. Have so many cases where I want to make a slight aside instead of taking over the entire stream of a chat.

We've got big plans to improve the core ChatGPT experience in 2026. What are some thing you'd love to see? Even small ideas welcome! Looking forward to getting them built 🙏

@ID_AA_Carmack TIL

I can’t believe I only just now found out about this four years late while trawling through settings, but windows terminal has (literally!) “Quake Mode”, where win+backtick/tilde opens/closes a terminal at the top of your screen.

@cremieuxrecueil Always measure in Kelvin. It's the only honest measure of temperature.

My apologies for messing up that chart. Any real temperature chart needs to start at absolute zero, not just the zero for a given scale. How foolish of me. I've now made it much less misleading to assess the patient's health:

@nikitabier X on web defaulting to "For You" is so painful. Feed is getting better but it's Never what I want to see first. If it's a bug, plz fix. If it's intentional - can you please add the ability to bookmark the "Following" tab via url (x.com/following) or similar?

We sat down with @IGN to discuss our partnership with @CDPROJEKTRED and reveal a few cards! Read our article below and join our Discord here: discord.com/invite/cyberpu…

@RhettReese Feels like the author is trying to just his film school degree to mom & dad. Average movie in the top 20 is black & white and what, 60-70 years old? jfc

I have various quibbles, but number one made the whole list worth it.

It's all in the cards… 👀 Right, @WeirdCo_Games?

@CyberpunkGame The tabletop is set, see you soon, legends! Until then visit us weirdco.net or hit our Discord!