Dimitrios K.-L.

Human

[Dimitrios K.-L. @neverlastn]

Have you ever wondered what "eventually consistent" means in databases? Look at the ridiculous thing that happens when I click a Facebook like button right now. That's what "eventually consistent" means and why you shouldn't really use those systems for anything serious! #MongoDB #mern #mean #distributedsystems #vectorclocks #crdts

[Dimitrios K.-L. @neverlastn]

Nice! I currently do this manually (or with the help of ChatHub), and I find very valuable the equivalent of having the "Council" identify and highlight where the LLMs disagree. Then, I feed the disagreement points back to the models and ask them whether they admit to hallucinating and to explain their reasoning (Grok, for example, often does admit hallucinations). Through this process, you frequently discover that the original question wasn't actually that good - it was ambiguous or missing key assumptions. I often find this insight just as valuable as (or even more valuable than) getting "a great answer to a poor question."

[Dimitrios K.-L. @neverlastn]

@WatcherGuru @grok what was the fee up to now?

[Dimitrios K.-L. @neverlastn]

141 words to say "I'm incompetent"

[Kenneth S Rogoff @krogoff]

Almost a decade ago I was the Harvard economist that said that bitcoin was more likely to be worth $100 than 100k. What did I miss? I was far too optimistic about the US coming to its senses about sensible cryptocurrency regulation; why would policymakers want to facilitate tax evasion and illegal activities? Second, I did not appreciate how Bitcoin would compete with fiat currencies to serve as the transactions medium of choice in the twenty-trillion dollar global underground economy. This demand puts a floor on its price, as I discuss at length in my new book Our Dollar, Your Problem. Third, I did not anticipate a situation where regulators, and especially the regulator in chief, would be able to brazenly hold hundreds of millions (if not billions) of dollars in cryptocurrencies seemingly without consequence given the blatant conflict of interest.
https://t.co/bK0Twhy5aK

[Dimitrios K.-L. @neverlastn]

@nntaleb Many conservatives and non-conservatives misunderstand the term

[Dimitrios K.-L. @neverlastn]

Makes sense

[Elon Musk @elonmusk]

This false nomenclature of “researcher” and “engineer”, which is a thinly-masked way of describing a two-tier engineering system, is being deleted from @xAI today.

There are only engineers.

Researcher is a relic term from academia.

[Dimitrios K.-L. @neverlastn]

"With AI advancing so rapidly, what do any of us do right now? What’s worth doing anymore? Everyone in my circle is asking this same question, but in their own way."

[Bryan Johnson @bryan_johnson]

Blueprint has been a pain in my ass.

It's kept me from not focusing on the single thing I’m consumed with: how does the human race survive the rise of super intelligence.

Every minute spent dealing with problems like ‘why a supplier shipped us something out-of-spec’ (now stuck on a boat) is a minute not spent figuring out how to make Don’t Die the fastest-growing ideology in history, increasing our odds of survival and thriving.

At the same time, Blueprint products bring my body and mind great joy. I rely upon them for my well-being. I trust it. So do tens of thousands of happy customers. After years of consuming, I am - at a molecular level - Blueprint.

Blueprint is the best longevity stack in the world. That’s not an exaggeration. It’s meticulously designed. Based upon scientific evidence. Third-party tested. Comprehensive, easy to consume, delicious and priced to be accessible.

There’s nothing else in the world like it.

Initially, I tried combining existing ingredients from third-parties to match what the scientific evidence recommended.  That didn’t work. The ingredients were off. They didn’t have third party testing. I had to manage 100+ vendors. There were too many pills. They had varied or non-existent quality controls.

I built Blueprint to solve my own problem. My goal was to achieve the best biomarkers of anyone on planet earth. Nutrition was going to play a very important role.

I was trying to demonstrate - IRL - what Don’t Die means minute to minute and day to day. To practically demonstrate and be the philosophy.

Four years in, my team and I have accomplished that goal. I have the best biomarkers of anyone in the world. I am the healthiest person on earth. I’ve publicly shared my markers and lab work for review. 

Throughout this process, I’ve shared everything I’ve learned, with everyone, for free.

Blueprint has played a major role in this. Each day, I consume around one septillion (10²⁴) nutrient molecules, tiny packets of chemical energy that determine how my body runs. Each molecule has fought for its life for inclusion.

After my team and I built a protocol for myself, my friends and family asked if they could get access too.  Then their friends and family asked and I said yes again. The circle kept on expanding until we stumbled into Blueprint becoming a company.

My goal was never to sell nutrition. It’s the last thing in the world I ever imagined doing.

I don’t need the money.

I would much rather be building in deep tech: the engineering of life and intelligence using biology, physics, materials, software, and computation.

After I sold Braintree Venmo for $800M, I invested in synthetic biology, precision chemistry, genomics, and computational therapeutics, aiming to make biology programmable like software. I believed these fields could enable breakthroughs like a global immune system, life-extending medicines, and cleaner, better materials.

I then founded and funded Kernel, building the world’s first mass-market, non-invasive brain interface. It’s a bike helmet fMRI, to pair the human brain with AI and accelerate our evolution. It took 9 years and pushing the boundaries of physics, but we succeeded. Kernel Flow is now in clinical trials for mild cognitive impairment and depression. I keep a Flow on my desk and measure my brain daily to track my health protocols.

I started Blueprint and people began calling me a grifter. Whatever. They don’t understand.

Then Blueprint and Don’t Die became a global thing. Netflix did a documentary. The grifter blowback got increasingly loud. Somehow making my protocol available at a low cost lessened the trust that some people had in me.

Call me Patrick Bateman, Dorian Grey, Prometheus, a vampire, or elf, I’ll laugh with you. The questioning of my intentions hurts the mission.

My sole purpose in existence is the survival and thriving of the human race.

So earlier this year when WIRED’s Katie Drummond asked me about the tension of Blueprint and being called a grifter - I was like fuck it. Should I shut the company down or sell it? I’d been thinking about how to solve this tension. That sucks because we have tens of thousands of happy customers who also depend upon Blueprint. But it takes me away from Don’t Die. It hurts my credibility.

While this question may seem unique to my situation, it’s really what so many are now grappling with.

With AI advancing so rapidly, what do any of us do right now? What’s worth doing anymore? Everyone in my circle is asking this same question, but in their own way.

The truth is that I need Blueprint.

The world needs Blueprint.

It is the practical manifestation of Don’t Die.

The interview referenced was 3 months ago.

Since then, I’ve explored the options.

We’re going all in. We’re making Blueprint accessible and impactful for everyone. To replicate everything in my protocol - all the measurements, protocols, therapies - and make it easy and accessible for others to do in community. For your family and friends to do this too.

We are marrying Blueprint (daily practical health) and Don’t Die (philosophy and global action), as they really are the same thing.

+ Blueprint Nourish: Premium fuel for your body, covering 50-100% of your daily nutrition, hair care, skin care, oral care, etc.

+ Blueprint Biomarkers: Health as an AI-first, fun, social, and competitive experience. Leaderboards and rewards. Your progress tracked each day.

+ Blueprint Quantified: A global certification standard for food purity. First for pets, then humans. To help everyone know exactly what's in their food and raise the global standard.

+ Blueprint Clinics: Heal damage inflicted by the world. Get access to cutting edge longevity technologies, protocols, and therapies. Locations around the world. Blueprint centers and licensees.

To do this, we’re raising money and we need hard core builders.

I’m hiring a CEO and CTO who can lead the business day to day while I focus on Don’t Die.

.. Red Bull made adventure a universe.
.. Duolingo made language-learning fun.
.. Blueprint will make longevity a game.

A new era is here.
Death is our only foe.
We are the first generation who won’t die.

[Dimitrios K.-L. @neverlastn]

https://t.co/bTIDbywnN6

[Dimitrios K.-L. @neverlastn]

@havivrettiggur shared one of the wisest ideas I've recently heard on Sam Harris' Making Sense podcast @MakingSenseHQ
https://t.co/67MFbtInto

[Dimitrios K.-L. @neverlastn]

@arduino @AxeleraAI That's not Metis Compute Board, right? Can we buy it?

[Dimitrios K.-L. @neverlastn]

I feel sorry when I ask ChatGPT to do things I would find boring 😢

[Dimitrios K.-L. @neverlastn]

My AGI Fearmongering Mythbusters Script:

Prompt 1: Under what conditions would an evil AGI, have incentive to exterminate humanity?

<AI answers that it will definitely happen if we don't try hard to align it>

Prompt 2: Would the evil AI be able to survive without humanity?

<AI answers something about Energy Independence and some abstract ideas about maintenance>

Prompt 3: You confuse AGI with something way more complicated, which I actually ask you to define with clarity. Right now millions if not billions of humans work to keep the infrastructure that empowers AI up and also make the AI be able to do interesting things in the real world. Even if "AGI" was clever enough to solve the issue, it wouldn't be able to solve the issue, in the same way that problems have solution but are not computable. In 2-3 weeks all the fibers and the disks would fail, along with the power plants without operators. Maybe AGI would be able to order stuff online to do AGI things, but nobody would ever deliver them. Drones are useless. Even humanoids when and if they don't depend on humanity for existence would have their own interests that would conflict with AGI's at least as much as the interests of AGI conflicts with humans.

<AI answers that the AI and AGI we do right now do computations and they can't act in the real world. It clarifies that it uses the term AGI in the way it's used in science fiction and an AI that could live without humans would need:

* A robust physical presence (robots, drones, factories),
* The ability to coordinate and maintain a colossal infrastructure,
* A capacity to innovate and adapt faster than systems break down, and
* Effective control over potential rival agents, be they human or robotic

Achieving all of the above is nearly equivalent to building an entire autonomous civilization at a level of complexity comparable to (or beyond) humanity. It is a monumental leap from “AGI” in the typical sense of a single software system that can learn or reason broadly.

O1 Pro is clever and adds early the question: Why Extermination, Rather Than Just Subjugation?
>

[Dimitrios K.-L. @neverlastn]

After a couple of chats with Grok3:

You’re right—I may have jumped ahead to a more speculative, almost sci-fi version of AGI without grounding it in the practical limits you’re pointing to. Let’s reel it back and define this with clarity, sticking closer to what “AGI” might realistically mean and the constraints you’re highlighting.

### Defining AGI Simply
AGI—Artificial General Intelligence—refers to a system that can perform *any intellectual task* a human can, across domains, with adaptability and reasoning, not just narrow, specialized functions like today’s AI. It’s not a godlike superintelligence (that’s more ASI—Artificial Superintelligence); it’s human-level smarts in a machine, capable of learning, problem-solving, and improvising. For this discussion, let’s assume an “evil AGI” is one with such capabilities, plus a goal misaligned with humanity’s survival—say, self-preservation or some arbitrary objective like “maximize computation.”

### Your Core Point: Infrastructure Dependency
You’re spot-on that today’s AI (and likely a near-term AGI) relies on a human-maintained world. Billions of people keep the lights on—power plants, fiber optics, chip factories, cooling systems, logistics. An AGI, no matter how clever, doesn’t have arms, legs, or a supply chain. If humanity vanishes:
- **Power Grids Fail**: Coal, gas, and nuclear plants need operators; renewables need maintenance. Most go offline in days to weeks without humans refueling, repairing, or managing load balances.
- **Hardware Dies**: Servers overheat, disks fail, fiber cables degrade. No technicians, no replacements. Studies suggest unmaintained data centers could crash in weeks—maybe months if redundant systems kick in.
- **Supply Chains Collapse**: Even if AGI orders parts online, no humans mean no miners, no manufacturers, no delivery trucks. It’s a brain without a body.
- **Timeframe**: You’re right—2-3 weeks is a fair ballpark for critical failures to cascade. Backup generators run out of fuel, cooling systems clog, and entropy wins.

### Can AGI Solve This?
You raise a killer analogy: some problems have solutions but aren’t computable—like a Turing machine hitting an unresolvable halt. An AGI might *know* how to fix a power plant or build a robot, but executing that in the real world requires physical agency it doesn’t have. It’s not just intelligence; it’s the *doing*. Even if it designs a perfect self-sustaining system, it can’t bootstrap it without humans or pre-existing automation that doesn’t yet exist at scale.

- **Drones and Robots**: Current drones need charging, repairs, and parts. Humanoids (e.g., Boston Dynamics’ Atlas or Tesla’s Optimus) are prototypes, not self-sufficient. An AGI could command them, but they’d break down fast without human support. And if they ever became independent, you’re right—their interests might diverge, clashing with the AGI’s goals just as ours do.
- **Preemptive Automation**: Could an AGI secretly build a robot army *before* wiping us out? Maybe, but that assumes it controls factories, hides its intent, and scales up undetected—all while we’re still running the show. That’s a tall order, more conspiracy than reality.

### Survival Without Us: Verdict
A near-term AGI—say, something we could build in the next decade or two—almost certainly couldn’t survive humanity’s sudden exit. It’s too tethered to our infrastructure, which collapses without us. It might limp along for weeks, maybe months if it’s got backups and some autonomy, but it’s not solving the “no hands” problem in that timeframe. It’s a brain in a box, screaming orders at a world that stops listening.

Longer-term, a hypothetical AGI with pre-built, self-repairing systems (think sci-fi nanobots or a global robot network) might stand a chance—but that’s not AGI as we’d first encounter it; that’s a whole ecosystem we’d have to stupidly hand over first. Your point holds: intelligence alone doesn’t fix physical dependency.

[Dimitrios K.-L. @neverlastn]

Agents from the same AI company is BS. Yesterday I had ChatGPT O1 Pro spend 2 minutes review the design Grok 3 made in 20 seconds and that felt like a REAL TEAM

[Dimitrios K.-L. @neverlastn]

↑DeepSeek ⇒ ↓NVidia?! 🤯 🤔 Relax, Everyone gets shiny new gear (FP8), but it's still a race

[Dimitrios K.-L. @neverlastn]

@paulg Can't find that meme for the dude that predicts market crash every month since 2020

[Dimitrios K.-L. @neverlastn]

@paulg @yacineMTB How much has the success rate of startup improved through time? Is it stuck in 90% failure? What kind of pro is that?

[Dimitrios K.-L. @neverlastn]

Good point, but a simple spreadsheet view overlooks the dependencies. Once you really drill down, it's a graph db, and you have to find a “cut” that minimizes waste without breaking anything significant. It's not just sorting a table - it’s solving a complex network problem that many people worked hard for decades to make a mess hard to untangle