James Mart

The trick is caffeine addiction. 1. My rule is that I'm not allowed to have a second cup of coffee until after I've done some exercise. 2. I always want my second cup of coffee >> 3. I always exercise.

@philliphamnett If turning on the buyback/burn utility could show a tiny but monotonically increasing number capturing the total burned, I still think it would be valuable; it shows the logic is written/tested/deployed. Agreed wouldn't make sense to show APR though

20/ On utility and dashboards: David and the team need to deliver. But activating these before there was something meaningful to show would not have made sense. Staking goes live, dashboards up, and the token displays an APR of 0.0001%? This would have upset people equally.

1/ @GunnisonCap and the @ChintaiNetwork team minted an additional 250 million $CHEX tokens. I was not part of this decision. But having been deeply involved with Chintai for years, I believe it was the right call, provided certain things happen going forward. Here's why. A thread.

I no longer agree with this previous tweet of mine - since 2017, I have become a much more willing connoisseur of mountains. It's worth explaining why. x.com/VitalikButerin… First, the original context. That tweet was in a debate with Ian Grigg, who argued that blockchains should track the order of transactions, but not the state (eg. user balances, smart contract code and storage): > The messages are logged, but the state (e.g., UTXO) is implied, which means it is constructed by the computer internally, and then (can be) thrown away. I was heavily against this philosophy, because it would imply that users have no way to get the state other than either (i) running a node that processed every transaction in all of history, or (ii) trusting someone else. In blockchains that commit to the state in the block header (like Ethereum), you can simply prove any value in the state with a Merkle branch. This is conditional on the honest majority assumption: if >= 50% of the consensus participants are honest, then the chain with the most PoW (or PoS) support will be valid, and so the state root will be correct. Trusting an honest majority is far better than trusting a single RPC provider. Not trusting at all (by personally verifying every transaction in the chain) is theoretically ideal, but it's a computation load infeasible for regular users, unless we take the (even worse) tradeoff of keeping blockchain capacity so low that most people cannot even use the chain. Now, what has changed since then? The biggest thing is of course ZK-SNARKs. We now have a technology that lets you verify the correctness of the chain, without literally re-executing every transaction. WE INVENTED THE THING THAT GETS YOU THE BENEFITS WITHOUT THE COSTS! This is like if someone from the future teleported back into US healthcare debates in 2008, and demonstrated a clearly working pill that anyone could make for $15 that cured all diseases. Like, yes, if we have that pill, we should get the government fully out of healthcare, let people make the pill and sell it at Walgreens, and healthcare becomes super affordable so everyone is happy. ZK-SNARKs are literally like that but for the block size war. (With two asterisks for block building centralization and data bandwidth, but that's a separate topic) With better technology, we should raise our expectations, and revisit tradeoffs that we made grudgingly in a previous era. But also, I have actually changed my mind on some of the underlying issues. In 2017, I was thinking about blockchains in terms of academic assumptions - what is okay to rely on honest majority for, when we are ok with 1-of-N trust assumption, etc. If a construction gave better properties under known-acceptable assumptions, I would eagerly embrace it. On a raw subconscious level, I don't think I was sufficiently appreciative of the fact that _in the real world, lots of things break_. Sometimes the p2p network goes down. Sometimes the p2p network has 20x the latency you expected - anyone who has played WoW can attest to long spans of time when the latency spiked up from its usual ~200ms to 1000-5000ms. Sometimes a third party service you've been relying on for years shuts down, and there isn't a good alternative. If the alternative is that you personally go through a github repo and figure out how to PERSONALLY RUN A SERVER, lots of people will give up and never figure it out and end up permanently losing access to their money. Sometimes mining or staking gets concentrated to the point where 51% attacks are very easy to imagine, and you almost have to game-theoretically analyze consensus security as though 75% of miners or stakers are controlled by one single agent. Sometimes, as we saw with tornado cash, intermediaries all start censoring some application, and your *only* option becomes to directly use the chain. If we are making a self-sovereign blockchain to last through the ages, THE ANSWER TO THE ABOVE CONUNDRUMS CANNOT ALWAYS BE "CALL THE DEVS". If it is, the devs themselves become the point of centralization - they become DEVS in the ancient Roman sense, where the letter V was used to represent the U sound. The Mountain Man's cabin is not meant as the replacement lifestyle for everyone. It is meant as the safe place to retreat to when things go wrong. It is also meant as the universal BATNA ("Best Alternative to a Negotiated Agreement") - the alternative option that improves your well-being not just in the case when you end up needing it, but also because knowledge of it existing motivates third parties to give you better terms. This is like how Bittorrent existing is an important check on the power of music and video streaming platforms, driving them to offer customers better terms. We do not need to start living every day in the Mountain Man's cabin. But part of maintaining the infinite garden of Ethereum is certainly keeping the cabin well-maintained.

you don't need a 2 hour workout. you don't need to read a whole book this week. you don't need to write a full chapter. go for a walk. read 10 pages. write one paragraph. "a little" beats "nothing" every single time because it keeps the habit alive

The logarithmic scales of pleasure and pain also strongly suggest a prior where the variability in the intensity of experience in response to sensory and chemical stimulus is itself a long-tail. Due to enzyme genetics, for some people 100 micrograms of LSD is a museum dose, while for others it's full ego death equivalent to a 300 micrograms typical response. For some people, a moderate hot sauce is genuinely traumatizing... not because they're being dramatic; their TRPV1 receptors are firing at 10x than others in a post-critical state of neural excitation generating what is *actually* an order of magnitude more pain sensation. For some people, a back massage feels orgasmic; for others it's uncomfortable bordering on painful due to inability to relax deeply. For some people, caffeine in the afternoon means no sleep; for others, espresso at midnight does nothing. It's important to realize these aren't psychological differences in "tolerance" or "mental strength" (precisely what "insensitive" people would want you to believe!) Rather, these are largely hardware differences (at least before any kind of significant biohacking or transformational journey). The stimulus is identical but the qualia triggered varies in orders of magnitude across people. If you're not sensitive to pain but you can "endure it," I've got news for you: you're good at enduring stimuli, not pain, because you literally don't have as much pain to endure. The person screaming from a broken bone might be experiencing subjectively more pain than what someone might feel from being set on fire, due to nothing more than SCN9A gene variations affecting their sodium channels. One isn't braver than them. One just got luckier in the genetic lottery for nociceptor density. The deepest form of knowing someone is to model their valence landscape accurately. We generally catastrophically fail to do this well for one another. Thus, I'd say we have it backwards. There is no bravery in being brave. All bravery is in the coward. And there are no strong personalities who have a strong personality. And so on. Those who endure pain the best are in fact the most sensitive to it, not the least sensitive to it.

Prompt: Write a two paragraph short story that starts on a topic David foster Wallace would find fascinating but in the style of Scott Alexander, and ends discussing a topic Scott Alexander would find fascinating in the style of David foster Wallace. Smooth interpolation transition in latent space. ----- Claude: Consider the cruise ship buffet line at 11:47 AM, when you've already been standing there for six minutes watching an elderly man methodically evaluate seventeen different salad dressing options. There's a fascinating coordination problem here that nobody discusses: everyone in line is trapped in a prisoner's dilemma where the socially optimal solution (quick decisions, consideration of others) conflicts with individual incentive (maximizing personal satisfaction from unlimited options). A 2019 study in the Journal of Consumer Psychology found that choice paralysis peaks at around 15-20 options, but cruise lines typically offer 30+ items per food station, presumably because abundance signals luxury even as it creates the exact type of low-grade anxiety that vacations are meant to eliminate. The man finally selects ranch dressing after a process that resembled chess strategy more than lunch preparation, and you move forward exactly eighteen inches. Which brings us to the psychiatric question of akrasia—that Greek term for weakness of will, for knowing what you should do (move quickly through the line) but finding yourself somehow constitutionally unable to do it—and the peculiar way that modern choice architecture has transformed what used to be straightforward moral failures into something more like...what? Neurological inevitabilities? The man with the ranch dressing (which he is now applying in a spiral pattern of extraordinary, almost obsessive precision) probably "knows" at some level that he's been holding up the line, just as you "know" you should say something, should maybe cough meaningfully or radiate impatience through pure force of will (though both of you also know, in that deeper more honest place we usually avoid, that confrontation would make everything worse, would transform a minor annoyance into a full-fledged social crisis requiring apologies and face-saving and those awful little gestures of reconciliation that cruise ship proximity makes both necessary and unbearable), but the gap between knowing and doing has been widened by architecture both physical (the narrow lane, the sneeze guard, the sheer quantity of optionality) and mental (decision fatigue, the sunk cost of waiting, the American ideology that says unlimited choice equals freedom even when freedom feels exactly like standing very still while someone deliberates about condiments).

today we announced that galaxy is the first ever publicly traded company to tokenize its SEC-registered shares on a public blockchain these are real $GLXY shares -- not wrappers, not synthetics, not shares in a foreign SPV. Galaxy Class A Common Stock, onchain more here 👇

🕹️ Turning drawings into XR worlds you can play in. I built a POC for @Spectacles that turns imagination into reality. My niece drew a picture and with the help of Mirage 2, I brought it to life in an interactive environment.

This is actually insane

Here is "AI Consciousness: A Centrist Manifesto". I've been working on this feverishly because the issue seems to me so urgent - and I'm worried extreme positions on both sides are becoming locked in, when the best way forward is in the centre. Please read it! (1/2)

Continuing the journey of optimal LLM-assisted coding experience. In particular, I find that instead of narrowing in on a perfect one thing my usage is increasingly diversifying across a few workflows that I "stitch up" the pros/cons of: Personally the bread & butter (~75%?) of my LLM assistance continues to be just (Cursor) tab complete. This is because I find that writing concrete chunks of code/comments myself and in the right part of the code is a high bandwidth way of communicating "task specification" to the LLM, i.e. it's primarily about task specification bits - it takes too many bits and too much latency to communicate what I want in text, and it's faster to just demonstrate it in the code and in the right place. Sometimes the tab complete model is annoying so I toggle it on/off a lot. Next layer up is highlighting a concrete chunk of code and asking for some kind of a modification. Next layer up is Claude Code / Codex / etc, running on the side of Cursor, which I go to for larger chunks of functionality that are also fairly easy to specify in a prompt. These are super helpful, but still mixed overall and slightly frustrating at times. I don't run in YOLO mode because they can go off-track and do dumb things you didn't want/need and I ESC fairly often. I also haven't learned to be productive using more than one instance in parallel - one already feels hard enough. I haven't figured out a good way to keep CLAUDE[.]md good or up to date. I often have to do a pass of "cleanups" for coding style, or matters of code taste. E.g. they are too defensive and often over-use try/catch statements, they often over-complicate abstractions, they overbloat code (e.g. a nested if-the-else constructs when a list comprehension or a one-liner if-then-else would work), or they duplicate code chunks instead of creating a nice helper function, things like that... they basically don't have a sense of taste. They are indispensable in cases where I inch into a more vibe-coding territory where I'm less familiar (e.g. writing some rust recently, or sql commands, or anything else I've done less of before). I also tried CC to teach me things alongside the code it was writing but that didn't work at all - it really wants to just write code a lot more than it wants to explain anything along the way. I tried to get CC to do hyperparameter tuning, which was highly amusing. They are also super helpful in all kinds of lower-stakes one-off custom visualization or utilities or debugging code that I would never write otherwise because it would have taken way too long. E.g. CC can hammer out 1,000 lines of one-off extensive visualization/code just to identify a specific bug, which gets all deleted right after we find it. It's the code post-scarcity era - you can just create and then delete thousands of lines of super custom, super ephemeral code now, it's ok, it's not this precious costly thing anymore. Final layer of defense is GPT5 Pro, which I go to for the hardest things. E.g. it has happened to me a few times now that I / Cursor / CC are all stuck on a bug for 10 minutes, but when I copy paste the whole thing to 5 Pro, it goes off for 10 minutes but then actually finds a really subtle bug. It is very strong. It can dig up all kinds of esoteric docs and papers and such. I've also used it for other meatier tasks, e.g. suggestions on how to clean up abstractions (mixed results, sometimes good ideas but not all), or an entire literature review around how people do this or that and it comes back with good relevant resources / pointers. Anyway, coding feels completely blown open with possibility across a number of "kinds" of coding and then a number of tools with their pros/cons. It's hard to avoid the feeling of anxiety around not being at the frontier of what is collectively possible, hence random sunday shower of thoughts and a good amount of curiosity about what others are finding.

Don’t be surprised if China offers Terry Tao the chair of the mathematics department at Tsinghua University. And all the funding he wants. Because it is possible for the US to fumble the bag as the destination for global talent. And indeed it is fumbling that bag right now.

If you're a Rust/C++ dev interested in Web3, serverless, or the webassembly component model, I want to hear from you. ...Or if you're a sys-admin interested in running a node for the testnet.

I am hoping to be part of a network launch on psibase infra by the end of the year, which will be radical: * No premine/ico * No corporate/VC involvement (community-owned from day-1) * Grassroots growth (word-of-mouth) ...Bitcoin-style. Super excited.

For devs who want to keep up-to-date on the project I've been working on since largely leaving the #EOS community, here's the update 🧵 I've spent the last 3 years working on a new Web3 app protocol/platform called "psibase". github.com/gofractally/ps…

Living the dream, or hardly dreaming?

@joyfulfuckup Persuasion and coertion Aren't that different Than Go and Chess