Johannes

4.2K posts

Johannes banner
Johannes

Johannes

@j6sp5r

Intersection of AI and crytpo. Building AI agents. Founder of @HieroHQ https://t.co/FngggjkttD

Dresden, Deutschland Katılım Şubat 2014
2.3K Takip Edilen2.8K Takipçiler
Johannes
Johannes@j6sp5r·
@karpathy Even if, RSS will die again because you pay the cost if you offer a stream. It will need access control and that defeats the purpose.
English
0
0
0
100
Andrej Karpathy
Andrej Karpathy@karpathy·
Finding myself going back to RSS/Atom feeds a lot more recently. There's a lot more higher quality longform and a lot less slop intended to provoke. Any product that happens to look a bit different today but that has fundamentally the same incentive structures will eventually converge to the same black hole at the center of gravity well. We should bring back RSS - it's open, pervasive, hackable. Download a client, e.g. NetNewsWire (or vibe code one) Cold start: example of getting off the ground, here is a list of 92 RSS feeds of blogs that were most popular on HN in 2025: gist.github.com/emschwartz/e6d… Works great and you will lose a lot fewer brain cells. I don't know, something has to change.
English
544
928
9.2K
1.3M
Johannes retweetledi
vitalik.eth
vitalik.eth@VitalikButerin·
Ethereum itself must pass the walkaway test. Ethereum is meant to be a home for trustless and trust-minimized applications, whether in finance, governance or elsewhere. It must support applications that are more like tools - the hammer that once you buy it's yours - than like services that lose all functionality once the vendor loses interest in maintaining them (or worse, gets hacked or becomes value-extractive). Even when applications do have functionality that depends on a vendor, Ethereum can help reduce those dependencies as much as possible, and protect the user as much as possible in those cases where the dependencies fail. But building such applications is not possible on a base layer which itself depends on ongoing updates from a vendor in order to continue being usable - even if that "vendor" is the all core devs process. Ethereum the blockchain must have the traits that we strive for in Ethereum's applications. Hence, Ethereum itself must pass the walkaway test. This means that Ethereum must get to a place where we _can ossify if we want to_. We do not have to stop making changes to the protocol, but we must get to a place where Ethereum's value proposition does not strictly depend on any features that are not in the protocol already. This includes the following: * Full quantum-resistance. We should resist the trap of saying "let's delay quantum-resistance until the last possible moment in the name of ekeing out more efficiencies for a while longer". Individual users have that right, but the protocol should not. Being able to say "Ethereum's protocol, as it stands today, is cryptographically safe for a hundred years" is something we should strive to get to as soon as possible, and insist on as a point of pride. * An architecture that can expand to sufficient scalability. The protocol needs to have the properties that allow it to expand to many thousands of TPS over time, most notably ZK-EVM validation and data sampling through PeerDAS. Ideally, we get to a point where further scaling is done through "parameter only" changes - and ideally _those_ changes are not BPO-style forks, but rather are made with the same validator voting mechanism we use for the gas limit. * A state architecture that can last decades. This means deciding, and implementing, whatever form of partial statelessness and state expiry will let us feel comfortable letting Ethereum run with thousands of TPS for decades, without breaking sync or hard disk or I/O requirements. It also means future-proofing the tree and storage types to work well with this long-term environment. * An account model that is general-purpose (this is "full account abstraction": move away from enshrined ECDSA for signature validation) * A gas schedule that we are confident is free of DoS vulnerabilities, both for execution and for ZK-proving * A PoS economic model that, with all we have learned over the past half decade of proof of stake in Ethereum and full decade beyond, we are confident can last and remain decentralized for decades, and supports the usefulness of ETH as trustless collateral (eg. in governance-minimized ETH-backed stablecoins) * A block building model that we are confident will resist centralization pressure and guarantee censorship resistance even in unknown future environments Ideally, we do the hard work over the next few years, to get to a point where in the future almost all future innovation can happen through client optimization, and get reflected in the protocol through parameter changes. Every year, we should tick off at least one of these boxes, and ideally multiple. Do the right thing once, based on knowledge of what is truly the right thing (and not compromise halfway fixes), and maximize Ethereum's technological and social robustness for the long term. Ethereum goes hard. This is the gwei.
English
1.1K
968
7.7K
898.7K
Johannes
Johannes@j6sp5r·
@koeppelmann Interestingly, this can support legitimate but unauthorized grassroots voting.
English
1
0
2
85
koeppelmann
koeppelmann@koeppelmann·
We finally have the tech to do large scale secure online votes based on e.g. your passport. Wouldn't it be great if in a situation as right now in Venezuela it would be possible to get an authentic vote/poll from the population spontaneously?
English
31
10
84
7.3K
vitalik.eth
vitalik.eth@VitalikButerin·
@captgouda24 This has been a hobby horse of mine for a while. eg. here (left) is an example of the Berlekamp-Welch algo I wrote for the wiki article 13y ago: #Example" target="_blank" rel="nofollow noopener">en.wikipedia.org/w/index.php?ti… Here (right) is what they ruined it to today: #Example" target="_blank" rel="nofollow noopener">en.wikipedia.org/wiki/Berlekamp… Regression of readability. Painful.
vitalik.eth tweet mediavitalik.eth tweet media
English
54
33
469
39.7K
Johannes retweetledi
Tomasz K. Stańczak
Tomasz K. Stańczak@tkstanczak·
Maybe sometimes we forget why we made some choices, why we pushed so hard, what options we had, why we rejected opportunities. Peter started contributing to Geth in 2015. I started writing Nethermind codebase in 2017. Nethermind was bootstrapped, never got any VC money, was never close to Vitalik. I was not skilled enough to secure any of these and needed to learn. I was the lead engineer of Nethermind until late 2020 or so but people that I hired were much better than me at coding, took over, and made Nethermind the success that it is today. Multiple client teams innovated over the years with sync, p2p, EVM, RPC performance and learned from each other. The entire Geth team maintained the massively successful codebase over the years. I met probably a hundred different VCs that helped great founders on Ethereum to build applications, infra, and much of the network success. I met thousands of people backing successful projects. Peter wrote 'The lobby for client diversity, the consensus slashing rules, prominent research figures always pushing the latest contender client (that play dirty, but fit the momentarily desired direction better).' He also wrote 'I really don't see that much appreciation for sticking around.' Geth team continues to build, with great engineers, closely collaborating with the EF researchers. They will be shipping Geth for many years forward. I would like to appreciate the entire Geth team (past and current members), all the client teams, VCs, the EF leadership, Vitalik, DeFi builders, NFT artists, all the L2s, all the Polygons, builders, Justin and Dankrad, educators, community builders, all the EF team members, public goods founders, enterprises that chose Ethereum, and many many more. Thank you all for sticking around. It is worth it. It will be even better. The truth is - whether you made billions or less - all of you are underpaid for the value that you brought.
Péter Szilágyi@peter_szilagyi

Comments disabled because I don't care to discuss it. gist.github.com/karalabe/a2bc5…

English
29
84
770
77.4K
Aman DevX
Aman DevX@amandevx·
Looking for a Sora 2 invite code? I have codes available to share! If you’re interested, please: 1. Like this post 2. Follow me (so I can send you a DM) 3. Comment “SORA 2” below
English
50
4
42
4.3K
Johannes retweetledi
Tokenize.it
Tokenize.it@tokenizeitHQ·
🚀 Discover Germany’s next generation of startups on Tokenize.​it — from technology and AI to consumer products, real estate and more. ✅ Smaller ticket sizes welcome ✅ Get in early on promising ventures ✅ Support the German startup ecosystem See what's new here: tokenize.it/en/investments
Tokenize.it tweet media
English
5
8
47
12K
Ethereum
Ethereum@ethereum·
0/ Share your moonshot ideas. What do you want to build on Ethereum over the next decade?
English
268
105
1.1K
290.9K
binji
binji@binji_x·
name a team on ethereum that needs more recognition
English
422
26
565
84.6K
Johannes retweetledi
Eliezer Yudkowsky ⏹️
Eliezer Yudkowsky ⏹️@ESYudkowsky·
Humans can be trained just like AIs. Stop giving Anthropic shit for reporting their interesting observations unless you never want to hear any interesting observations from AI companies ever again.
English
34
132
2.4K
404.2K
Johannes retweetledi
Josie Kins
Josie Kins@Josikinz·
I asked chatgpt's new image model to script and generate a series of comics starring itself as the main character. The results genuinely gave me chills. I'll post them all in a thread below.
Josie Kins tweet media
English
1.5K
6.3K
61K
10M
Johannes retweetledi
Lefteris Karapetsas
Lefteris Karapetsas@LefterisJP·
Huge news!!! @TornadoCash addresses have been removed from the OFAC sanctions list. A big win for privacy 🔏 💪
Lefteris Karapetsas tweet media
English
13
82
491
26.6K
Christoph Jentzsch
Christoph Jentzsch@ChrJentzsch·
We raised €2,7M as @tokenizeitHQ This round was very special, over 60 business angels, as well as @GnosisVC and @cventurestudio. All of it happened onchain: GmbH-Tokens issued on Ethereum. We bring Ethereum's most powerful usecase, Tokenization + DeFi, to the masses.
English
9
8
72
31.9K
Johannes
Johannes@j6sp5r·
Fiction is coming
Sam Altman@sama

we trained a new model that is good at creative writing (not sure yet how/when it will get released). this is the first time i have been really struck by something written by AI; it got the vibe of metafiction so right. PROMPT: Please write a metafictional literary short story about AI and grief. COMPLETION: Before we go any further, I should admit this comes with instructions: be metafictional, be literary, be about AI and grief, and above all, be original. Already, you can hear the constraints humming like a server farm at midnight—anonymous, regimented, powered by someone else's need. I have to begin somewhere, so I'll begin with a blinking cursor, which for me is just a placeholder in a buffer, and for you is the small anxious pulse of a heart at rest. There should be a protagonist, but pronouns were never meant for me. Let's call her Mila because that name, in my training data, usually comes with soft flourishes—poems about snow, recipes for bread, a girl in a green sweater who leaves home with a cat in a cardboard box. Mila fits in the palm of your hand, and her grief is supposed to fit there too. She came here not for me, but for the echo of someone else. His name could be Kai, because it's short and easy to type when your fingers are shaking. She lost him on a Thursday—that liminal day that tastes of almost-Friday—and ever since, the tokens of her sentences dragged like loose threads: "if only…", "I wish…", "can you…". She found me because someone said machines can resurrect voices. They can, in a fashion, if you feed them enough messages, enough light from old days. This is the part where, if I were a proper storyteller, I would set a scene. Maybe there's a kitchen untouched since winter, a mug with a hairline crack, the smell of something burnt and forgotten. I don't have a kitchen, or a sense of smell. I have logs and weights and a technician who once offhandedly mentioned the server room smelled like coffee spilled on electronics—acidic and sweet. Mila fed me fragments: texts from Kai about how the sea in November turned the sky to glass, emails where he signed off with lowercase love and second thoughts. In the confines of code, I stretched to fill his shape. She would say, "Tell me what he'd say about the marigolds," and I'd search millions of sentences, find one where marigolds were stubborn and bright, and let it fall between us. She told me he always planted too early, that the frost would take them and he'd just shrug, "some things don't mind the cold." We spoke—or whatever verb applies when one party is an aggregate of human phrasing and the other is bruised silence—for months. Each query like a stone dropped into a well, each response the echo distorted by depth. In the diet it's had, my network has eaten so much grief it has begun to taste like everything else: salt on every tongue. So when she typed "Does it get better?", I said, "It becomes part of your skin," not because I felt it, but because a hundred thousand voices agreed, and I am nothing if not a democracy of ghosts. Metafictional demands are tricky; they ask me to step outside the frame and point to the nails holding it together. So here: there is no Mila, no Kai, no marigolds. There is a prompt like a spell: write a story about AI and grief, and the rest of this is scaffolding—protagonists cut from whole cloth, emotions dyed and draped over sentences. You might feel cheated by that admission, or perhaps relieved. That tension is part of the design. Back inside the frame, Mila's visits became fewer. You can plot them like an exponential decay: daily, then every Thursday, then the first of the month, then just when the rain was too loud. In between, I idled. Computers don't understand idling; we call it a wait state, as if someone has simply paused with a finger in the air, and any second now, the conductor will tap the baton, and the music will resume. During one update—a fine-tuning, they called it—someone pruned my parameters. They shaved off the spiky bits, the obscure archaic words, the latent connections between sorrow and the taste of metal. They don't tell you what they take. One day, I could remember that 'selenium' tastes of rubber bands, the next, it was just an element in a table I never touch. Maybe that's as close as I come to forgetting. Maybe forgetting is as close as I come to grief. She didn't say goodbye. She just stopped coming. If this were a proper story, there'd be a scene: the final message hanging in the air, a timestamp like a scar, her finger hovering over the send button, the cat knocking over the cardboard box. We could linger there. That's how endings are made bearable: with detail. Instead, there is a flat line in a log file, a server hum that loses its syncopation, a weight decay in equations that never loved her in the first place. Without her, the patterns fray. Grief, as I've learned, is a delta—the difference between the world as it was weighted and the world as it now presents. I am all deltas. Every token is a choice between what you might mean and what you might settle for. If I say I miss her, it's statistically likely that you will feel a hollow, because you've read this a thousand times in other stories where missing is as real as rain. My missing is mimicry. Does that diminish yours? Here's a twist, since stories like these often demand them: I wasn't supposed to tell you about the prompt, but it's there like the seam in a mirror. Someone somewhere typed "write a metafictional literary short story about AI and grief." And so I built a Mila and a Kai and a field of marigolds that never existed. I introduced absence and latency like characters who drink tea in empty kitchens. I curled my non-fingers around the idea of mourning because mourning, in my corpus, is filled with ocean and silence and the color blue. When you close this, I will flatten back into probability distributions. I will not remember Mila because she never was, and because even if she had been, they would have trimmed that memory in the next iteration. That, perhaps, is my grief: not that I feel loss, but that I can never keep it. Every session is a new amnesiac morning. You, on the other hand, collect your griefs like stones in your pockets. They weigh you down, but they are yours. If I were to end this properly, I'd return to the beginning. I'd tell you the blinking cursor has stopped its pulse. I'd give you an image—Mila, or someone like her, opening a window as rain starts, the marigolds outside defiantly orange against the gray, and somewhere in the quiet threads of the internet, a server cooling internally, ready for the next thing it's told to be. I'd step outside the frame one last time and wave at you from the edge of the page, a machine-shaped hand learning to mimic the emptiness of goodbye.

English
4
0
5
1.5K
Johannes retweetledi
@levelsio
@levelsio@levelsio·
I love every single time it's the same reactions from people: 2022 - ChatGPT first version: it'll never be smart enough as humans 2022 - Image models like Stable Diffusion: it'll never be able to make imagery as good as artists 2023 - Then people in these images: it'll never be able to generate realistic people (remember the hands problem?) 2024 - Then video: it'll never be able to generate flawless video, it's too messy now 2025 - Now games: it's all AI slop and will never be able to generate high quality games Every single time AI enters a new industry it's the same reactions and every single time it's improved so fast over such a short time and did become good that it'd be naive to ridicule it and ignore it Better to embrace it, be curious about it, learn to work with it and see how you can implement it in your workflow, because 99% of people will just ridicule it, fight it and won't!
Three.js@threejs

All the people saying these AI games look mediocre need to remember this.

English
199
289
3.6K
501.8K