Johannes
4.2K posts

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

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
Johannes retweetledi

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

@koeppelmann Interestingly, this can support legitimate but unauthorized grassroots voting.
English

@VitalikButerin @captgouda24 Huh? They keep your original example as "Simple Example" right above it though? Or did they add it back after you posted?
English

@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.


English
Johannes retweetledi

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
Johannes retweetledi

🚀 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

English
Johannes retweetledi
Johannes retweetledi
Johannes retweetledi
Johannes retweetledi
Johannes retweetledi

Huge news!!!
@TornadoCash addresses have been removed from the OFAC sanctions list.
A big win for privacy 🔏 💪

English

@ChrJentzsch @tokenizeitHQ @GnosisVC @cventurestudio @Etherealize_io @ethereum
This is the stuff you shouldn't ignore! This project is special.
(Yes I'm biased but it's still special)
English

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


@Truemarketsorg @base Looks great! Good job not using "prediction market" in the announcement
English
Johannes retweetledi

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









