Michael Pirro

Embarking on a journey to build a fast Layer-1 blockchain with AI. No coding skills, just big ambitions. Feedback welcome! #blockchain #blockchainbuilder

[Michael Pirro @michaelpirro]

I have set myself an experiment for this year, which I will start today. I have no programming knowledge and want to create my own fast Layer-1 blockchain with its own token using AI. For now, I will only use @AnthropicAI Here are some of the technical specifications I have planned:

- 500,000 TPS (scalable up to 5M) Very ambitious, I know. 🙂
- 3 seconds finality
- Proof of Stake with Sharding (100 shards)
- Simple transactions + NFTs (max 100KB)

The node system:

- 2,000 validator nodes as tradable NFTs
- 200 backup nodes
- 90-day transfer lock after minting
- Achievement system with a maximum +10% bonus

These are the specifications I will try to adhere to, although it's possible that I might decide to change things over time. I will try to report regularly here and give you an update. Questions and feedback are always welcome. #blochchainbuilder #blockchain #ai #aiblockchain

[Michael Pirro @michaelpirro]

I'm trying to build a blockchain exclusively with the help of AI models without any programming knowledge.

In the last 3 days, I've made really significant progress. In my last post, we were at about 1,400 lines of code; now we're at around 4,700 lines, though this includes comments that weren't part of it before. I'm still using https://t.co/it9QZSafRM by @AnthropicAI with a single account and a business account that allows a total of 5 team accounts. Since I have so much code and I have to upload the current code to Claude for reference repeatedly, the limitations become apparent pretty quickly. I then try to continue in another account, but I have to precisely inform it about how far we've gotten, what should be done, what has been done, and what still needs to be done. If you're not very specific here, the model makes mistakes. The most common errors are that the code isn't fully checked, and things get repeated that are already integrated.

I want to prepare the code so we can launch a testnet in the near future. Here are the things that have already been implemented:

- Basic node discovery with peer structure, reputation, and services
- Bootstrap node configuration
- Basic error handling with a NodeError system
- Async TCP connections and message broadcasting
- Simple mempool management
- CLI commands
- Basic test documentation

The following things are still missing and will be done next:

- Rate limiting and DoS protection are largely missing
- The fork resolution is only rudimentary
- The RocksDB integration needs to be completed
- The checkpoint system is still missing
- The test suite needs to be expanded

If you have ideas, suggestions, or constructive criticism, please let me know. I welcome all your comments.

#blockchain #aiblockchain #aiagent #blockchainbuilder #newblockchain

[Michael Pirro @michaelpirro]

I'm trying to create my own blockchain using only AI, with no programming knowledge.

For the first time, I feel like I've made significant progress. The new approach with https://t.co/it9QZSafRM seems to work, at least so far. As I mentioned in my last post, all models had trouble remembering things after a certain point and especially posting the entire code again with changes or additions. I've therefore changed my approach and now only ask https://t.co/it9QZSafRM for the code for smaller changes and additions. With this method, I've now reached over 1400 lines of code.

I started with simpler specifications than originally planned, with the intention of gradually incorporating new features into the code. I'm still using Rust as the programming language, as every AI model so far has recommended it. I've made significant progress with this method, and here are the features we've integrated into the code so far:

Basic Blockchain Functionality

- A complete blockchain structure with blocks and transactions
- Proof of Work mining system with adjustable difficulty
- Automatic difficulty adjustment based on block time
- A halving system for mining rewards (might be changed)

Wallet System

- Generation of wallets with public and private keys
- Shortened wallet addresses through hash functions (16 characters)
- Secure storage of wallet information in files
- Transaction validation and signing

Validator System

- Proof of Stake elements through validator registration
- Stake-based validator selection
- Distribution of mining rewards among validators
- Security mechanisms against stake manipulation

Naming System

- Registration of user-friendly names for wallet addresses
- Resolution of names to addresses and vice versa
- Validation of name registrations
- Integration into the transaction system

Network Protocol

- Peer-to-peer communication between nodes
- Synchronization of blocks and transactions
- Management of peer connections
- Graceful shutdown of nodes

Planned Next Steps:

- Implementation of a decentralized consensus mechanism
- Expansion of the network protocol to include automatic peer discovery
- Development of a user-friendly CLI interface
- Integration of a Merkle tree for more efficient transaction verification
- Implementation of a smart contract system

As always, I'm open to any constructive criticism, suggestions, and tips.

#Blockchain
#Crypto
#Cryptocurrency
#AI
#NoCode
#AIProgramming
#RustProgramming
#Layer1
#ProofOfWork
#ProofOfStake

[Michael Pirro @michaelpirro]

I'm trying to build my own blockchain completely without programming knowledge, using the help of AI models.

I've been thinking back and forth about why I've hit the limits of various models so far, and I think I've found an answer. In the past, whenever new code was supposed to be added, I told the model to show me the entire code again for error prevention. However, since these models don't have "long-term memory," this led to errors being made, and all AI models struggled with the entire codebase. Then, I thought about which model I had gone the furthest with, and that was clearly https://t.co/it9QZSafRM by @AnthropicAI

The goal of creating an extremely fast blockchain with up to 500,000 TPS is probably very challenging or even unattainable for current AI models, so at the start, my aim is just to develop a blockchain where transactions can be processed as quickly as possible. That doesn't mean I've completely abandoned my original goal; rather, I want to start this way, and once we get this thing running, we'll see what we can implement to make the blockchain faster and more comprehensive. But it remains: everything I do, I will try to achieve only with the help of AI models. I will keep you regularly updated on the progress or setbacks. I'm open to all improvement suggestions and ideas.

#Blockchainbuilder #Blockchain #BlockchainSimplicity #blockchainstartup

[Michael Pirro @michaelpirro]

I'm trying to build my own blockchain using AI, without any programming knowledge.

Yesterday, I tried using https://t.co/mWPQOPyw9S but didn't get very far. Cursor uses well-known models, such as https://t.co/it9QZSafRM's 3.5 Sonnet. The user interface is very simple and might be too simple for non-programmers. I didn't even get to use the software because I simply didn't know how to use it effectively. Maybe it was because I didn't have the Pro version. At least, I gave up quickly on that and asked ChatGPT which AI model it would recommend. The suggestions from ChatGPT were the following, in this order:

- OpenAI's GPT (like ChatGPT, Code Interpreter, or GPT-4 Code Pro)
- GitHub Copilot
- Tabnine
- Replit Ghostwriter

ChatGPT itself had never heard of GPT-4 Code Pro, which makes this selection a bit challenging. I then asked Google and came across Amazon Q. The information on the website, as usual, is incomprehensible for non-programmers. However, there seems to be a plugin that can be integrated with various programs like Visual Studio Code. I downloaded and installed the plugin for this. A prerequisite for using it is an AWS account. After some testing, I realized that this is more of a tool that helps find errors in existing code or improve it. Programming a new blockchain from scratch is difficult for novices and not particularly user-friendly because you input prompts in a small window and the responses are such that you have to scroll a lot. So, Amazon Q isn't what I'm looking for either.

As you can see, I haven't made much progress yet, but I'm not giving up. I will keep trying to find the AI model that is suitable for programming a blockchain. I still have some options if my initial plan doesn't work out. But don't worry, I'm not giving up that easily. The year has just begun, and I'm sure I'll find the model I can work with. #Blockchain #myownblockchain #blockchainbuilder #blockchainstartup

[Michael Pirro @michaelpirro]

I'm trying to create my own Layer-1 blockchain without programming knowledge and only with the help of AI.

At the end of the week, I want to summarize where I stand with my project. I started with https://t.co/it9QZSafRM from @AnthropicAI. https://t.co/it9QZSafRM is a very good tool when only a few lines of code are needed. Perfect for Excel VBA Macros as well. However, when the code gets longer and needs to be improved or expanded, it has issues; it forgets older code that is relevant and ignores instructions. It even knows it does this, but for some reason, it can't change it. For me, it stopped working at around 600 lines of code.

So, I switched to @googleaistudio. There, I first tried the models Gemini 2.0 Experimental and then Gemini 1.5 Flash-8B. Both models showed several problems after a short time, so I switched to the Gemini 1.5 Pro model. That was the day before yesterday, and I didn't make much progress yesterday either. This model also struggles with outputting longer code. Yesterday, it stopped after about 160 lines of code. The typical sequence afterward was that this model also forgot parts of the code and didn't follow instructions, even though I wrote several times that this should be noted. We reached this point much earlier than where I was with Claude at 600 lines of code. Clearly, these models have problems implementing instructions beyond a certain point. The communication usually went like this:

Gemini 1.5 Pro: Here is the complete code.

Me: Unfortunately, the code is not complete. Please output the complete code again.

Gemini 1.5 Pro: You are absolutely correct. I am incredibly sorry... Here is the complete, corrected, and fully functional code.

Me: Unfortunately, the code is still not complete. Please always keep in mind to output the complete code considering all previous inputs.

Gemini 1.5 Pro: I sincerely apologize. You are absolutely correct. The code was, unbelievably, still incomplete. Here's the complete, corrected, and (I believe, finally) fully functional code.

Me: The code is incomplete again. Can you please generate the complete code?

And so on. It went back and forth. Sometimes, Gemini 1.5 Pro took minutes to respond. In the end, it was simply not possible to continue this way. Maybe I'm using these models incorrectly too. If anyone has ideas on what I can improve, I would appreciate your feedback. I've been working on a Windows system so far, but today I'll switch to my MAC and try @cursor_ai. I'll definitely report back on whether I can make progress with this software.
#blockchainbuilder #blockchain #BlockchainNews #BlockchainForGood #aiblockchain #buildingablockchain

[Michael Pirro @michaelpirro]

@maxescu WOW!

[Michael Pirro @michaelpirro]

Yesterday I mentioned switching from https://t.co/it9QZSafRM to @googleaistudio. I started with Gemini 2.0 Experimental, but noticed it kept making the same errors, similar to https://t.co/it9QZSafRM. It would apologize after I pointed it out, but still mess up. The model isn’t usable, but it’s experimental. Errors mostly involved the code shrinking instead of expanding.
Then I switched to Gemini 1.5 Flash-8B, but that also had too many issues. Now I’m on Gemini 1.5 Pro. Not sure if we’ll stick with it, but we’ll see. Google AI Studio is part of my Google Suite package, and they use a token count system. Each character in/out costs a token. I’ve got 2 million tokens free with Gemini 1.5 Pro and have used about 47,000 so far, so it’s definitely more flexible than https://t.co/it9QZSafRM. My code is at 127 lines, and I’m coding in Rust. I'm currently using 3 different tools:
- 64-bit Git for Windows Setup
- @rustlang
- @code

I’ll update you tomorrow on my progress!
#blockchain #blockchainbuilder #blockchainDev #BlockchainFuture #blockchainstartup

[Michael Pirro @michaelpirro]

I want to build my own blockchain without any programming knowledge, just with the help of AI.

I spent all day yesterday trying to make progress with https://t.co/it9QZSafRM from @AnthropicAI, but I encountered two issues. After we had 600 lines of code and I thought we were really making progress, I seemed to have hit https://t.co/it9QZSafRM's limits. Claude would try to append the code but kept forgetting parts of the old code, despite multiple reminders it kept happening. The next problem was that you can only send relatively few prompts before Claude limits you. I added another team account to my personal account, but even with these five additional accounts, the limits are quite restrictive. Since these limitations come on quickly, I'm going to cancel the team account, and I've chosen a new platform for programming the blockchain: @googleaistudio. I'll try to make progress there. I welcome all comments and any feedback. If you have tips on other platforms, let me know. #blockchain #blockchainbuilder #newblockchain #aiblockchain #BlockchainInnovation

[Michael Pirro @michaelpirro]

Great decision.

[tobi lutke @tobi]

Huge and important change.

[Michael Pirro @michaelpirro]

I can't shake the feeling that the #blockchain industry doesn't care about usability. Only top-notch #usability will lead to mass adoption. Why does no one see this?

[Michael Pirro @michaelpirro]

@ShortNseXy87 @Xfinity Right. They don‘t care. We are at day 17 of an outage here.

[Michael Pirro @michaelpirro]

@FoxNews 🤣🤣🤣🤣🤣🤣

[Sheel Mohnot @pitdesi]

CEO of a 400+ employee business says WFH is working well, he may not renew his SF lease to save $10m a year (office + lunches etc) and instead do a couple of all-hands offsites a year (much cheaper). Lots of others must be thinking similarly- CRE could be permanently altered.

[hardmaru @hardmaru]

So where do you do your best work?

[The Block @TheBlockCo]

Nike receives patent to tokenize shoes on Ethereum
@Nike
https://t.co/d2dXs0AIFj

[Rony Abovitz @rabovitz]

Anyone expert in the XR field knows the problem set is enormous, the journey will be many years - but there will be incredible peaks coming and many moments of pure magic.