I've been looking around a bit, including on GitHub, and I noticed that the files are extremely small and contain far too little code. This surprised me a lot, so I started reading the code more closely. Perhaps someone here can offer an explanation, because I don't quite understand it. 1. The network code generates a standard libp2p identity using `generate_ed25519()`, and the transport uses `noise::new`. This contradicts your quoted website statement that the P2P handshake is replaced by ML-KEM-1024. The code here shows a classic libp2p/Noise network handshake, not a PQ-KEM network handshake. 2. Cargo.toml includes pqcrypto-dilithium, and the Fun88 20211 module contains genuine Dilithium5/ML-DSA-like signing and verification logic. However, there are no hits for ML-KEM, ml_kem, liboqs, or oqs in the repository snippet displayed by GitHub. This reinforces the impression: PQ signatures, yes; PQ network stack, no. 3. The mining module explicitly states: iterate nonces until SHA-256d(header) < target. This is correct as a starting point, but it looks like CPU/reference mining logic, not a serious ASIC integration stack or a complete mining ecosystem. I also see no evidence of midstate optimization or stratum-level complexity within the mining module itself. 4. The consensus module is structured as GhostDAG/GhostDAG-Q, with blue/red coloring, blue_score, and k-cluster comments. Nevertheless, at around 523 lines, it's very compact for something that's supposed to run at 10 BPS, handle finality claims, and offer attack tolerance. 5. bootstrap_peers is empty by default, SEED_NODES is empty???, and even the example bootstrap peer is commented out??. This doesn't look like a mature, robust, bootstrappable mainnet P2P network. Something's wrong here, guys, don't use the compiled code!!!!! At best, this code is an unfinished demo, not production code. However, I suspect otherwise and warn everyone against using the pre-compiled bins.
I've been looking around a bit, including on GitHub, and I noticed that the files are extremely small and contain far too little code. This surprised me a lot, so I started reading the code more closely. Perhaps someone here can offer an explanation, because I don't quite understand it. 1. The network code generates a standard libp2p identity using `generate_ed25519()`, and the transport uses `noise::new`. This contradicts your quoted website statement that the P2P handshake is replaced by ML-KEM-1024. The code here shows a classic libp2p/Noise network handshake, not a PQ-KEM network handshake. 2. Cargo.toml includes pqcrypto-dilithium, and the Fun88 20211 module contains genuine Dilithium5/ML-DSA-like signing and verification logic. However, there are no hits for ML-KEM, ml_kem, liboqs, or oqs in the repository snippet displayed by GitHub. This reinforces the impression: PQ signatures, yes; PQ network stack, no. 3. The mining module explicitly states: iterate nonces until SHA-256d(header) < target. This is correct as a starting point, but it looks like CPU/reference mining logic, not a serious ASIC integration stack or a complete mining ecosystem. I also see no evidence of midstate optimization or stratum-level complexity within the mining module itself. 4. The consensus module is structured as GhostDAG/GhostDAG-Q, with blue/red coloring, blue_score, and k-cluster comments. Nevertheless, at around 523 lines, it's very compact for something that's supposed to run at 10 BPS, handle finality claims, and offer attack tolerance. 5. bootstrap_peers is empty by default, SEED_NODES is empty???, and even the example bootstrap peer is commented out??. This doesn't look like a mature, robust, bootstrappable mainnet P2P network. Something's wrong here, guys, don't use the compiled code!!!!! At best, this code is an unfinished demo, not production code. However, I suspect otherwise and warn everyone against using the pre-compiled bins.

I've been looking around a bit, including on GitHub, and I noticed that the files are extremely small and contain far too little code. This surprised me a lot, so I started reading the code more closely. Perhaps someone here can offer an explanation, because I don't quite understand it. 1. The network code generates a standard libp2p identity using `generate_ed25519()`, and the transport uses `noise::new`. This contradicts your quoted website statement that the P2P handshake is replaced by ML-KEM-1024. The code here shows a classic libp2p/Noise network handshake, not a PQ-KEM network handshake. 2. Cargo.toml includes pqcrypto-dilithium, and the Fun88 20211 module contains genuine Dilithium5/ML-DSA-like signing and verification logic. However, there are no hits for ML-KEM, ml_kem, liboqs, or oqs in the repository snippet displayed by GitHub. This reinforces the impression: PQ signatures, yes; PQ network stack, no. 3. The mining module explicitly states: iterate nonces until SHA-256d(header) < target. This is correct as a starting point, but it looks like CPU/reference mining logic, not a serious ASIC integration stack or a complete mining ecosystem. I also see no evidence of midstate optimization or stratum-level complexity within the mining module itself. 4. The consensus module is structured as GhostDAG/GhostDAG-Q, with blue/red coloring, blue_score, and k-cluster comments. Nevertheless, at around 523 lines, it's very compact for something that's supposed to run at 10 BPS, handle finality claims, and offer attack tolerance. 5. bootstrap_peers is empty by default, SEED_NODES is empty???, and even the example bootstrap peer is commented out??. This doesn't look like a mature, robust, bootstrappable mainnet P2P network. Something's wrong here, guys, don't use the compiled code!!!!! At best, this code is an unfinished demo, not production code. However, I suspect otherwise and warn everyone against using the pre-compiled bins.

I've been looking around a bit, including on GitHub, and I noticed that the files are extremely small and contain far too little code. This surprised me a lot, so I started reading the code more closely. Perhaps someone here can offer an explanation, because I don't quite understand it. 1. The network code generates a standard libp2p identity using `generate_ed25519()`, and the transport uses `noise::new`. This contradicts your quoted website statement that the P2P handshake is replaced by ML-KEM-1024. The code here shows a classic libp2p/Noise network handshake, not a PQ-KEM network handshake. 2. Cargo.toml includes pqcrypto-dilithium, and the Fun88 20211 module contains genuine Dilithium5/ML-DSA-like signing and verification logic. However, there are no hits for ML-KEM, ml_kem, liboqs, or oqs in the repository snippet displayed by GitHub. This reinforces the impression: PQ signatures, yes; PQ network stack, no. 3. The mining module explicitly states: iterate nonces until SHA-256d(header) < target. This is correct as a starting point, but it looks like CPU/reference mining logic, not a serious ASIC integration stack or a complete mining ecosystem. I also see no evidence of midstate optimization or stratum-level complexity within the mining module itself. 4. The consensus module is structured as GhostDAG/GhostDAG-Q, with blue/red coloring, blue_score, and k-cluster comments. Nevertheless, at around 523 lines, it's very compact for something that's supposed to run at 10 BPS, handle finality claims, and offer attack tolerance. 5. bootstrap_peers is empty by default, SEED_NODES is empty???, and even the example bootstrap peer is commented out??. This doesn't look like a mature, robust, bootstrappable mainnet P2P network. Something's wrong here, guys, don't use the compiled code!!!!! At best, this code is an unfinished demo, not production code. However, I suspect otherwise and warn everyone against using the pre-compiled bins.