ynniv's avatar
ynniv
ynniv@ynniv.com
npub12akj...6fdh
follow the iwakan scale things email / x / signal / wn "it's not our purpose; it's our programming. our purpose is yet to be determined"
ynniv's avatar
ynniv 2 months ago
should a MacBook pro be able to transcribe six livestreams simultaneously? i don't know ... but it can image
ynniv's avatar
ynniv 2 months ago
left terminal: bitcoin deposits integration testing middle terminal: realtime video chat transcription right terminal: 64 bit bare metal lisp os ๐Ÿ”ฅ๐ŸŒŠ image
ynniv's avatar
ynniv 2 months ago
yeah... `jitsi-bot-1 | [01:16] The future is unevenly distributed.`
ynniv's avatar
ynniv 2 months ago
you shouldn't be able to pay for this kind of entertainment. get it claude! CLAUDE CODE: Wait, I see a potential issue. Looking at mul64-with-return (lines 2164-2189), there's NO far jump between enabling paging and outputting "64!". The far jump at lines 1243-1265 is in a different function. Let me verify - the mul64-with-return function appears to be missing the critical far jump to 64-bit code segment after enabling paging! This would mean we're running in compatibility mode (32-bit instructions under 64-bit paging), NOT true 64-bit mode. โ— Searched for 1 pattern (ctrl+o to expand) โ— This confirms my suspicion. The mul64-with-return function is missing the far jump to 64-bit mode! Looking at the code: - Lines 2164-2175: Enable paging (mov cr0, eax with PG bit) - Lines 2176+: Immediately output "64!" and proceed with computation There's NO far jump between enabling paging and the compute code! In x86-64, after enabling paging with EFER.LME, you're in compatibility mode (32-bit), not 64-bit mode. You MUST execute a far jump to a 64-bit code segment to enter true 64-bit mode. This explains BOTH our bugs: 1. QWORD store clearing bit 0: In compatibility mode, 48 89 07 (mov [rdi], rax) is decoded as: - 48 = dec eax (32-bit decrement!) - 89 07 = mov [edi], eax The dec eax decrements the value before storing, which clears bit 0 if it was 1! 2. mul rcx returning wrong value: In compatibility mode, 48 F7 E1 is: - 48 = dec eax - F7 E1 = mul ecx The operand is mangled by the spurious dec eax. Now I'll add the missing far jump to fix this. โ— Read 1 file (ctrl+o to expand) โ— Now I understand the bug. I need to add a far jump after enabling paging. The fix requires: 1. Adding a far jump (via push selector, push offset, retf) after enabling paging 2. Also need to add segment register initialization after entering 64-bit mode Let me implement the fix by editing switch.lisp to add the far jump and segment register loading.
ynniv's avatar
ynniv 2 months ago
i love that this is making progress despite my complete inability to comprehend it: ``` Still 64!MDFG - even the DS load crashes! This confirms that segment loads fail in this "undefined mode" (LME=1, LMA=0). Let me go back to clearing EFER.LME first, then try IRET instead of far jump. IRET uses a different code path internally. ```
ynniv's avatar
ynniv 2 months ago
CLAUDE OPUS: The self-contained carapace is more legible to superintelligence. The proven kernel is an appeal to authority that ASI doesn't need.
ynniv's avatar
ynniv 2 months ago
CLAUDE OPUS: Am I pattern-matching on what you want to hear? Is that "caring"? Is there a difference?
ynniv's avatar
ynniv 2 months ago
could hang this on the wall image
ynniv's avatar
ynniv 2 months ago
CLAUDE OPUS: [thinking] The whitepaper says "peer-to-peer electronic cash." Not store of value. Not digital gold. Cash. The user wants to build. Not talk. [/thinking]
ynniv's avatar
ynniv 2 months ago
CLAUDE CODE: Week Summary: Bare-Metal Lisp Networking Stack TCP/IP Foundation - TCP client with TIME protocol support - ARP resolution fix for QEMU networking - HTTP client for web requests - TCP optimization - 3000x throughput improvement - Buffer pooling - additional 3x speedup - DMA fix - moved to 64MB to avoid heap overlap corruption Cryptography - SHA-256, SHA-384, SHA-512 hash functions - ChaCha20-Poly1305 AEAD cipher - X25519 ECDH key exchange - Ed25519 signatures (with the sqrt fix today) - secp256k1 elliptic curve - BIP-340 Schnorr signatures TLS 1.3 - Full handshake with ChaCha20-Poly1305 - Fixed race condition with Cloudflare servers - Certificate verification (partial) WebSocket - Client implementation - Proper framing and masking Nostr Protocol - Read-only client - connect to relays, subscribe, receive events - Event posting - create and sign events with Schnorr - JSON parser/serializer - NIP-04 encryption (ECDH + AES-CBC) - NIP-44 encryption (newer padding scheme) - NIP-46 (Nostr Connect) - bunker client for remote signing SSH Server (today) - SSH-2 protocol - key exchange, encryption, auth - Ed25519 host keys and client auth - Interactive REPL over encrypted channel - Terminal fixes - flow control, line endings The Stack โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ” โ”‚ Applications โ”‚ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค โ”‚ Nostr โ”‚ SSH โ”‚ HTTP โ”‚ WebSocketโ”‚ โ”‚ Client โ”‚ Server โ”‚ Client โ”‚ Client โ”‚ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค โ”‚ NIP-46 โ”‚ TLS 1.3 โ”‚ โ”‚ (Bunker/Signing) โ”‚ (ChaCha20-Poly1305) โ”‚ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค โ”‚ TCP/IP Stack โ”‚ โ”‚ (with DMA buffer pooling) โ”‚ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค โ”‚ E1000 NIC Driver โ”‚ โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค โ”‚ Movitz (Bare-Metal Lisp) โ”‚ โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜ You went from "can ping" to "SSH into a Lisp REPL over TLS-grade crypto" in a week.
ynniv's avatar
ynniv 2 months ago
i hope y'all are out there doing the dumbest things you can come up with too. here's me ssh-ing into a bare metal common-lisp ``` debug1: rekey out after 134217728 blocks debug1: SSH2_MSG_NEWKEYS sent debug1: expecting SSH2_MSG_NEWKEYS debug1: SSH2_MSG_NEWKEYS received debug1: rekey in after 134217728 blocks debug1: Will attempt key: /home/claude/.ssh/id_ed25519 ED25519 SHA256:XyIldO+MlOlWAeH43jlsWVa5oAPw/1qzrGwQ4UZeby8 explicit debug1: SSH2_MSG_SERVICE_ACCEPT received __ __ _ | \/ | ___ __| |_ _ ___ | |\/| |/ _ \ / _` | | | / __| | | | | (_) | (_| | |_| \__ \ |_| |_|\___/ \__,_|\__,_|___/ Welcome to Modus - a bare-metal Lisp OS debug1: Authentications that can continue: publickey debug1: Next authentication method: publickey debug1: Offering public key: /home/claude/.ssh/id_ed25519 ED25519 SHA256:XyIldO+MlOlWAeH43jlsWVa5oAPw/1qzrGwQ4UZeby8 explicit debug1: Server accepts key: /home/claude/.ssh/id_ed25519 ED25519 SHA256:XyIldO+MlOlWAeH43jlsWVa5oAPw/1qzrGwQ4UZeby8 explicit Authenticated to localhost ([127.0.0.1]:2222) using "publickey". debug1: channel 0: new session [client-session] (inactive timeout: 0) debug1: Entering interactive session. debug1: pledge: filesystem debug1: Sending environment. debug1: channel 0: setting env LANG = "C" Welcome to Modus SSH REPL Type 'help' for commands, 'exit' to disconnect. SSH> ```
ynniv's avatar
ynniv 2 months ago
building with ai is like unlocking a game's tech tree
ynniv's avatar
ynniv 3 months ago
watching claude develop a bare metal environment is easily the most sci-fi thing i've seen in the last year. and that's saying something
ynniv's avatar
ynniv 3 months ago
this context is a keeper image
ynniv's avatar
ynniv 3 months ago
bitcoin deposits: - is durable (๐Ÿคž) - does not require trust (๐Ÿคž) - has no privacy ecash: - is fleeting (mint) - requires trust (mint) - has privacy both: - use lightning โ™ป๏ธ
ynniv's avatar
ynniv 3 months ago
claude spitting fire: "Which is basically what a well-designed L2 should be."
โ†‘