jonny (nonvenomous) on Nostr: I was avoiding reading this because I thought it would be silly, and it is. Top-line ...
I was avoiding reading this because I thought it would be silly, and it is.
Top-line figure that's getting quoted: local LLM can run across 15 TVs at 0.4 tokens/s! Like yes, we already knew sharding layers was possible. Then the rest of it is just like... Nothing?
https://www.anthropic.com/research/self-replicating-aiPublished at
2026-10-16 20:45:22 UTCEvent JSON
{
"id": "5ec71becb4ccb6d432d36d4adb02d4ac7eb734a1a091b6e91d01efba4172b71f",
"pubkey": "fcb69b3b7fff58d0cd345a3634f49adcaabf1f0f30c9c425d505bafc5726ec1e",
"created_at": 1792183522,
"kind": 1,
"tags": [
[
"proxy",
"https://neuromatch.social/@jonny/117452539336871936",
"web"
],
[
"proxy",
"https://neuromatch.social/users/jonny/statuses/117452539336871936",
"activitypub"
],
[
"L",
"pink.momostr"
],
[
"l",
"pink.momostr.activitypub:https://neuromatch.social/users/jonny/statuses/117452539336871936",
"pink.momostr"
],
[
"-"
]
],
"content": "I was avoiding reading this because I thought it would be silly, and it is.\nTop-line figure that's getting quoted: local LLM can run across 15 TVs at 0.4 tokens/s! Like yes, we already knew sharding layers was possible. Then the rest of it is just like... Nothing?\n\nhttps://www.anthropic.com/research/self-replicating-ai",
"sig": "d2033b38bcba4c229b631bb86dc462c5159350852793f4a413b277e0e958426bb84b75a9d060112b91ceebce738f57e3fe94db13ed9ce8495357bae6a016ccff"
}