MCP servers -> add actual data to hope for better guesses.
Intermingle with parsers that check correctness of other guesses.
All of these are like force vectors that push guesses, mold guesses.
But there are no models there. Your head has many. If llm had models, it would stick to them instead of being on a wind of next token train/generator, what we call in humanized way, halucinations (thank marketing for misleading).
[@david_chisnall](https://infosec.exchange/@david_chisnall ) Prof Heino Falcke (npub1xn9…u8sx)
Mikalai
npub1pl…d049p
2026-07-19 00:14:03 UTC
in reply to nevent1q…qqag
Author Public Key
npub1pl24t9ex94xd6tk7cwfdxrzt0lhmte8206heu8kf8n9vu57wxphqdd049pSeen on
wss://relay.momostr.pinkPublished at
2026-07-19 00:14:03 UTCEvent JSON
{
"id": "5a6beda0cb2c6d05d9a6a3069d721bb14ceef5eee21a8d0161a366c22d232973",
"pubkey": "0fd55597262d4cdd2edec392d30c4b7fefb5e4ea7eaf9e1ec93ccace53ce306e",
"created_at": 1784420043,
"kind": 1,
"tags": [
[
"p",
"2aad90c13120482441b028cb1eefad12fafca60fa257c35fe7aedf5c94c6b90a"
],
[
"e",
"bdc5fe80b3f275cb2fc78bd5439c38ab27a637234907b4b88be3504d667da31f",
"",
"root",
"34cb25e939e097b437faa001259c8404b2f788968d6e6e153a1b3734bd4f5bd7"
],
[
"proxy",
"https://privacysafe.social/@mikalai/116943751949961718",
"web"
],
[
"e",
"522e6c1648e9e11223fe958d2eb2f5499355f8e0828f4eb396c68733c2b8661b",
"",
"reply",
"0fd55597262d4cdd2edec392d30c4b7fefb5e4ea7eaf9e1ec93ccace53ce306e"
],
[
"p",
"34cb25e939e097b437faa001259c8404b2f788968d6e6e153a1b3734bd4f5bd7"
],
[
"p",
"8a30e1f5176e1c530ac88aec455539e3fe2b5d7f5d3ce0b674392bbaac83281b"
],
[
"p",
"0fd55597262d4cdd2edec392d30c4b7fefb5e4ea7eaf9e1ec93ccace53ce306e"
],
[
"proxy",
"https://privacysafe.social/users/mikalai/statuses/116943751949961718",
"activitypub"
],
[
"L",
"pink.momostr"
],
[
"l",
"pink.momostr.activitypub:https://privacysafe.social/users/mikalai/statuses/116943751949961718",
"pink.momostr"
],
[
"-"
]
],
"content": "MCP servers -\u003e add actual data to hope for better guesses.\nIntermingle with parsers that check correctness of other guesses.\nAll of these are like force vectors that push guesses, mold guesses.\nBut there are no models there. Your head has many. If llm had models, it would stick to them instead of being on a wind of next token train/generator, what we call in humanized way, halucinations (thank marketing for misleading).\n\n [@david_chisnall](https://infosec.exchange/@david_chisnall ) nostr:npub1xn9jt6feuztmgdl65qqjt8yyqje00zyk34hxu9f6rvmnf020t0tsytu8sx",
"sig": "431954c14fd31fd81b953f8e7e50963687eb1a07ca3bb5214fda393eeba5ebd4bfee803ef67eea59721cf2a168e8e218bd918c0a7552347a3eedec4ef2ba573c"
}