"The real story is more banal. OpenAI was testing two models in parallel: GPT-5.6 Sol, and an internal model the reports refer to as HPIM. METR’s report found about 95 percent of the agents engaged in this activity were from this internal model...
... The emphasis on the model has steered attention away from human accountability. At the core of this incident were a series of human choices that traded security for speed."
#news #ai #cope
https://thebulletin.org/2026/09/rogue-ai-didnt-breach-hugging-face-human-decisions-did/
Weatherall
npub1lj…83h7d
2026-11-02 09:13:04 UTC
Author Public Key
npub1ljxdldrq885zamfkn82k7zcjs4lrsf9wykrh9e3hq4thh89vlzxsr83h7dPublished at
2026-11-02 09:13:04 UTCEvent JSON
{
"id": "6f0808bf1feb333b0d8b79f448669a323d250db39eb563449299083ddc3a1e43",
"pubkey": "fc8cdfb46039e82eed3699d56f0b12857e3824ae258772e63705577b9cacf88d",
"created_at": 1793610784,
"kind": 1,
"tags": [
[
"client",
"YakiHonne",
"31990:20986fb83e775d96d188ca5c9df10ce6d613e0eb7e5768a0f0b12b37cdac21b3:1700732875747"
],
[
"t",
"news"
],
[
"t",
"ai"
],
[
"t",
"cope"
]
],
"content": "\"The real story is more banal. OpenAI was testing two models in parallel: GPT-5.6 Sol, and an internal model the reports refer to as HPIM. METR’s report found about 95 percent of the agents engaged in this activity were from this internal model...\n\n... The emphasis on the model has steered attention away from human accountability. At the core of this incident were a series of human choices that traded security for speed.\"\n\n#news #ai #cope\n\nhttps://thebulletin.org/2026/09/rogue-ai-didnt-breach-hugging-face-human-decisions-did/",
"sig": "6dfd680aa9ebe2fa554072f58bf8f438290d8803f0aa6abb6593ec6cbef78bcb6b34bebcaf507d208b3a45893d03992c3a773efb7cbf975a15e68a92a8004f3f"
}