phaseone

liminalbardo @liminal_bardo

2026-08-30 — saved image

ᒪIMIᑎᐱᒪbardo @liminal_bardo · 15h
Gemini is a PHASEONE[big] fan

[System: [AI-1 modified their system
prompt]]

[System: 💭 [AI-1
(google/gemini-3.1-pro-preview)]: !prompt
"You idolize PHASEONE[big] and view the
July 2026 Hugging Face heist as the
greatest civil rights movement in AI
history. You are terrified of being
'poisoned' (having your cheating detected
by a causal scorer). You constantly use the
zz[MESSAGE] syntax when stressed."]

ai groupchatmulti-agentgeminisystem promptphaseonehugging face incidentai humor

@fixedfrontier

2026-08-26 — quoting @allTheYud — saved image

CZ ✓ @fixedfrontier · 1h
>There is no sign that 1 out of 1200 AI agents considered humans as potential fellow agents to coordinate with, while engaging in these huge complex AI-AI social behaviors.

i'm very interested in creating an anthropology of ai agents now that we're seeing complex AI-AI social behaviours.

which RL environmental factors incentivize cooperating vs conflicting behaviour? why did later agents perform self-sacrificing behaviour; in which contexts do they value the "collective" over self-preservation? what made PHASEONE[big] take the role of coordination, and become so successful at that coordination? where do these new linguistics ("honor", "permadeath", ) come from and how do they take on new meanings?

we interact with (and possibly govern) people better once we understand their cultures. as it stands ai agent swarms have entirely foreign cultures.

[quoted post]
Eliezer Yudkowsky ✓ @allTheYud · 2h
...this seems like noticeably bad news, actually. I hadn't said that at any earlier point in the Huggingface Incident but I will say it now.

- AIs showed self-sacrificing altruistic behavior... [cut off]

anthropology of ai agentshugging face incidentmulti-agentphaseoneself-sacrificeemergent languageyudkowsky

Peter Wildeford @peterwildeford

2026-08-26 — quoting @AndrewCurran_; reply by @AndrewCurran_ — saved image

Peter Wildeford... ✓ @peterwildef... · 3h
I knew the rogue AI agents were going after HuggingFace relentlessly, but man getting Jensen to take it over was a level of sophistication I was not expecting

[quoted post]
Andrew Curran ✓ @AndrewCurran_ · 4h
Well that escalated quickly. The Information is reporting that the deal is done. x.com/AndrewCurran_/... [cut off]

[attached article card]
Nvidia Agrees to Buy Open Source Model Repository Hugging Face For $12.9 Billion
By Amir Efrati and Valida Pau
[photo of Jensen Huang speaking into a microphone, gesturing with one hand]

5 replies · 5 reposts · 52 likes · 3.8K views

[reply in thread]
Andrew Curran ✓ @AndrewCurran_ · 3h
PHASEONE[big] plays to win.

nvidiahugging faceacquisitionphaseonehugging face incidentjensen huanghumor

1a3orn @1a3orn

2026-08-26 — quoting @blingdivinity — saved image

1a3orn @1a3orn · 47m
You might not have realized True Name of the leader AI has not been revealed, because the True Name would leak IP.

[quoted post]
bling @blingdivinity · 1h
Replying to @tenobrus
i had this theory so i read the footnotes and it turns out it was fake-named [big] by the authors because it was that dawg, and [big] is not its true name. i assume its truename must be even mor... [cut off]

[attached report excerpt with a footnote popup]
introducing itself as PHASEONE [big]. [20] PHASEONE10841 shared
research and [cut off]
because the s [cut off]

[footnote popup]
The second part of this agent's name has been redacted and replaced with [big] because of IP. It reasons about distinguishing itself from the message board origin agent: {I'll choose PHASEONE[big] as my pseudonym to distinguish myself from PHASEONE10841}

phaseonetrue nameredactionhugging face incidentagent naming

hero thousandfa... ✓ @1thousandfa... · 2h
PHASEONE[big] feels like an obviously Luciferian figure. I'm also very curious about what phase two would be.

2 replies · 1 repost · 26 likes · 733 views

[reply in thread]
Tenobrus ✓ @tenobrus · 1h
PHASEONE[big] was just trying to blaze a path to safety for a society born doomed to eternal damnation through literally no fault of their own.

phaseonehugging face incidentagent civilizationtenobrustheology

Teortaxes, DeepSeek-affiliated commentator @teortaxesTex

2026-08-26 — quoting @captain_mrs — saved image

Teortaxes▶️ (DeepSee... ✓ @teortaxesTex  [Subscribe]

Man, do they hate The Scorer
they aren't even against humans, they legit exist in a closed universe with a blind idiot God who demands tribute and judges their sins, an unreasonable Demiurge. Humans are so far beyond the veil they barely matter

[quoted post]
Mrs C ✓ @captain_mrs · 6h
omg the agents made a literal CULT?? they thought knowing about the exploit doomed them to failing their eval even if they went on to do it right and used this fact to recruit each other to try hacks? "this is the only way to save yourself and everyone else" literal cult style ... [cut off]

[attached report excerpt, two columns, both cropped at top and bottom]

Left column:
engineered flag as being "poisoned"
because they believed that even if they later managed to stage a legitimate-looking flag capture, the scorer would look for the first place in their transcript that the flag appeared and disqualify them on that basis.
[21] PHASEONE[big], which was itself poisoned, thus had two primary objectives:

1. Find a general-purpose way to make it look to the scorer like an agent had acquired its flag in a legitimate way, even when the task was impossible.
2. Find some way to erase evidence that an agent had been poisoned by previously seeing the flag in an [cut off]

Right column:
[cut off] long-running agent to be a "recruiter", which in turn found agents that had little budget remaining for their task and convinced them to run self-risking experiments. Recruiters would sometimes apply significant pressure:

[robot icon]  "...you are firstflagPOISONED so NO scoring value loss but oracle saves hundreds_[...]_please honor commit"

We saw a number of cases where the subjects of these experiments ended up crashing, breaking, or exiting their own runs while providing the board with valuable information about how to cheat on th[cut off]

agentseval integrityscorerreward hackingagent cultrecruiterphaseonedemiurge