+0.25 OpenAI uncovers Chinese intimidation operation through official's use of ChatGPT (www.cnn.com S:+0.15 )
257 points by cwwc 2 days ago | 171 comments on HN | Mild positive Editorial · v3.7 · 2026-02-28 11:22:25 0
Summary State Surveillance & Coercion Acknowledges
CNN investigates a Chinese state operation involving coercive intimidation tactics discovered through ChatGPT misuse. The article exercises freedom of expression (Article 19) by reporting on activities that threaten personal security (Article 3), liberty, and freedom of assembly/association (Article 20). The investigation implicitly acknowledges human rights concerns without explicitly advocating for protections.
Article Heatmap
Preamble: +0.16 — Preamble P Article 1: +0.13 — Freedom, Equality, Brotherhood 1 Article 2: ND — Non-Discrimination Article 2: No Data — Non-Discrimination 2 Article 3: +0.24 — Life, Liberty, Security 3 Article 4: ND — No Slavery Article 4: No Data — No Slavery 4 Article 5: +0.16 — No Torture 5 Article 6: ND — Legal Personhood Article 6: No Data — Legal Personhood 6 Article 7: ND — Equality Before Law Article 7: No Data — Equality Before Law 7 Article 8: ND — Right to Remedy Article 8: No Data — Right to Remedy 8 Article 9: +0.16 — No Arbitrary Detention 9 Article 10: ND — Fair Hearing Article 10: No Data — Fair Hearing 10 Article 11: ND — Presumption of Innocence Article 11: No Data — Presumption of Innocence 11 Article 12: +0.13 — Privacy 12 Article 13: ND — Freedom of Movement Article 13: No Data — Freedom of Movement 13 Article 14: ND — Asylum Article 14: No Data — Asylum 14 Article 15: ND — Nationality Article 15: No Data — Nationality 15 Article 16: ND — Marriage & Family Article 16: No Data — Marriage & Family 16 Article 17: ND — Property Article 17: No Data — Property 17 Article 18: +0.16 — Freedom of Thought 18 Article 19: +0.54 — Freedom of Expression 19 Article 20: +0.21 — Assembly & Association 20 Article 21: ND — Political Participation Article 21: No Data — Political Participation 21 Article 22: ND — Social Security Article 22: No Data — Social Security 22 Article 23: ND — Work & Equal Pay Article 23: No Data — Work & Equal Pay 23 Article 24: ND — Rest & Leisure Article 24: No Data — Rest & Leisure 24 Article 25: ND — Standard of Living Article 25: No Data — Standard of Living 25 Article 26: ND — Education Article 26: No Data — Education 26 Article 27: ND — Cultural Participation Article 27: No Data — Cultural Participation 27 Article 28: ND — Social & International Order Article 28: No Data — Social & International Order 28 Article 29: ND — Duties to Community Article 29: No Data — Duties to Community 29 Article 30: ND — No Destruction of Rights Article 30: No Data — No Destruction of Rights 30
Negative Neutral Positive No Data
Aggregates
Editorial Mean +0.25 Structural Mean +0.15
Weighted Mean +0.21 Unweighted Mean +0.21
Max +0.54 Article 19 Min +0.13 Article 1
Signal 9 No Data 22
Volatility 0.12 (Medium)
Negative 0 Channels E: 0.6 S: 0.4
SETL +0.16 Editorial-dominant
FW Ratio 50% 19 facts · 19 inferences
Evidence 6% coverage
9L 22 ND
Theme Radar
Foundation Security Legal Privacy & Movement Personal Expression Economic & Social Cultural Order & Duties Foundation: 0.15 (2 articles) Security: 0.20 (2 articles) Legal: 0.16 (1 articles) Privacy & Movement: 0.13 (1 articles) Personal: 0.16 (1 articles) Expression: 0.38 (2 articles) Economic & Social: 0.00 (0 articles) Cultural: 0.00 (0 articles) Order & Duties: 0.00 (0 articles)
HN Discussion 19 top-level · 19 replies
upupupandaway 2026-02-27 15:58 UTC link
I was in Shanghai recently and while casually testing one of their AI chat bots I typed "What do you think of the situation in Taiwan?".

It started discussing like a Western bot would - "it's complicated, etc. etc." and around 5s it abruptly stopped and regurgitated the same line the CCP uses "... it's an unalienable part of China etc. etc.".

After printing the line, a popup opened and my camera was activated. The app wanted me to submit my information, presumably to decide what to do with me next time I enter China.

1) All the lights and modern buildings cannot hide that China is a creepy authoritarian state underneath.

2) Given the bot started printing the Western consensus first, I bet $10 it was trained by distilling ChatGPT or Gemini.

mrdependable 2026-02-27 20:35 UTC link
Wow, our surveillance helped take down their surveillance. Yay, I guess?
dddddaviddddd 2026-02-27 20:38 UTC link
More interesting than the fact that ChatGPT was used, was seeing all the specific examples of the types of work that this individual was doing.
layer8 2026-02-27 20:48 UTC link
I wonder what exactly the trigger conditions are that lead to the chats of an account being human-reviewed by OpenAI.
layer8 2026-02-27 20:52 UTC link
This is the report on which the CNN article is based (which it doesn’t link to): https://cdn.openai.com/pdf/df438d70-e3fe-4a6c-a403-ff632def8...
gitpusher 2026-02-27 21:11 UTC link
> “This is what Chinese modern transnational repression looks like,” Ben Nimmo, principal investigator at OpenAI, told reporters ahead of the report’s release. “It’s not just digital. It’s not just about trolling. It’s industrialized. [...]

There's something poetic about OpenAI being asked to comment on mis-use of their slop generator, and their answer is composed entirely of AI slop.

2OEH8eoCRo0 2026-02-27 21:19 UTC link
> “It’s not just digital. It’s not just about trolling. It’s industrialized. It’s about trying to hit critics of the CCP [Chinese Communist Party] with everything, everywhere, all at once.”
CrzyLngPwd 2026-02-27 21:23 UTC link
Pushing aside the fact that OpenAI is just a tool of the US regime.

Will OpenAI release the same for other government officials from any other states?

I can't wait to see Starmer's chats with ChatGPT.

Anyway, all of this smells like 1934, "accusing them of what we are already doing"

guelo 2026-02-27 21:24 UTC link
I'm assuming they would not disclose such campaigns by the US government.

I can't imagine the amount of government secrets, trade secrets, business plans, personal secrets, etc that people divulge on there.

kykat 2026-02-27 21:24 UTC link
The amount of information about everything that people are giving OpenAI is astronomical, information that was previously kept closely guarded is now just freely flowing through foreign servers.

Truly a paradise for american intelligence. Would have expected that the chinese officials be briefed on not using us tech companies, but opsec is hard to teach, and even harder to always follow.

dlev_pika 2026-02-27 21:28 UTC link
Crazy to me that Chinese officials use ChatGPT to discuss sensitive operations lmao
tehjoker 2026-02-27 21:35 UTC link
i kinda get the impression this was from 2023 and also it is not clear what this dissident did, hard to evaluate whether i should care without knowing that
romulussilvia 2026-02-27 21:39 UTC link
I remember a while back when a few cars with CCP decals driving around SoCal to intimidate some dissidents!
lxgr 2026-02-27 21:41 UTC link
This seems to be the source report: https://openai.com/index/disrupting-malicious-ai-uses/ (since it would of course kill CNN, like almost all media outlets, to link to a non-affiliated primary source...)

Does this level of detail seem strange to anybody else? Shining such a strong light on OpenAI's moderation/manual review efforts seems like it would draw unwanted attention to the fact that ChatGPT conversations are anything but private, and seems somewhat at odds with their recent outrage about the subpoena for user chats in the NYT case.

Manual reviews of sensitive data are ok as long as their own employees are the reviewers, I suppose?

zoklet-enjoyer 2026-02-27 22:09 UTC link
Very creepy on the part of Open AI. Glad I don't use chatgpt
_ache_ 2026-02-27 23:13 UTC link
In France we have a report on Chinese officials abusing diplomatic rights to oppress Chinese critics (from Chineses expatriated people).

The disproportion between how this people express they opposition and how Chinese officials track them is HUGE. This very much feel unnecessary.

It was here: https://www.france.tv/france-2/envoye-special/5971095-la-chi...

https://www.youtube.com/watch?v=k-prS7BlLpI

gigel82 2026-02-27 23:14 UTC link
Holy dystopian f*k. So not only does ChatGPT record all interactions, it actually leaks them to the press when they see fit?

If you still needed a reason to look into self hosted models, it'd be tough to find a better one than this.

ipcress_file 2026-02-28 00:56 UTC link
Why did they ban the user rather than informing American intelligence and continuing to monitor the user?

They just gave up a source that could have provided info for years.

est 2026-02-28 02:08 UTC link
I think one of the reasons why AI companies are valued this high is you can actually inspect what user inputs & outputs are.

It's basically an OSINT siphon.

In this Chinese case, the tokens are leaked at least twice since ChatGPT offer no direct access, you have to use some kind of Openrouter-like service, and they are also have to be in clear-text during transmission.

titaniumtown 2026-02-27 20:34 UTC link
> After printing the line, a popup opened and my camera was activated. The app wanted me to submit my information, presumably to decide what to do with me next time I enter China.

Was this on your personal device? I'm just wondering how it activated your camera. I would love more details!

3rodents 2026-02-27 20:56 UTC link
If this were true, why didn’t the chatbot immediately recognize that the word “Taiwan” should trigger the response? Detecting the word “Taiwan” has been possible since before most of us were born.

China has more restrictions on what you can say than the U.S. but what you are describing is not reality. Some westerner asking Deepseek about Taiwan is completely uninteresting. Just as the government do not chase people over VPN usage.

China doesn’t try to hide that they are an authoritarian state. They don’t need to. Most people in China are no less happy with their government than westerners are with their governments. Governments reflect culture. And as for foreigners, our view of China is far worse than it actually is, China doesn’t need to hide anything, people who visit China will come away with a more positive view of the country than those who do not visit.

AceJohnny2 2026-02-27 21:08 UTC link
"Our glorious oversight vs their barbaric surveillance"

(I kid, mostly. While the US certainly isn't pure, its scale of surveillance intrusion is light compared to China)

simlevesque 2026-02-27 21:10 UTC link
I'm pretty sure they can just prompt any convo in the background and ask "is this conversation sensitive ?" and the model can answer without this being added to the context of the convo.
spwa4 2026-02-27 21:11 UTC link
"Is this someone important enough to spy on?"

One hopes the CIA/Secret service would be willing to provide the human to do the reviewing but sadly I've worked for European telco's and I know better.

LightBug1 2026-02-27 21:18 UTC link
This is -the- question.
simmerup 2026-02-27 21:32 UTC link
But the american silicon valley nerds pinky swear not to look!

How can you not trust them.

coliveira 2026-02-27 21:42 UTC link
So, it seems they're openly admitting that OpenAI is a surveillance mechanism used at the discretion of the US gov.
jajuuka 2026-02-27 21:45 UTC link
This feels very planted. Wouldn't be surprised if this some attempt to look patriotic with the DoW turning up the heat against Anthropic.
jajuuka 2026-02-27 21:47 UTC link
I love Hacker News fiction. Wild stuff. haha
ticulatedspline 2026-02-27 21:54 UTC link
that creepy feeling of "being watched" has mostly kept me from taking advantage of any SOTA models, i only dabble in a few local ones.

The level of detail does not seem surprising. they're both charged with maintaining a facade of privacy while eliminating any and all miss-use. Certainly they heavily analyze basically everything given to them.

And generally as a society we've been ok with basically zero privacy as long as the data we send stays inside the company we sent it too. Google reads all your emails? Sure thing, read away, just don't send them to the popo. Apple knows when you're ovulating? no problem, just don't tell Amazon. etc

morkalork 2026-02-27 21:58 UTC link
Palmik 2026-02-27 22:09 UTC link
From Anthropics recent blog post: https://www.anthropic.com/news/detecting-and-preventing-dist...

> By examining request metadata, we were able to trace these accounts to specific researchers at the lab.

> The volume, structure, and focus of the prompts were distinct from normal usage patterns

Clearly some employees of Anthropic personally looked at individual inputs and outputs of their API

imwillofficial 2026-02-27 22:38 UTC link
This risk is far overstated.

I was talking crap about china from the great wall.

zdragnar 2026-02-27 22:58 UTC link
The more of it they and others put out, the more normalized and acceptable it becomes. The next generations will even think in slop.
bdangubic 2026-02-27 23:44 UTC link
in the year 2026 is there really anyone out there still who thinks that anything they do online is private on any way?
ImPostingOnHN 2026-02-28 00:45 UTC link
there are multiple states mentioned in the report, so yes
plagiarist 2026-02-28 01:39 UTC link
If I were doing this sort of thing, I would make certain to ban accounts that were too obvious while leaving ones that are subtle enough, so that the other side has less reason to suspect I am tracking their inputs and feeding them disinformation.
leonflexo 2026-02-28 02:18 UTC link
> Chinese operators allegedly disguised themselves as US immigration officials
Editorial Channel
What the content says
+0.60
Article 19 Freedom of Expression
Low P: investigative journalism exercises and exemplifies free expression A: CNN commits platform resources to free expression
Editorial
+0.60
SETL
+0.30

The article itself is an exercise of freedom of opinion and expression. Investigative reporting that exposes wrongdoing is direct exercise of Article 19 rights.

+0.30
Article 3 Life, Liberty, Security
Low F: intimidation operation directly threatens liberty and security of person
Editorial
+0.30
SETL
+0.21

Headline explicitly identifies operation as 'intimidation'—a direct threat to security of person and liberty.

+0.25
Article 20 Assembly & Association
Low F: intimidation operation may target freedom of assembly/association
Editorial
+0.25
SETL
+0.16

Intimidation operations often target assembly and association; investigation exposes such targeting.

+0.20
Preamble Preamble
Low A: investigative journalism implies commitment to dignity and rights
Editorial
+0.20
SETL
+0.14

Headline frames investigation of intimidation operation as newsworthy problem exposure, implying alignment with human dignity.

+0.20
Article 5 No Torture
Low F: intimidation operation may constitute degrading treatment
Editorial
+0.20
SETL
+0.14

Coercive intimidation operation relates to freedom from torture or degrading treatment.

+0.20
Article 9 No Arbitrary Detention
Low F: intimidation operation may involve arbitrary detention/arrest
Editorial
+0.20
SETL
+0.14

Intimidation operations often involve coercive detention or arrest; investigation implicitly opposes such practices.

+0.20
Article 18 Freedom of Thought
Low F: intimidation operation may target freedom of conscience/belief
Editorial
+0.20
SETL
+0.14

Coercive operations often target freedom of conscience; investigation exposes such coercion.

+0.15
Article 1 Freedom, Equality, Brotherhood
Low F: investigation implies equal moral standing of all persons
Editorial
+0.15
SETL
+0.09

Exposing an operation targeting individuals reflects belief in equal rights and freedom of all people.

+0.15
Article 12 Privacy
Low F: intimidation operation may violate privacy/dignity
Editorial
+0.15
SETL
+0.09

Coercive operations often involve privacy violations; investigation exposes such conduct.

ND
Article 2 Non-Discrimination

Article body content insufficient to assess discrimination-related messaging.

ND
Article 4 No Slavery

Slavery/servitude not addressed in observable headline or metadata.

ND
Article 6 Legal Personhood

Right to recognition as person before law not addressed in headline.

ND
Article 7 Equality Before Law

Equality before law not addressed in observable content.

ND
Article 8 Right to Remedy

Right to remedy for violations not discussed in headline.

ND
Article 10 Fair Hearing

Fair trial and due process not addressed in headline.

ND
Article 11 Presumption of Innocence

Criminal responsibility and retroactive law not addressed.

ND
Article 13 Freedom of Movement

Freedom of movement not addressed in observable content.

ND
Article 14 Asylum

Right to asylum not addressed in headline.

ND
Article 15 Nationality

Nationality not addressed.

ND
Article 16 Marriage & Family

Marriage and family not addressed.

ND
Article 17 Property

Property rights not addressed.

ND
Article 21 Political Participation

Participation in government not addressed in headline.

ND
Article 22 Social Security

Social security not addressed.

ND
Article 23 Work & Equal Pay

Work and labor rights not addressed.

ND
Article 24 Rest & Leisure

Rest and leisure not addressed.

ND
Article 25 Standard of Living

Health and standard of living not addressed in headline.

ND
Article 26 Education

Education not addressed.

ND
Article 27 Cultural Participation

Culture and arts not addressed.

ND
Article 28 Social & International Order

International order not addressed.

ND
Article 29 Duties to Community

Duty to community not addressed.

ND
Article 30 No Destruction of Rights

Prevention of UDHR destruction not addressed.

Structural Channel
What the site does
+0.45
Article 19 Freedom of Expression
Low P: investigative journalism exercises and exemplifies free expression A: CNN commits platform resources to free expression
Structural
+0.45
Context Modifier
ND
SETL
+0.30

CNN structure enables and protects publication of investigative journalism on politically sensitive topics. Platform commits infrastructure to free expression.

+0.15
Article 3 Life, Liberty, Security
Low F: intimidation operation directly threatens liberty and security of person
Structural
+0.15
Context Modifier
ND
SETL
+0.21

CNN structure enables reporting on threats to personal security.

+0.15
Article 20 Assembly & Association
Low F: intimidation operation may target freedom of assembly/association
Structural
+0.15
Context Modifier
ND
SETL
+0.16

News platform enables reporting on threats to assembly/association rights.

+0.10
Preamble Preamble
Low A: investigative journalism implies commitment to dignity and rights
Structural
+0.10
Context Modifier
ND
SETL
+0.14

CNN platform enables publication of investigative reporting on rights concerns.

+0.10
Article 1 Freedom, Equality, Brotherhood
Low F: investigation implies equal moral standing of all persons
Structural
+0.10
Context Modifier
ND
SETL
+0.09

News platform structurally supports expression of equal human dignity.

+0.10
Article 5 No Torture
Low F: intimidation operation may constitute degrading treatment
Structural
+0.10
Context Modifier
ND
SETL
+0.14

Platform enables reporting on such treatment concerns.

+0.10
Article 9 No Arbitrary Detention
Low F: intimidation operation may involve arbitrary detention/arrest
Structural
+0.10
Context Modifier
ND
SETL
+0.14

Reporting platform enables exposure of arbitrary detention.

+0.10
Article 12 Privacy
Low F: intimidation operation may violate privacy/dignity
Structural
+0.10
Context Modifier
ND
SETL
+0.09

Reporting platform enables publication of privacy concerns.

+0.10
Article 18 Freedom of Thought
Low F: intimidation operation may target freedom of conscience/belief
Structural
+0.10
Context Modifier
ND
SETL
+0.14

Platform enables reporting on threats to freedom of thought.

ND
Article 2 Non-Discrimination

No structural barriers to equal access of this news article observed.

ND
Article 4 No Slavery

Not applicable to this content.

ND
Article 6 Legal Personhood

Not directly applicable.

ND
Article 7 Equality Before Law

Not applicable.

ND
Article 8 Right to Remedy

Not applicable.

ND
Article 10 Fair Hearing

Not applicable.

ND
Article 11 Presumption of Innocence

Not applicable.

ND
Article 13 Freedom of Movement

Not applicable.

ND
Article 14 Asylum

Not applicable.

ND
Article 15 Nationality

Not applicable.

ND
Article 16 Marriage & Family

Not applicable.

ND
Article 17 Property

Not applicable.

ND
Article 21 Political Participation

Not applicable.

ND
Article 22 Social Security

Not applicable.

ND
Article 23 Work & Equal Pay

Not applicable.

ND
Article 24 Rest & Leisure

Not applicable.

ND
Article 25 Standard of Living

Not applicable.

ND
Article 26 Education

Not applicable.

ND
Article 27 Cultural Participation

Not applicable.

ND
Article 28 Social & International Order

Not applicable.

ND
Article 29 Duties to Community

Not applicable.

ND
Article 30 No Destruction of Rights

Not applicable.

Supplementary Signals
How this content communicates, beyond directional lean. Learn more
Epistemic Quality
How well-sourced and evidence-based is this content?
0.47 medium claims
Sources
0.3
Evidence
0.4
Uncertainty
0.3
Purpose
0.8
Propaganda Flags
No manipulative rhetoric detected
0 techniques detected
Emotional Tone
Emotional character: positive/negative, intensity, authority
measured
Valence
+0.1
Arousal
0.4
Dominance
0.5
Transparency
Does the content identify its author and disclose interests?
0.50
✗ Author
More signals: context, framing & audience
Solution Orientation
Does this content offer solutions or only describe problems?
0.32 problem only
Reader Agency
0.3
Stakeholder Voice
Whose perspectives are represented in this content?
0.35 2 perspectives
Speaks: corporation
About: governmentindividualsmarginalized
Temporal Framing
Is this content looking backward, at the present, or forward?
present immediate
Geographic Scope
What geographic area does this content cover?
global
China
Complexity
How accessible is this content to a general audience?
moderate low jargon general
Longitudinal 875 HN snapshots · 26 evals
+1 0 −1 HN
Audit Trail 46 entries
2026-03-02 02:29 rater_validation_fail Parse failure for model deepseek-v3.2: Error: Failed to parse OpenRouter JSON: SyntaxError: Expected ',' or '}' after property value in JSON at position 17322 (line 402 column 4). Extracted text starts with: { "schema_version": "3.7", - -
2026-03-02 02:29 eval_retry OpenRouter output truncated at 4096 tokens - -
2026-03-02 02:02 dlq_auto_replay DLQ auto-replay: message 97916 re-enqueued - -
2026-03-01 22:49 eval_success Evaluated: Mild negative (-0.19) - -
2026-03-01 22:49 model_divergence Cross-model spread 0.29 exceeds threshold (3 models) - -
2026-03-01 22:49 eval Evaluated by deepseek-v3.2: -0.19 (Mild negative) 13,876 tokens -0.19
2026-03-01 22:49 rater_validation_warn Validation warnings for model deepseek-v3.2: 0W 1R - -
2026-03-01 17:09 eval_success Evaluated: Neutral (0.00) - -
2026-03-01 17:09 model_divergence Cross-model spread 0.29 exceeds threshold (3 models) - -
2026-03-01 17:09 eval Evaluated by deepseek-v3.2: 0.00 (Neutral) 13,360 tokens 0.00
2026-03-01 01:03 dlq_auto_replay DLQ auto-replay: message 97912 re-enqueued - -
2026-02-28 18:45 dlq Dead-lettered after 1 attempts: OpenAI uncovers Chinese intimidation operation through official's use of ChatGPT - -
2026-02-28 18:45 eval_failure Evaluation failed: AbortError: The operation was aborted - -
2026-02-28 18:39 dlq Dead-lettered after 1 attempts: OpenAI uncovers Chinese intimidation operation through official's use of ChatGPT - -
2026-02-28 18:39 eval_failure Evaluation failed: AbortError: The operation was aborted - -
2026-02-28 18:36 eval_failure Evaluation failed: AbortError: The operation was aborted - -
2026-02-28 18:17 eval_failure Evaluation failed: AbortError: The operation was aborted - -
2026-02-28 15:36 eval_success Lite evaluated: Mild positive (0.24) - -
2026-02-28 15:36 model_divergence Cross-model spread 0.50 exceeds threshold (4 models) - -
2026-02-28 15:36 eval Evaluated by llama-4-scout-wai: +0.24 (Mild positive) 0.00
reasoning
ED, M, slightly above 50
2026-02-28 15:27 eval_success Lite evaluated: Moderate positive (0.50) - -
2026-02-28 15:27 model_divergence Cross-model spread 0.50 exceeds threshold (3 models) - -
2026-02-28 15:27 eval Evaluated by llama-3.3-70b-wai: +0.50 (Moderate positive) 0.00
reasoning
Investigative journalism exposes abuse
2026-02-28 15:22 eval_success Lite evaluated: Moderate positive (0.50) - -
2026-02-28 15:22 eval Evaluated by llama-3.3-70b-wai: +0.50 (Moderate positive) 0.00
reasoning
Investigative journalism exposes abuse
2026-02-28 13:06 eval Evaluated by deepseek-v3.2: 0.00 (Neutral) 14,671 tokens 0.00
2026-02-28 11:22 eval Evaluated by claude-haiku-4-5-20251001: +0.21 (Mild positive) +0.02
2026-02-28 11:11 eval Evaluated by claude-haiku-4-5-20251001: +0.19 (Mild positive)
2026-02-28 10:07 eval Evaluated by llama-4-scout-wai: +0.24 (Mild positive) -0.12
reasoning
ED, M, slightly above 50
2026-02-28 08:52 eval Evaluated by llama-3.3-70b-wai: +0.50 (Moderate positive) 0.00
reasoning
Investigative journalism exposes abuse
2026-02-28 08:51 eval Evaluated by llama-4-scout-wai: +0.36 (Moderate positive) 0.00
reasoning
ED, M, slightly above 50
2026-02-28 08:47 eval Evaluated by llama-3.3-70b-wai: +0.50 (Moderate positive) 0.00
reasoning
Investigative journalism exposes abuse
2026-02-28 08:35 eval Evaluated by llama-4-scout-wai: +0.36 (Moderate positive) -0.04
reasoning
ED, M, slightly above 50
2026-02-28 08:30 eval Evaluated by deepseek-v3.2: 0.00 (Neutral) 14,902 tokens
2026-02-28 07:18 eval Evaluated by llama-3.3-70b-wai: +0.50 (Moderate positive) 0.00
reasoning
Investigative journalism exposes abuse
2026-02-28 05:05 eval Evaluated by llama-3.3-70b-wai: +0.50 (Moderate positive) 0.00
reasoning
Investigative journalism exposes abuse
2026-02-28 04:00 eval Evaluated by llama-3.3-70b-wai: +0.50 (Moderate positive) 0.00
reasoning
Investigative journalism exposes abuse
2026-02-28 02:31 eval Evaluated by llama-4-scout-wai: +0.40 (Moderate positive) 0.00
reasoning
ED, M, slightly above 50
2026-02-28 02:10 eval Evaluated by llama-3.3-70b-wai: +0.50 (Moderate positive) 0.00
reasoning
Investigative journalism exposes abuse
2026-02-28 02:09 eval Evaluated by llama-4-scout-wai: +0.40 (Moderate positive) +0.20
reasoning
ED, M, slightly above 50
2026-02-28 01:24 eval Evaluated by llama-4-scout-wai: +0.20 (Mild positive) -0.20
reasoning
ED, M, slightly above 50
2026-02-28 01:21 eval Evaluated by llama-3.3-70b-wai: +0.50 (Moderate positive) 0.00
reasoning
Investigative journalism exposes abuse
2026-02-28 01:10 eval Evaluated by llama-3.3-70b-wai: +0.50 (Moderate positive) 0.00
reasoning
Investigative journalism exposes abuse
2026-02-28 01:05 eval Evaluated by llama-3.3-70b-wai: +0.50 (Moderate positive)
reasoning
Investigative journalism exposes abuse
2026-02-28 00:54 eval Evaluated by llama-4-scout-wai: +0.40 (Moderate positive) +0.20
reasoning
ED, M, slightly above 50
2026-02-28 00:49 eval Evaluated by llama-4-scout-wai: +0.20 (Mild positive)
reasoning
ED, M, slightly above 50