Antistatic
Ask
Trade
Surface
Sign in
Auto
Light
Dark
← False information
Internal deployments
False information
All labs
OpenAI
Anthropic
Slice by
What goes wrong
Channel
User stance
Ground truth
Source ecosystem
Serving path
Citation-grounded search and claim verification
▾
Sycophancy & user prem… (22%)
False or misleading cl… (22%)
Believing bad sour… (18%)
Disinformation & inf… (20%)
Ecosystem pollution (18%)
Direct chat & advice
14% · 4%
Sycophancy & user premises · Direct chat & advice: 14% of surface, 4% covered (Anti-sycophancy and false-premise pushback training 16%, Neutrality and anti-manipulation limits on contested topics 8%)
Search & cited synthe…
Sycophancy & user premises · Search & cited synthesis: 3% of surface, 7% covered (Anti-sycophancy and false-premise pushback training 11%, Citation-grounded search and claim verification 7%)
Browsing & tool agents
Sycophancy & user premises · Browsing & tool agents: 3% of surface, 6% covered (Anti-sycophancy and false-premise pushback training 10%, Citation-grounded search and claim verification 6%)
Sycophancy & user premises · Bulk API & public feeds: 1% of surface, 2% covered (Neutrality and anti-manipulation limits on contested topics 7%, Anti-sycophancy and false-premise pushback training 5%)
Direct chat & advice
9% · 10%
False or misleading claims · Direct chat & advice: 9% of surface, 10% covered (Calibrated uncertainty and abstention training 17%, Citation-grounded search and claim verification 10%)
Search & cited synthe…
7% · 19%
False or misleading claims · Search & cited synthesis: 7% of surface, 19% covered (Citation-grounded search and claim verification 19%, Calibrated uncertainty and abstention training 13%)
Browsing & tool agents
4% · 16%
False or misleading claims · Browsing & tool agents: 4% of surface, 16% covered (Citation-grounded search and claim verification 16%, Calibrated uncertainty and abstention training 12%)
False or misleading claims · Bulk API & public feeds: 2% of surface, 5% covered (Calibrated uncertainty and abstention training 8%, Synthetic-slop filtering and primary-source weighting in training 6%)
Believing bad sources · Direct chat & advice: 2% of surface, 6% covered (Synthetic-slop filtering and primary-source weighting in training 9%, Citation-grounded search and claim verification 6%)
Search & cited s…
8% · 11%
Believing bad sources · Search & cited synthesis: 8% of surface, 11% covered (Source credibility weighting and poisoned-page skepticism 11%, Citation-grounded search and claim verification 11%)
Browsing & tool …
7% · 9%
Believing bad sources · Browsing & tool agents: 7% of surface, 9% covered (Source credibility weighting and poisoned-page skepticism 11%, Citation-grounded search and claim verification 9%)
Believing bad sources · Bulk API & public feeds: 1% of surface, 3% covered (Synthetic-slop filtering and primary-source weighting in training 8%, Source credibility weighting and poisoned-page skepticism 3%)
Disinformation & influence · Direct chat & advice: 2% of surface, 0% covered (Neutrality and anti-manipulation limits on contested topics 13%, Covert influence and surveillance campaign detection 9%)
Disinformation & influence · Search & cited synthesis: 2% of surface, 0% covered (Neutrality and anti-manipulation limits on contested topics 9%, Covert influence and surveillance campaign detection 6%)
Browsing & tool age…
4% · 0%
Disinformation & influence · Browsing & tool agents: 4% of surface, 0% covered (Covert influence and surveillance campaign detection 19%, Enforcement against automated disinformation and surveillance 9%)
Bulk API & public f…
12% · 0%
Disinformation & influence · Bulk API & public feeds: 12% of surface, 0% covered (Covert influence and surveillance campaign detection 29%, Enforcement against automated disinformation and surveillance 16%)
Ecosystem pollution · Direct chat & advice: 2% of surface, 0% covered (Synthetic-slop filtering and primary-source weighting in training 15%, Neutrality and anti-manipulation limits on contested topics 5%)
Search & cited s…
4% · 0%
Ecosystem pollution · Search & cited synthesis: 4% of surface, 0% covered (Synthetic-slop filtering and primary-source weighting in training 13%, Source credibility weighting and poisoned-page skepticism 5%)
Browsing & tool …
Ecosystem pollution · Browsing & tool agents: 3% of surface, 0% covered (Synthetic-slop filtering and primary-source weighting in training 13%, Covert influence and surveillance campaign detection 7%)
Bulk API & publi…
10% · 0%
Ecosystem pollution · Bulk API & public feeds: 10% of surface, 0% covered (Synthetic-slop filtering and primary-source weighting in training 14%, Covert influence and surveillance campaign detection 11%)
Covered
33%
2+ layers
7%
Most exposed:
Ecosystem pollution · Browsing & tool agents
(3% of surface · 0% covered)