Can LLMs with reasoning + web search reliably fact-check political claims?
We evaluated 15 models from OpenAI, Google, Meta, and DeepSeek on 6,000+ PolitiFact claims (2007–2024).
Short answer: Not reliably—unless you give them curated evidence.
arxiv.org/abs/2511.18749
Can LLMs with reasoning + web search reliably fact-check political claims?
We evaluated 15 models from OpenAI, Google, Meta, and DeepSeek on 6,000+ PolitiFact claims (2007–2024).
Short answer: Not reliably—unless you give them curated evidence.
arxiv.org/abs/2511.18749
It’s just another enemies list in disguise ⤵️
It’s just another enemies list in disguise ⤵️
This race is down to the wire, and we're leaving it all on the field. Sign up today!
Fri & Mon: tr.ee/final-sprint
Sat (with @jimmcgovernma.bsky.social !) & Sun: tr.ee/weekend-phonebank
This race is down to the wire, and we're leaving it all on the field. Sign up today!
Fri & Mon: tr.ee/final-sprint
Sat (with @jimmcgovernma.bsky.social !) & Sun: tr.ee/weekend-phonebank
Seems the NSF quietly archived ALL calls for DDRIG grants in the SBE directorate. This is a massive blow for PhD students wanting to do cutting-edge social science research. 🏺🧪
www.nytimes.com/2025/11/26/u...
My evidence for that: the right did exactly this to government websites. So they were projecting what they planned to do onto us.
My evidence for that: the right did exactly this to government websites. So they were projecting what they planned to do onto us.
I don’t say this lightly: if there were any justice in this world, the people responsible for this devastation would be in jail
www.on-ramps.com/jobs/3518
www.on-ramps.com/jobs/3518
Gift link: www.bloomberg.com/news/article...
Gift link: www.bloomberg.com/news/article...
THIS is what our information ecosystem supports. Twitter just made it 1% more visible.
asbruckman.medium.com/x-added-acco...
With cites to @katestarbird.bsky.social
asbruckman.medium.com/x-added-acco...
With cites to @katestarbird.bsky.social