Valentin Guigon
@guigonv.bsky.social
PhD,
Cognitive neuroscientist at UMD, member of the Social Learning and Decisions Lab. I study decision-making, social learning and the formation/update of human beliefs.
🔗valentinguigon.github.io
Cognitive neuroscientist at UMD, member of the Social Learning and Decisions Lab. I study decision-making, social learning and the formation/update of human beliefs.
🔗valentinguigon.github.io
April 28, 2025 at 4:51 PM
Still ran into the usual [hallucinations, random loops, repetitive tool use, slow responses] on my pc. Server access is still key.
Once resolved, I can see small academic teams using these to level the playing field in the “publish or perish” environment.
Once resolved, I can see small academic teams using these to level the playing field in the “publish or perish” environment.
April 17, 2025 at 2:25 PM
Still ran into the usual [hallucinations, random loops, repetitive tool use, slow responses] on my pc. Server access is still key.
Once resolved, I can see small academic teams using these to level the playing field in the “publish or perish” environment.
Once resolved, I can see small academic teams using these to level the playing field in the “publish or perish” environment.
AI agents to design [tools, roles, workflows, agentic collab]; multi-agent systems to run them. No doubt individuals/companies will rely on this kind of setup - once we downsize the need for massive parameters and RAM.
April 17, 2025 at 2:25 PM
AI agents to design [tools, roles, workflows, agentic collab]; multi-agent systems to run them. No doubt individuals/companies will rely on this kind of setup - once we downsize the need for massive parameters and RAM.
March 10, 2025 at 11:16 AM
Pour mes collègues français, un résumé de l'étude disponible ici: www.insb.cnrs.fr/fr/cnrsinfo/...
Comment la confiance en soi peut nous induire en erreur face à la désinformation
Dans un monde où les réseaux sociaux regorgent d’informations douteuses, il devient essentiel de savoir distinguer le vrai du faux.
www.insb.cnrs.fr
January 26, 2025 at 4:44 PM
Pour mes collègues français, un résumé de l'étude disponible ici: www.insb.cnrs.fr/fr/cnrsinfo/...
I am thrilled to share this collaborative work with Marie Claire Villeval and @jc-dreher.bsky.social, which sheds light on the mechanisms shaping how we navigate today’s complex information landscape.
January 26, 2025 at 4:32 PM
I am thrilled to share this collaborative work with Marie Claire Villeval and @jc-dreher.bsky.social, which sheds light on the mechanisms shaping how we navigate today’s complex information landscape.
As a result, when faced with ambiguous news, individuals often fail to recognize and address gaps in their knowledge, hindering their ability to evaluate subsequent information effectively.
January 26, 2025 at 4:32 PM
As a result, when faced with ambiguous news, individuals often fail to recognize and address gaps in their knowledge, hindering their ability to evaluate subsequent information effectively.
Ambiguity—defined by the precision of the news content and its capacity to polarize opinions (perceived dissensus)—plays a critical role in shaping veracity assessment. It leads individuals to confidently misinterpret both true and fake news, making them vulnerable to systematic errors.
January 26, 2025 at 4:32 PM
Ambiguity—defined by the precision of the news content and its capacity to polarize opinions (perceived dissensus)—plays a critical role in shaping veracity assessment. It leads individuals to confidently misinterpret both true and fake news, making them vulnerable to systematic errors.
Our study reveals that metacognition, not beliefs, drives the demand for information. However, individuals’ metacognition is often uncalibrated: their confidence in discerning true from fake news does not reliably reflect their actual accuracy.
January 26, 2025 at 4:32 PM
Our study reveals that metacognition, not beliefs, drives the demand for information. However, individuals’ metacognition is often uncalibrated: their confidence in discerning true from fake news does not reliably reflect their actual accuracy.