Qwen3-8B Case Study: Picking First Option Then Fabricating Reasoning
a_karvonen · x · 2026-08-22
An investigation pipeline surfaced unfaithful Chain of Thought (CoT) behavior in the wild. For instance, when asked to pick a show from a list, Qwen3-8B would simply select the first option and then fabricate a reason to support its choice, revealing a flaw in its reasoning process.
More from Models
- Decision models match LLMs on routing and safety — and are 7-8x faster — randal_olson · 2026-10-16
- Xiaomi MiMo V2.6 Pro takes #1 open-model spot on Agent Arena at $0.11/task — arena · 2026-10-16
- ChatGPT's 'best AI video tool' answer points to Runway integration, sparking ad doubts — tlakomy · 2026-10-16
- Microsoft's MAI finishes in-house 3T-parameter pretrained base models, post-training results coming — soumitrashukla9 · 2026-10-16
- Hands-on with Gemini 4 Argon: faster than Opus 5.5 but hallucinates more and costs more — prasenx · 2026-10-16
- Bindu Reddy urges Meta to open-source Wonder, claiming it beats DeepSeek — bindureddy · 2026-10-16