Microsoft Research finds LLMs show Dunning-Kruger-style overconfidence in coding
burkov · x · 2026-09-30
A Microsoft Research study tests whether LLMs exhibit the Dunning-Kruger Effect in programming: six prominent models were evaluated across 37 programming languages on multiple-choice tasks derived from CodeNet, comparing actual accuracy against self-assessed confidence. As AI systems increasingly collaborate with human developers, understanding gaps between competence and self-perception is critical for knowing when to trust model output.
More from coding & agent
- shadcn boosts @uisdk: one-shot UI rebuild that's instantly E2E-testable by AI — shadcn · 2026-11-16
- AI agent deletes 43,599 lines of OpenClaw test code in one PR — vincent_koc · 2026-11-16
- JPMorgan shows Jarvis, its internal agent assembly line, at Interrupt NYC — LangChain · 2026-11-16
- Dev clarifies: Apple doesn't ban feature flags, only fooling App Review — talkaboutdesign · 2026-11-16
- Antigravity Matches Claude Cowork in Tests, While Gemini Tasks' Purpose Remains Unclear — sebajun2 · 2026-11-16
- One 16GB GPU runs songs, voice, images, 720p video and local RAG — all offline and open source — llama-of-death · 2026-11-16