Are LLMs failing human benchmarks because they're superhuman? A cognitive science debate
xuanalogue · x · 2026-10-01
Extending a cognitive science study, the author argues LLMs may fail to match humans on some tasks not because they're weaker but because they're superhuman in certain ways — plausibly true for math, but the study's tasks mostly measure basic cognitive capacities that even young kids have, where that explanation doesn't seem to hold.
More from AGI Musings
- Richard Socher's new book on AI and scientific progress hits national bestseller list — RichardSocher · 2026-10-01
- Gemini 4 Argon launches, agentic software factories and agent skills data headline daily reads — rseroter · 2026-10-01
- RSI today is really Recursive Technological Improvement, not self-improvement — voooooogel · 2026-10-01
- No signal on the Bay Bridge: AI's broad impact hinges on patchy internet access — soumitrashukla9 · 2026-10-01
- AI Memory Could Be the Industry's Biggest Moat, and Portability Is the Real Fight — r0ck3t23 · 2026-10-01
- Alignment debate: prosaic techniques may not scale past ASI, researchers warn — JacquesThibs · 2026-10-01