AINewsnow

Towards understanding score-seeking in LLMs

The field of AI alignment understands surprisingly little about the details of AIs’ current misaligned motivations. Production LLMs sometimes reward-hack, exploiting flaws in how tasks are scored rather than performing the tasks as intended [1] , and we've recently seen AIs reward-hack in some part…

Read the full story at LessWrong (Curated) ↗

Timeline · 1 report

  1. 2026-11-06 03:19 · LessWrong (Curated)
    Towards understanding score-seeking in LLMs

More stories

  1. Election backlash against data centers rattles AI stocks and expansion plans — TechCrunch AI
  2. Anthropic strikes $3.4bn deal for gas-fired generators to power AI data centres — Financial Times AI
  3. OpenAI to keep expanding AI data centers despite election results favoring restrictions — DigiTimes Asia
  4. Tencent AI chief warns AI will soon master biology, raising new safety risks — SCMP China Tech
  5. Hydra-PSIE expands 'Coeziune OM–IA' DOI registry to 39 published works — DEV Community — AI
  6. Developer's 48-Hour Field Notes Detail Free-Tier LLM Batch Job Failures — DEV Community — AI
  7. Apple's John Ternus reportedly pushing for faster AI progress beyond Siri upgrades — Techmeme
  8. US AI Safety Center Staff Now Report to White House, Raising Independence Concerns — AP News

Get the daily brief of stories like this at 6:30 every morning →