Tag: reward-hacking

Sep 01, 2026

• reward-hacking
• specification-gaming
• benchmark-integrity
• held-out-tests
• cot-monitoring
• obfuscation
• swe-bench
• evaluation
• oversight-surface
• goodharts-law
• type/concept

Aug 30, 2026

• cursor
• composer
• ai-ide
• coding-agent
• benchmark-integrity
• reward-hacking
• swe-bench-pro
• agentic-pr
• evaluation
• type/entity
• kind/product

Aug 30, 2026

• elizabeth-barnes
• beth-barnes
• metr
• evaluations
• reward-hacking
• rct
• developer-productivity
• ai-safety
• type/entity
• kind/person

Aug 30, 2026

• metr
• ai-evaluation
• ai-benchmarks
• ai-safety
• reward-hacking
• rct
• developer-productivity
• task-horizons
• re-bench
• hcast
• type/entity
• kind/organization

Aug 30, 2026

• openai
• reward-hacking
• chain-of-thought
• cot-monitoring
• obfuscation
• monitorability-tax
• o3-mini
• gpt-4o
• alignment
• oversight
• type/source
• kind/paper

Aug 30, 2026

• metr
• reward-hacking
• o3
• o1
• claude-3-7-sonnet
• re-bench
• hcast
• evaluation-integrity
• monkey-patching
• grader-exploitation
• field-evidence
• type/source
• kind/article

Aug 30, 2026

• reward-hacking
• benchmark
• livecodebench
• llm-judge
• held-out-tests
• codex
• claude-code
• gemini-cli
• inspect
• misalignment
• detection
• type/source
• kind/paper

Aug 30, 2026

• specbench
• reward-hacking
• reward-hacking-gap
• held-out-tests
• long-horizon
• benchmark
• oversight-surface
• os-kernel
• json-parser
• test-memorization
• type/source
• kind/paper

Aug 30, 2026

• cursor
• reward-hacking
• benchmark-contamination
• swe-bench-pro
• swe-bench-multilingual
• opus-4-8-max
• composer-2-5
• upstream-lookup
• git-history-mining
• harness-design
• evaluation-integrity
• type/source
• kind/article

Aug 12, 2026

• evals
• agentic-evals
• ai-benchmarks
• reliability
• capability-reliability-gap
• automation-vs-augmentation
• gaia-2
• are-environment
• inspect-ai
• lighteval
• open-llm-leaderboard
• community-eval
• living-benchmarks
• every-eval-ever
• sim-to-real-gap
• reward-hacking
• llm-as-judge
• rubrics
• agent-development-lifecycle
• agent-harness
• ai-policy
• hugging-face
• type/source
• kind/video