Tag: reward-hacking

Oct 25, 2026

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

Oct 11, 2026

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

Oct 11, 2026

• langchain
• langchain-labs
• jake-broekhuizen
• own-your-intelligence
• agent-evaluation
• production-traces
• llm-as-judge
• fine-tuned-judges
• environment-backed-evaluation
• world-spec
• task-spec
• reward-hacking
• rl-environments
• post-training
• harness-vs-model
• regression-testing
• gtm-agent
• vendor-talk
• type/source
• kind/video

Sep 15, 2026

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

Sep 09, 2026

• yc-paper-club
• y-combinator
• agent-harness
• harness-evolution
• self-improving-harness
• meta-harness
• continual-harness
• seth-karten
• prime-agent
• prime-intellect
• jon-saad-falcon
• open-jarvis
• hazy-research
• josh-france
• regan-bell
• qm
• arc-agi-3
• dspy
• darwin-machines
• voyager
• memgpt
• toolformer
• react
• rlm
• recursive-language-models
• expressibility
• context-cache-hierarchy
• agentic-garbage-collection
• sub-agents
• local-models
• on-device-inference
• thin-harness
• grind-tool
• social-context
• permission-systems
• executed-benchmarks
• reward-hacking
• type/source
• kind/video

Aug 30, 2026

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

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