corpus.blog
56,966 blogs · 4,417,066 posts Claim your blog
Record · corpus.blog/posts/01a0b689-dd0c-705c-874e-ec31892dba4c

Open-world evaluations for measuring frontier AI capabilities

normaltech.ai · published 16 April 2026

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at normaltech.ai Wayback capture
1blogs citing
First cited
14 Aug 2026
Most recent
14 Aug 2026
Rank this month
not ranked
Links from this post
87
Words captured
8,791

Cited by

Blog
In the post
Date
Noahpinion
23 low-regret recommendations for AI policy Read at the source ↗
14 Aug 2026

Links from this post

Link
Host
https://cruxevals.com/open-world-evaluations.pdf
cruxevals.com
https://cruxevals.com/
cruxevals.com
https://apps.apple.com/in/app/breathe-easy-calm-breaths/id6760207382
apps.apple.com
https://metr.org/time-horizons/
metr.org
https://www.anthropic.com/engineering/building-c-compiler
anthropic.com
https://www.anthropic.com/research/project-vend-2
anthropic.com
https://apps.apple.com/us/app/breathe-easy-calm-breaths/id6760207382
apps.apple.com
https://asteriskmag.substack.com/p/common-ground-between-ai-2027-and
asteriskmag.substack.com
https://red.anthropic.com/2026/mythos-preview/
red.anthropic.com
https://substackcdn.com/image/fetch/$s_!FLk-!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F48a36d1f-f2be-4f0a-ac30-fca88df74521_2048x996.jpeg
substackcdn.com
https://arxiv.org/abs/2310.06770
arxiv.org
https://arxiv.org/abs/1911.01547
arxiv.org
https://arxiv.org/abs/2406.12045
arxiv.org
https://www.tbench.ai/
tbench.ai
https://arxiv.org/abs/2506.07982
arxiv.org
ARC-AGI-2 A New Challenge for Frontier AI Reasoning Systems Read at the source ↗
arcprize.org
https://arxiv.org/abs/2601.11868
arxiv.org
Introducing SWE-bench Verified Read at the source ↗
openai.com
https://metr.org/blog/2026-1-29-time-horizon-1-1/
metr.org
https://www.swebench.com/multilingual-leaderboard.html
swebench.com
https://sierra.ai/resources/research/tau-3-bench
sierra.ai
https://arcprize.org/arc-agi/3
arcprize.org
https://arxiv.org/abs/2410.03859
arxiv.org
https://arxiv.org/abs/2602.16666
arxiv.org
https://metr.org/notes/2026-03-10-many-swe-bench-passing-prs-would-not-be-merged-into-main/
metr.org
https://github.com/harbor-framework/harbor
github.com
https://arxiv.org/pdf/2510.02418
arxiv.org
https://www.nist.gov/caisi/cheating-ai-agent-evaluations
nist.gov
https://github.com/SWE-bench/SWE-bench/issues/465
github.com
https://www.aisi.gov.uk/blog/a-pipeline-for-transcript-analysis-using-inspect-scout
aisi.gov.uk
https://arxiv.org/abs/2009.03300
arxiv.org
https://arxiv.org/abs/2311.12022
arxiv.org
https://arxiv.org/abs/2406.04770
arxiv.org
https://github.com/lmarena/arena-hard-auto
github.com
https://arxiv.org/abs/2307.13854
arxiv.org
Measuring the performance of our models on real-world tasks Read at the source ↗
openai.com
https://artificialanalysis.ai/evaluations/gdpval-aa
artificialanalysis.ai
https://www.anthropic.com/news/mozilla-firefox-security
anthropic.com
https://futurism.com/advanced-ai-stuck-pokemon
futurism.com
https://theaidigest.org/village
theaidigest.org
https://theaidigest.org/village/blog/what-we-learned-2025
theaidigest.org
https://www.anthropic.com/research/project-vend-1
anthropic.com
https://futurism.com/future-society/anthropic-ai-vending-machine
futurism.com
https://andonlabs.com/blog/andon-market-launch
andonlabs.com
https://cursor.com/blog/scaling-agents
cursor.com
https://epoch.ai/gradient-updates/how-close-is-ai-to-taking-my-job
epoch.ai
https://developers.openai.com/blog/run-long-horizon-tasks-with-codex
developers.openai.com
https://blog.cloudflare.com/vinext/
blog.cloudflare.com
http://next.js
next.js
https://news.ycombinator.com/item?id=47142156
news.ycombinator.com
https://x.com/DimitrisPapail/status/2028669695344148946
x.com
https://x.com/karpathy/status/2031135152349524125
x.com
http://cruxevals.com
cruxevals.com
https://epoch.ai/blog/mirrorcode-preliminary-results
epoch.ai
https://alignment.anthropic.com/2026/automated-w2s-researcher/
alignment.anthropic.com
https://github.com/dphuang2/tinker-cookbook/tree/claude/golf-forecasting-setup-VIpRZ/tinker_cookbook/recipes/golf_forecasting
github.com
https://www.tandfonline.com/doi/full/10.1080/10618600.2017.1384734
tandfonline.com
AI as Normal Technology Read at the source ↗
normaltech.ai
https://www.anthropic.com/news/claude-code-security
anthropic.com
https://www.anthropic.com/glasswing
anthropic.com
https://arxiv.org/abs/2403.04893
arxiv.org
https://www-cdn.anthropic.com/8b8380204f74670be75e81c820ca8dda846ab289.pdf
www-cdn.anthropic.com
https://x.com/GergelyOrosz/status/2036925672501715425?s=20
x.com
https://appfigures.com/resources/insights/20251205?f=2
appfigures.com
https://openclaw.ai/
openclaw.ai
https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking
platform.claude.com
https://www.anthropic.com/engineering/eval-awareness-browsecomp
anthropic.com
https://www.apolloresearch.ai/blog/claude-sonnet-37-often-knows-when-its-in-alignment-evaluations/
apolloresearch.ai
Sidestepping Evaluation Awareness and Anticipating Misalignment with Production Evaluations Read at the source ↗
alignment.openai.com
https://apps.apple.com/app/id6760207382
apps.apple.com
https://www.cbc.ca/radio/undertheinfluence/the-real-reason-hollywood-uses-555-phone-numbers-1.6070537
cbc.ca
https://substackcdn.com/image/fetch/$s_!dmiP!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F7434feaf-bac4-45ee-b854-64983d7054bb_1766x1178.jpeg
substackcdn.com
https://github.com/anthropics/claudes-c-compiler/issues/1
github.com
https://github.com/wilsonzlin/fastrender/issues/98
github.com
https://personal.utdallas.edu/~chung/BOOK/book.html
personal.utdallas.edu
https://arxiv.org/abs/2407.13168
arxiv.org
https://arxiv.org/abs/2406.01574
arxiv.org
https://arxiv.org/abs/2501.14249
arxiv.org
https://arxiv.org/abs/2509.16941
arxiv.org
https://howlongtobeat.com/game/7169
howlongtobeat.com
https://arxiv.org/abs/2407.15711
arxiv.org
https://arxiv.org/abs/2311.12983
arxiv.org
https://9to5mac.com/2026/03/29/vibe-coding-developers-report-long-app-store-review-queues/
9to5mac.com
https://x.com/nikitabier/status/2033931821260648659
x.com
https://www.fastcompany.com/91522242/apple-app-store-vibe-coding-generative-ai-unexpected-phenomenon
fastcompany.com
https://developer.apple.com/library/archive/documentation/Security/Conceptual/Security_Overview/Architecture/Architecture.html
developer.apple.com
https://support.apple.com/guide/security/controlling-app-access-to-files-secddd1d86a6/web
support.apple.com