niftycent.com
NiftyCent
CZ
Přihlášení
Tržiště
Slevy

AI Agent Benchmarks Are Broken

Article URL: https://ddkang.substack.com/p/ai-agent-benchmarks-are-broken

Comments URL: https://news.ycombinator.com/item?id=44531697

Points: 3

# Comments: 0

https://ddkang.substack.com/p/ai-agent-benchmarks-are-broken

Vytvořeno 6h | 11. 7. 2025 13:20:03


Chcete-li přidat komentář, přihlaste se

Ostatní příspěvky v této skupině

Top DNS domains seen on the Quad9 recursive resolver array each day
Top DNS domains seen on the Quad9 recursive resolver array each day

Article URL: https://github.com/Quad9DNS/quad9-domains-top500

Comments URL:

11. 7. 2025 17:50:10 | Hacker news
Turmeric is the culprit in a global lead poisoning mystery (2024)
Turmeric is the culprit in a global lead poisoning mystery (2024)

Article URL: https://www.npr.org/sections/goats-and-soda/2024/0

11. 7. 2025 17:50:10 | Hacker news
Kimi K2
Kimi K2

Article URL: https://twitter.com/Kimi_Moonshot/status/1943687594560332025

Comments URL:

11. 7. 2025 17:50:08 | Hacker news
Astronomers race to study interstellar interloper
Astronomers race to study interstellar interloper

Article URL: https://www.science.org/content/article/astronomers-race-study-interstellar-interloper

11. 7. 2025 17:50:08 | Hacker news
In a First, Solar Was Europe's Biggest Source of Power Last Month
In a First, Solar Was Europe's Biggest Source of Power Last Month

Article URL: https://e360.yale.edu/digest/solar-biggest-power-source-europe-june-2025

Comments URL:

11. 7. 2025 17:50:07 | Hacker news
Pa. House passes 'click-to-cancel' subscription bills
Pa. House passes 'click-to-cancel' subscription bills

Article URL: https://www.pennlive.com/news/2025/07/pa-house

11. 7. 2025 17:50:05 | Hacker news
Repaste Your MacBook (But Don't)
Repaste Your MacBook (But Don't)

Article URL: https://christianselig.com/2025/07/repaste-macbook/

Comments URL:

11. 7. 2025 15:30:15 | Hacker news
Techie
Techie