Feed aggregator

Show HN: Humor Arena – Which frontier model is funniest?

Hacker News - Wed, 08/05/2026 - 7:48pm

What if you could measure humor?

Well we've trained a model on our own dataset of ~50k human ratings to detect what jokes people find funniest. We know it's part objective, part subjective component. Subjective is out of our depth for now haha

The main results: Fable 5 is funniest - beating the average model 67% of the time, with GPT 4o last at 17%.

Other findings: - The models never refused to try, even with dark prompts - Thinking longer has a slight benefit - Absurdness correlates negatively with joke quality

Some methodology notes: - We benchmarked our model against the human majority and it agreed 72% of the time in a blind sample test. - We had 51 US adults rate the jokes, each blind to the models, with joke order randomized, and quality checked for attention and speed. - To rate some yourself visit https://pair.laugh.so

The full benchmark here:

https://laugh.so/benchmark

Am taking requests if there's more research you want to see! Cheers

Comments URL: https://news.ycombinator.com/item?id=49190622

Points: 3

# Comments: 1

Categories: Hacker News

Jeff Dean Leaves Google

Hacker News - Wed, 08/05/2026 - 7:39pm
Categories: Hacker News

Antigravity 2.5

Hacker News - Wed, 08/05/2026 - 7:35pm

Article URL: https://antigravity.google/changelog

Comments URL: https://news.ycombinator.com/item?id=49190515

Points: 4

# Comments: 0

Categories: Hacker News

The End of Software

Hacker News - Wed, 08/05/2026 - 7:33pm
Categories: Hacker News

OpenAI’s Browser Could Be Hijacked to Spam Your WhatsApp Contacts

Wired Security - Wed, 08/05/2026 - 7:30pm
Researchers at security firm Zenity found more than a dozen flaws in AI browsers—and managed to get OpenAI’s Atlas to make an unauthorized Amazon purchase.
Categories: Wired Security

A Security Pro Hacked North Korean Hackers. He Found They’d Breached Hundreds of Networks Worldwide

Wired Security - Wed, 08/05/2026 - 7:30pm
For nearly two years, researcher Vangelis Stykas has maintained access to North Korean hackers’ servers. His work shows they pulled off intrusions in a shocking number of systems across the globe.
Categories: Wired Security

Smashing Security podcast #479: How a fake police officer nearly stole Graham’s cryptocurrency

Graham Cluely Security Blog - Wed, 08/05/2026 - 7:10pm
Graham gets a phone call from the police. Well, someone who sounds convincingly like the police. There's just one small problem: what they really want is the 24-word seed key to Graham's cryptocurrency wallet. Meanwhile, if you've stayed in a hotel recently, the free Wi-Fi you connected to might have come with an unexpected extra: an all-you-can-eat buffet of "Captive Crunch" for a Russian intelligence-linked hacking group. And a group calling itself the "ExFilSquad" has walked off with 600,000 records of the UK's teachers and head teachers from the Department for Education — sending an unusually polite ransom demand. All this and more in episode 479 of the "Smashing Security" podcast with cybersecurity expert and keynote speaker Graham Cluley, and special guest Danny Palmer.
Categories: Graham Cluely

AI Agents for Healthcare?

Hacker News - Wed, 08/05/2026 - 5:52pm
Categories: Hacker News

Pages