niftycent.com
NiftyCent
SK
Prihlásiť sa
Marketplace
Zľavy

Constitutional Classifiers: Defending against universal jailbreaks

Article URL: https://www.anthropic.com/research/constitutional-classifiers

Comments URL: https://news.ycombinator.com/item?id=42920119

Points: 34

# Comments: 16

https://www.anthropic.com/research/constitutional-classifiers

Vytvorené 6mo | 3. 2. 2025, 19:20:11


Ak chcete pridať komentár, prihláste sa

Ostatné príspevky v tejto skupine

How we made JSON.stringify more than twice as fast
How we made JSON.stringify more than twice as fast

Article URL: https://v8.dev/blog/json-stringify

Comments URL: https://news.ycombinat

4. 8. 2025, 21:30:16 | Hacker news
Objects should shut up
Objects should shut up

Article URL: https://dustri.org/b/objects-should-shut-the-fuck-up.html

Comments URL:

4. 8. 2025, 21:30:14 | Hacker news
Why Greptile just does code reviews and doesn't also generate code
Why Greptile just does code reviews and doesn't also generate code

Article URL: https://www.greptile.com/blog/auditor

Comments URL: https://news.yco

4. 8. 2025, 21:30:12 | Hacker news
The Revolution of Token-Level Rewards
The Revolution of Token-Level Rewards

Article URL: https://www.levroai.com/blog/revolution-of-token-rewards-08-01-2025

Comments URL:

4. 8. 2025, 21:30:12 | Hacker news
Show HN: Sidequest.js – Background jobs for Node.js using your database
Show HN: Sidequest.js – Background jobs for Node.js using your database

Hey HN,

I'm the maintainer of node-cron (5M+ downloads/month), and I recently built Sidequest.js, a background job runner for Node.js inspired by Oban (Elixir) and Sidekiq (Rails).

It solves s

4. 8. 2025, 21:30:11 | Hacker news
Qwen-Image: Crafting with native text rendering
Qwen-Image: Crafting with native text rendering

https://huggingface.co/Qwen/Qwen-Image

4. 8. 2025, 21:30:11 | Hacker news
NASA's Curiosity picks up new skills
NASA's Curiosity picks up new skills

Article URL: https://www.jpl.nasa.gov/news/marking-13-years-on-mars-nasas-curiosity-picks-up-n

4. 8. 2025, 21:30:10 | Hacker news
Techie
Techie