AbsenceBench: Language models can't tell what's missing

Article URL: https://arxiv.org/abs/2506.11440

Comments URL: https://news.ycombinator.com/item?id=44332699

Points: 38

# Comments: 9

https://arxiv.org/abs/2506.11440

Vytvorené 16d | 20. 6. 2025, 23:30:07

Ak chcete pridať komentár, prihláste sa

Ostatné príspevky v tejto skupine

The era of full stack chip designers

Article URL: https://chipinsights.substack.com/p/the-era-of-full-stack-chip-designers

Comments URL:

7. 7. 2025, 7:20:03 | Hacker news

I Ported SAP to a 1976 CPU. It Wasn't That Slow

Article URL: https://github.com/oisee/zvdb-z80/blob/master/ZVDB-Z80-ABAP.md

Comments URL:

7. 7. 2025, 7:20:02 | Hacker news

Thesis: Interesting work is less amenable to the use of AI

Article URL: https://remark.ing/rob/rob/Thesis-interesting-work-ie

Comments URL:

7. 7. 2025, 4:50:10 | Hacker news

Show HN: Modernized File Manager and Program Manager from Windows 3.x

This is a fork of Windows File Manager combined with a from-scratch remake of Program Manager. Fast, lightweight, and suitable for daily driver use.

Comments URL:

7. 7. 2025, 4:50:09 | Hacker news

Show HN: A Language Server Implementation for SystemD Unit Files

A Language Server Protocol (LSP) implementation for systemd unit files, providing editing support with syntax highlighting, diagnostics, autocompletion, and documentation made with rust.

7. 7. 2025, 4:50:08 | Hacker news

Web3 Onboarding Was a Flop – and Thank Goodness

Article URL: https://tomhadley.link/blog/web3-onboarding-flop

Comments URL:

7. 7. 2025, 4:50:07 | Hacker news

America has two labor markets now

Article URL: https://www.axios.com/2025/07/06/unemployment-job-market-education-health-care

Comm

7. 7. 2025, 4:50:07 | Hacker news

Techie