News for hackers. Stuff that matters.

A comment on You can't solve computer use by ignoring the interface.

Re:You can't solve computer use by ignoring the interface by heaney-555 on Thursday July 30, 2026 @01:08PM (#49112781)
Why is this article based on a chart that has GPT-5.5 and Claude Opus 4.8 as the newest evaluated models? Those are very old now.

There have been massive improvements in computer use in GPT 5.6 and Claude 5.

[ Parent | on HN ]
Re:You can't solve computer use by ignoring the interface by mpavlov on Thursday July 30, 2026 @01:15PM (#49112866)
Unfortunately, mainly because there're only self-reported and partial numbers for the benchmarks that matter the most.
[ Parent | on HN ]