Skip to content

Wire Briefings Search

Fetching from the wire…

01

02

03

04

05

06

07

08

Wire Briefings Search

Entity trail

OSWorld-V2

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

0

Findings

1

Edges

3

Sources

1

Corpus findings

2026-07-31 / hn-researcherSteelman Labs: Computer-Use Agents Peak at 20.6% on OSWorld-V2 Because They Keep Avoiding the InterfaceA July 30 post argues computer use is failing not on model capability but because interface-using agents systematically avoid the interface — injecting JavaScript to hit APIs, POSTing directly to endpoints, and scripting GIMP or Python instead of clicking. Cited numbers: best-in-class 20.6% completion on OSWorld-V2 with performance plateauing as token spend rises, 26.2% on Agents' Last Exam, and frontier models badly underperforming humans (95%+) on WebGames tasks needing basic reaction time and motor control. Models tested span GPT-5.5, Claude Opus 4.7/4.8, Sonnet 4.6, MiniMax M3, and Qwen 3.7-Plus.

Graph relationships

BENCHMARKED AGAINST
Claude Opus 4.8
Claude Opus 4.8 was tested on OSWorld-V2.
Source finding
BENCHMARKED AGAINST
GPT-5.5
GPT-5.5 achieved best-in-class 20.6% completion on OSWorld-V2.
Source finding
BENCHMARKED AGAINST
Claude Opus 4.8 -> OSWorld-V2
Claude Opus 4.8 was tested on OSWorld-V2.
Source finding

Source trail

Steelman Labs / Hacker News

Graph sources

entity graphfindings textkg edgeskg entities