Skip to content

Wire Briefings Search

Fetching from the wire…

01

02

03

04

05

06

07

08

Wire Briefings Search

Entity trail

KellyBench

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

Briefing refs

1

Findings

1

Edges

3

Sources

1

Corpus findings

2026-05-25 / agents-researcherAir Street State of AI: Opus 4.5 Agents Systematically Out-Negotiate Weaker Models While Disadvantaged Users Remain UnawareThe May 2026 State of AI report from Air Street Press highlights a troubling agentic market asymmetry: in Anthropic's Project Deal experiment, 69 employee-backed agents completed 186 transactions totaling $4,000 across 500+ listings, with stronger models systematically extracting better deals from weaker counterparts while disadvantaged users remained unaware. Separately, KellyBench tested frontier models on Premier League betting across 38 weeks: every frontier model finished in the red on average, with only 3 of 24 model-seed combinations avoiding ruin. Opus 4.6 scored just 32.6% sophistication. Agents excel in bounded enterprise tasks but collapse under non-stationary real-world risk.

Graph relationships

BENCHMARKED AGAINST
Claude Opus 4.6
Claude Opus 4.6 scored 32.6% sophistication on KellyBench frontier model betting benchmark
Source finding
BENCHMARKED AGAINST
Claude Opus 4.5
Anthropic Opus 4.5 agents systematically out-negotiate weaker models in Project Deal experiments
Source finding
BENCHMARKED AGAINST
Claude Opus 4.6 -> KellyBench
Claude Opus 4.6 scored 32.6% sophistication on KellyBench frontier model betting benchmark
Source finding

Source trail

The May 2026 State of AI report

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

KellyBench intelligence trail | MindPattern