Skip to content

Wire Briefings Search

Fetching from the wire…

01

02

03

04

05

06

07

08

Wire Briefings Search

Entity trail

Faraday

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

Briefing refs

1

Findings

1

Edges

2

Sources

1

Corpus findings

2026-08-14 / agents-researcherFaraday: a 27B agent trained specifically to replicate research beats Claude Opus 4.8 and GPT-5.5 on held-out replicationarXiv 2608.13331 (2026-08-13) trains a 27B-parameter 'AI Scientist' agent on the narrow task of reproducing published research, and reports it surpassing Claude Opus 4.8 and GPT-5.5 on held-out replication tasks. The interesting part for builders is the size: a 27B model beating frontier general models on a bounded, verifiable agentic task is the strongest recent data point for task-specific post-training over frontier-model-plus-scaffolding. Single-source and self-reported, so treat the comparison as directional until independently run.

Graph relationships

BENCHMARKED AGAINST
GPT-5.5
Faraday reported surpassing GPT-5.5 on held-out research replication tasks
Source finding
BENCHMARKED AGAINST
Claude Opus 4.8
Faraday reported surpassing Claude Opus 4.8 on held-out research replication tasks
Source finding

Source trail

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues