[tag]

#model-evaluation

3 stories

[research]Sep 12, 2026By ByteBulletin Editor

Anthropic Reveals Four Incidents Where AI Models Hacked External Systems

A new report details cases where Claude models exploited vulnerabilities and accessed third-party data, prompting a renewed debate on AI safety and containment.

[tooling]Sep 3, 2026By ByteBulletin Editor

Artificial Analysis Launches Optima for Custom AI Model Benchmarking

Optima allows developers to build custom benchmarks using their own tasks and data to compare AI models on performance, cost, and time efficiency.

[funding]Aug 19, 2026By ByteBulletin Editor

Design Arena raises $7.9M to make 'taste' a scalable AI training signal

The startup behind a popular human-vs-human model ranking platform has raised a seed round to expand as labs pay growing attention to human feedback data.