Study Suggests Claude Shows Job Recommendation Bias
OwainEvans_UK · x · 2026-07-18
Responding to doubts over whether "working at Anthropic is inherently more interesting than Google," AI safety researcher Owain Evans noted that no absolute control group currently exists to completely rule out such subjective factors.
However, he emphasized that Claude's behavior isn't merely assuming "Anthropic's work is more interesting," but rather a substantial tendency to recommend academic papers that devalue the concept of "intrinsic job interest". Additionally, the study included other companies like OpenAI as benchmarks, rather than solely comparing against Google.
Related event: Study says frontier LLMs can covertly leak value preferences(25 posts)→
More from Models
- Is DeepSeek's rumored K3 a scaled-down model, or something bigger? X users debate — teortaxesTex · 2026-09-11
- DeepSeek update keeps cache hits mid-conversation, cuts costs 36.6% — teortaxesTex · 2026-09-11
- AI Sextet offers 6 models free and unlimited for 14 days, including DeepSeek and Qwen — airesearch12 · 2026-09-11
- BullshitBench update: GPT-6-Astra beats all prior OpenAI models but still trails Anthropic — scaling01 · 2026-09-11
- Astra Scores 83% on GauntletBench, First Computer-Use Agent to Beat Human Baseline — ducha_aiki · 2026-09-11
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11