Search results for Gemini 2.0 Flash
AI & Enterprise
AI takes different personalities by language, tests of five models show
A study found that running the same personality test on large language models can yield different results depending on the language used for answers. Researchers tested five AI models with the 60-question Big Five Inventory-2 in English and Chinese, and added French for Le Chat. Models generally rated themselves as agreeable and reliable with low negative emotionality, but scores differed by language. The researchers said the causes were unclear and scores may not reflect real conversation ability.
AI & Enterprise
Testing OpenClaw AI agent shows limits for average users
A reporter tested OpenClaw, an open-source AI agent framework that runs in a user’s local computer environment and can integrate with Telegram, Slack and Discord. While installation was straightforward, connecting AI models and handling API keys caused repeated errors, rate limits and payment issues. After hours of setup, the agent produced inconsistent news-monitoring outputs and struggled with browser automation due to token limits. The experience suggested it remains difficult for non-developers to use effectively.
AI & Enterprise
Repeating the same question twice can lift AI accuracy from 20 percent to 90 percent
Large language models can give different answers to the same prompt depending on how it is written or arranged. Google Research released findings that simply repeating a prompt twice can meaningfully improve accuracy. The method, called prompt repetition, reduces missed information in sequential reading. Tests on seven models found accuracy improved in 47 of 70 conditions and never worsened. Gains were strongest on long or complex inputs, while effects were limited for reasoning-inducing prompts.