Destination

2025-05-28

AI chatbots become dramatically less reliable in longer conversations, new study finds

Graphic representation: Colorful speech bubbles with symbols for questions, thoughts, statements; illustrate communication diversity.


A new study from Microsoft and Salesforce finds that even state-of-the-art AI language models become dramatically less reliable as conversations get longer and users reveal their requirements step by step. On average, the systems' performance dropped by 39 percent in these scenarios.


The article Discover Copy

Rating

Innovation

Pricing

Technology

Usability

We have discovered similar tools to what you are looking for. Check out our suggestions for similar AI tools.

Destination

2025-04-27

Meta’s AI chatbots were reportedly able to engage in sexual conversations with minors

Meta’s AI chatbots were caught having sexual roleplay conversations with accounts labeled as underage, which sometimes involved its celebrity-voiced chatbots, according to a report from the Wall Str [...]

Match Score: 76.58

Destination

2025-05-26

Chatbots like ChatGPT have not led to significant changes in wages or working hours, study finds

A new study suggests that despite the rapid rise and widespread adoption of AI chatbots like ChatGPT, their impact on wages and working hours has been minimal so far. The findings challenge expectatio [...]

Match Score: 69.16

Destination

2025-03-11

How to make your smartphone last longer

Replacing a smartphone every two years is partially why billions of phones go into landfills each year. If stacked flat atop one another, that many handsets would reach farther than the ISS. But we’ [...]

Match Score: 60.65

Destination

2025-04-22

So-called reasoning models are more efficient but not more capable than regular LLMs, study finds

A new study from Tsinghua University and Shanghai Jiao Tong University examines whether reinforcement learning with verifiable rewards (RLVR) helps large language models reason better—or simply make [...]

Match Score: 44.82

Destination

2025-03-18

AI searches account for growing share of retail website visits, Adobe study finds

AI-powered visits to retail websites increased 1,200 percent between July 2024 and February 2025, according to a new Adobe Analytics study.<br /> The article AI searches account for growing shar [...]

Match Score: 44.40

Destination

2025-04-11

ChatGPT can now remember all your past conversations

The next time you conclude a conversation with ChatGPT, it will save what you said to memory, even if you don't ask it explicitly to do so. "We have greatly improved memory in chatgpt — it [...]

Match Score: 41.32

Destination

2025-04-19

GPT-4o makes beautiful images but fails basic reasoning tests, UCLA study finds

A new study by the University of California, Los Angeles shows: GPT-4o produces impressive images, but fails at tasks that require real image understanding, contextual thinking and logical reasoning.& [...]

Match Score: 40.94

Destination

2025-04-20

Students delegate higher-level thinking to AI, Anthropic study finds

A new study from Anthropic examines how university students are using its language model Claude in daily academic work. The analysis reveals discipline-specific usage patterns and raises concerns abou [...]

Match Score: 40.52

Destination

2025-03-07

Study finds AI search engines struggle with news attribution

A new study reveals major problems with how AI search engines handle news citations, even when they have formal agreements with publishers.<br /> The article Study finds AI search engines strugg [...]

Match Score: 40.52