Discover ANY AI to make more online for less.

select between over 22,900 AI Tool and 17,900 AI News Posts.

<
New
Agents
Marketing
Video
Image
Music
Coding
Communication
Education
Travel
>

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

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 AI chatbots become dramatically less reliable in longer conversations, new study finds appeared first on THE DECODER.

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.

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

<p>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 [...]

Match Score: 76.17

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

<p><img width="1536" height="1024" src="https://the-decoder.com/wp-content/uploads/2025/05/AI-Chatbots-Impact-Labor-Market.jpg" class="attachment-full size- [...]

Match Score: 68.35

How to make your smartphone last longer
How to make your smartphone last longer

<p>Replacing a smartphone every two years is partially why <a data-i13n="cpos:1;pos:1" href="https://weee-forum.org/ws_news/of-16-billion-mobile-phones-possessed-worldwide-5-3- [...]

Match Score: 59.07

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

<p><img width="1536" height="1024" src="https://the-decoder.com/wp-content/uploads/2025/04/rlvf_illustration_reinforcment_learning_tree.png" class="attachme [...]

Match Score: 44.10

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

<p><img width="1456" height="816" src="https://the-decoder.com/wp-content/uploads/2025/03/growth_chart.png" class="attachment-full size-full wp-post-image&q [...]

Match Score: 43.70

ChatGPT can now remember all your past conversations
ChatGPT can now remember all your past conversations

<p>The next time you conclude a conversation with ChatGPT, it will save what you said to memory, even if you don&#39;t ask it explicitly to do so. &quot;We have greatly improved memory i [...]

Match Score: 40.95

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

<p><img width="1920" height="1080" src="https://the-decoder.com/wp-content/uploads/2024/06/DALL-E-3-GPT-4o-Comparison-Cubes-Stacked.jpg" class="attachment-f [...]

Match Score: 40.29

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

<p><img width="2400" height="1260" src="https://the-decoder.com/wp-content/uploads/2025/04/Anthropic-Claude-Education.webp" class="attachment-full size-full [...]

Match Score: 39.89

Study finds AI search engines struggle with news attribution
Study finds AI search engines struggle with news attribution

<p><img width="1456" height="816" src="https://the-decoder.com/wp-content/uploads/2024/06/perplexity_newspaper_illustration.png" class="attachment-full size [...]

Match Score: 39.89