Karsten Johansson<p>People have low expectations for AI. I asked ChatGPT (paid account, not the free stuff) what would make ChatGPT better. I think the answer is a lot higher quality than what people keep saying one should expect. This is what I got:</p><p>--- My Prompt:<br>With DeepSeek, there are things it is very good at, but it fails quickly and rather spectacularly. Your models tend to break down as well, but somewhere there must be a model that will be able to stay on topic, even when the topic changes, so that conversations move around like human conversations move around subject-to-subject. What would take ChatGPT over the top?</p><p>--- ChatGPT reply:<br>Here’s what it’ll take to get closer to that human-like conversation flow:</p><ol><li>Long-Term Memory That Actually Works. Most models either have no memory or they remember only in a clunky, artificial way.</li></ol><p>A better memory system would not just recall facts, but contextual relevance—like “we talked about LLM efficiency two days ago and you hate cheerleader language.”</p><p>It has to be smart recall, not just data storage.</p><ol><li><p>Thread Awareness<br>Imagine a model that can say: “You mentioned DeepSeek earlier. Should I compare it again now that we’ve brought up open-source tools?”<br>That requires models to track not just words, but conversational branches—like a tree, not a straight line.</p></li><li><p>Graceful Fallbacks<br>When a model doesn’t know, it should gracefully pivot, not hallucinate or go off-topic. This kind of conversational “stability” is rare and subtle.</p></li></ol><p>Most models that fail “spectacularly,” as you said, are trying to bluff through complexity instead of narrowing scope or clarifying.</p><ol><li>Hybrid Contextual ReasoningThe future model needs to reason across subjects rather than switching on and off.</li></ol><p>If we're talking about language models, and you shift to science fiction, it should be able to bring up Asimov or neural networks in storytelling—bridging topics, not just hopping between them.</p><p>Right now, most models either:</p><p>Stay sharp but shallow (good at Q&A, bad at memory), or</p><p>Drift into friendly nonsense (chatty, but brittle)</p><p>The sweet spot will be a system that grows with you across time and topics—and doesn’t forget what you value in a conversation.</p> <p>....</p><p>When you see stuff posted online meant to minimize the quality of output possible, This was a single question with no leader. I think this is the kind of answer we <em>want</em> from our AI devices.</p><p>Thoughts? Feel free to tear this response apart. It needs that kind of human analysis.</p><p><a href="https://infosec.exchange/tags/ai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ai</span></a> <a href="https://infosec.exchange/tags/openai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>openai</span></a> <a href="https://infosec.exchange/tags/deepseek" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>deepseek</span></a> <a href="https://infosec.exchange/tags/intelligence" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>intelligence</span></a> <a href="https://infosec.exchange/tags/chatgpt" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>chatgpt</span></a> <a href="https://infosec.exchange/tags/claude" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>claude</span></a> <a href="https://infosec.exchange/tags/gemini" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>gemini</span></a> <a href="https://infosec.exchange/tags/perplexity" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>perplexity</span></a> <a href="https://infosec.exchange/tags/copilot" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>copilot</span></a> <a href="https://infosec.exchange/tags/jasper" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>jasper</span></a></p>