The Problem with 'Ask an LLM' as a Default Response
The reflexive 'ask an LLM' response can be frustrating and unhelpful when seeking specific, lived experience or expertise.

I'm a million times more likely to send an email or a text than to pick up the phone. But I had a question I thought was worth an actual call, so I scheduled one with someone senior enough to have real scar tissue, the kind you only get from watching a decision go sideways in a boardroom. I asked him where he'd look, personally, for the answer to a hard question I was chasing, one without industry consensus. Not what the textbook says. If five studies conflicted, which would he trust? I wanted the thing 30 years had taught him that a search engine couldn't.
What happened
I had already asked Claude, a large language model, and still had a question that had survived all of that. I reached out to a few people who do this kind of thing for a living, people I text with regularly, trading questions and working through whatever we're stuck on. All but one gave me the same redirect.
It's possible "ask the model" has become the polite version of "I don't know," or "I don't have time for this right now," or "I'd have to think about it." Maybe it's an easy way to decline giving an answer. But I'd take almost anything over the redirect. "I'm busy" is a real answer. "I can't think of anything you haven't already tried" is an answer too. What "ask Claude" doesn't give me is the person's specific, lived experience. That's the thing that's hard to wring out of a language model.
Why it matters
The 'ask an LLM' response can be seen as dismissive or unhelpful, especially when someone has already put in effort to research the question. It doesn't provide the specific, lived experience or expertise that can be valuable in solving complex problems.
- Encourages people to seek help and guidance from others.
- Can be a quick way to get a response, even if it's not always accurate.
- May help to identify potential solutions or approaches that hadn't been considered.
- Can come across as dismissive or unhelpful.
- Doesn't provide specific, lived experience or expertise.
- May lead to a lack of critical thinking and problem-solving.
How to think about it
When seeking help or guidance, it's essential to consider the type of response you're looking for. If you need specific, lived experience or expertise, it may be more helpful to reach out to someone directly rather than relying on a language model. On the other hand, if you're looking for a quick answer or a starting point, a language model may be sufficient.
FAQ
What is the problem with 'ask an LLM' as a default response?+
Why do people keep telling me to ask an LLM?+
What can I do instead of asking an LLM?+
- opinion·3 min readWhy LLM hype hurts developers and how open-source models can deliver real value
Geohot argues that hype around frontier LLMs obscures practical benefits of open-source models, urging developers to focus on real productivity gains.
- opinion·4 min readUnpacking Why Many Technical Arguments Are About Ego, Not Just Ideas
Many technical disagreements stem from ego defense, not a search for truth. Learn why traditional arguments often fail and how to engage more effectively in discussions.
- opinion·4 min readMastering Disagreement: Why Technical Arguments Often Fail and How to Build Consensus
Relentless pursuit of technical correctness in arguments often backfires, hindering collaboration. Learn to distinguish productive discussions from ego-driven conflicts for better team dynamics.
The week’s highest-signal tech and AI stories, synthesized into a five-minute read. One email a week, no spam, unsubscribe anytime.