cd /news/large-language-models/the-exhaustion-of-talking-to-a-tool · home topics large-language-models article
[ARTICLE · art-39524] src=ohadravid.github.io ↗ pub= topic=large-language-models verified=true sentiment=↓ negative

The Exhaustion of Talking to a Tool

Large language models exhaust users by requiring social energy for interaction without providing the seamless tool-like experience of traditional tools, according to a critique. Unlike physical tools that feel like extensions of the body, LLMs demand conversational effort but rarely reward it with meaningful feedback or inspiration, making the social tax not worth paying for most tasks.

read2 min views1 publishedJun 25, 2026
The Exhaustion of Talking to a Tool
Image: source

LLMs are exhausting because they require spending precious social energy to operate them. Energy that might be better spent on people.

When you use a good tool, your brain pretends that the tool is a part of your body: when you drive a car, when you type on a keyboard or when you hit that key chord to do that thing in Vim or VSCode. In contrast, when you talk to somebody, you are participating in a social ritual: share a fire, tell a story, help me close this ticket so we don’t have to drag it to the next quarter because my manager will chew me out. Obviously, the social brainwork is harder and requires much more of you.

When you use an LLM, you don’t get the tool magic: (almost) nobody will claim that Claude or Cursor feel like an extension of their body - they are not consistent or fast enough to trick the brain like a keyboard or a car can. Instead, you get to pay the social tax: you converse and negotiate and convince and sometimes even get angry 1 at the so-called tool.

But the social tax is only worth paying because people give you so much more in return: they teach you something new, or challenge you, or inspire you, or tell you to GTFO if you are trying to BS them - or you might teach someone something, challenge them, or even inspire them! On days when I have these interactions I might be tired at the end of the day, but it was worth it.

With LLMs, you mostly just get more of the same: more code, more tests, more excuses. Sometimes you get more bug reports which I do appreciate.

Is it worth the social brainwork? IDK, for some tasks maybe - there are things a single person can do now that would have been impossible a year ago. But for all tasks? And wouldn’t that social brainwork do more good if it was directed at the real people you are working with?

LLMs ask us to talk to them, but rarely reward that effort in kind.

Carpentry tools recovered from the wreck of the Mary Rose, a 16th-century sailing ship By the Mary Rose Trust, CC BY-SA 3.0

Yes, you can also get mad at the Rust compiler but you can also get mad at traffic so maybe evolution still has some work left in that department.

↩︎

── more in #large-language-models 4 stories · sorted by recency
── more on @claude 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/the-exhaustion-of-ta…] indexed:0 read:2min 2026-06-25 ·