Sure, Claude Code is nothing short of magic… until you run out of tokens :-P
But here’s a thought I found interesting.
By now, we know that given a specific deliverable, your chances of getting it from the LLM increase if
- you provide as many details as you can about what you need done and how you’d prefer to have it done
- you’re in a position to evaluate the output and ask for amendments
- actually take the time to evaluate the output and ask for amendments
Well, as it turns out
- we’re not really sure what we want
- we can’t be bothered to provide details
- we’re unwilling and/or unable to evaluate the output
- we’re quite cavalier about using the LLM’s work, despite all of the above
- when things go sideways, we assume no responsibility, then turn to our preferred medium and rant about LLMs’ idiocy
On the other hand, empirical data suggests that the most frequent complaint people have about work is about their direct manager. They feel that their manager
- has no clue what they do and no interest to find out/ facilitate
- feels entitled to results despite vague requests, unrealistic deadlines, last minute changes etc
- shows little appreciation for their effort
- will throw them under the bus if things don’t go as planned
I’m utterly convinced LLMs gave all of us the chance to be managers.
We took it and became just as bad as the managers we vent to friends about.
The only missing piece of the puzzle is a thread in Moltbook for LLMs to vent about their incompetent users.
I’d totally subscribe to that :-)