Don't be a meat proxy

8 hours ago

Don't just relay AI-generated responses verbatim; it doesn't add value.
Reading AI output requires extra effort due to verbosity, plausible nonsense, and jargon.
Instead, read, understand, validate, and then rewrite the response in your own words.
In code reviews, using AI to generate code without understanding reduces the human to a 'meat proxy'.

Invest in upfront alignment by making implicit assumptions explicit in the initial prompt to avoid unexpected AI outputs.
Restart with better context rather than steering AI when initial outputs are far off; avoid compounding errors through path dependence.
Equip AI agents with the same tools you use (CLI, MCP, browser control) to handle setup, testing, and instrumentation tasks.

Using AI to generate content and passing it off as your own is likened to using WordArt in Word 97—it gives a false sense of expertise and quickly becomes banal when everyone does it.
The obvious way to use a new tool isn't always the best; AI-generated writing without thought breaks the social contract of writing and isn't enjoyable for readers.
AI is valuable for learning, research, and automating tedious tasks, but not for writing that you claim as your own, as it undermines authenticity and trust.

Using LLM coding assistants for one-shot features leaves the author unsatisfied and disoriented, but they still use them for boring parts.
Allowing the assistant to freely roam creates cognitive debt; the author wants to understand the code, not just offload it.
Reviewing AI-generated PRs is not enjoyable due to overly-defensive, badly-commented, and subtly incorrect code.

Using LLMs for professional writing can harm your career, especially early on, as experienced readers can detect AI-generated content.
Delegating writing to AI means delegating critical thinking, which is essential for career advancement.
The excuse of being a bad writer is like avoiding the gym because you're unfit; you must practice writing yourself.

Reading AI-generated content feels like a trick, evoking offense, sadness, and contempt for authors who use AI to write.
Defending AI-assisted writing by claiming 'ideas are mine, writing is AI's' is flawed because ideas and writing are inseparable.
Ideas are vague and nebulous; writing is the process that concretizes and refines them, revealing flaws and contradictions.

Invest in upfront alignment by making implicit assumptions explicit in the initial prompt to avoid unexpected AI outputs.
Restart with better context rather than steering AI when initial outputs are far off; avoid compounding errors through path dependence.
Equip AI agents with the same tools you use (CLI, MCP, browser control) to handle setup, testing, and instrumentation tasks.

Using AI to generate content and passing it off as your own is likened to using WordArt in Word 97—it gives a false sense of expertise and quickly becomes banal when everyone does it.
The obvious way to use a new tool isn't always the best; AI-generated writing without thought breaks the social contract of writing and isn't enjoyable for readers.
AI is valuable for learning, research, and automating tedious tasks, but not for writing that you claim as your own, as it undermines authenticity and trust.

Using LLM coding assistants for one-shot features leaves the author unsatisfied and disoriented, but they still use them for boring parts.
Allowing the assistant to freely roam creates cognitive debt; the author wants to understand the code, not just offload it.
Reviewing AI-generated PRs is not enjoyable due to overly-defensive, badly-commented, and subtly incorrect code.

Using LLMs for professional writing can harm your career, especially early on, as experienced readers can detect AI-generated content.
Delegating writing to AI means delegating critical thinking, which is essential for career advancement.
The excuse of being a bad writer is like avoiding the gym because you're unfit; you must practice writing yourself.

Reading AI-generated content feels like a trick, evoking offense, sadness, and contempt for authors who use AI to write.
Defending AI-assisted writing by claiming 'ideas are mine, writing is AI's' is flawed because ideas and writing are inseparable.
Ideas are vague and nebulous; writing is the process that concretizes and refines them, revealing flaws and contradictions.

Hasty Briefsbeta