I donât have any fun when I use LLMs to write. It may have perceived utility: popping out a LinkedIn article or two everyday. But I bet no one is actually reading. Itâs a strip mall for a thumb stroll.
LLMs suck at writing. The summaries that LLMs give with the âDeep Researchâ are so poor in quality that I start to skim it. Yes, I skim the thing that is already a summary.
Letâs do a small experiment using the Harry G. Frankfurt Essay On Bullshit:
Here are HGFâs opening lines:
âOne of the most salient features of our culture is that there is so much bullshit. Everyone knows this. Each of us contributes his share.â
Now here is ChatGPT o3, with the advantage of having HGF in the training data and extra contextualizing from me âtheory of bullshitâ:
Prompt: write me an introductory paragraph on the theory of bullshit
Result: âBullshit isnât just lying gone sloppy; itâs a distinct communicative strategy built on indifference to truth. Where the liar knows the facts and works to conceal or invert them, the bullshitter treats truth-value as irrelevant raw materialâselecting, mixing, or inventing claims to achieve an effect (status, alignment, vibe) rather than to inform. The result is epistemic pollution: signals thatâŚâ
Look! Itâs the secret flag of âcontentâ: âBlah isnât just X; Blah is Yâ.

I cannot assimilate this, it definitely canât help me synthesize anything. There is always better human writing even if it is poorly written. It has a certain aliveness, and that aliveness is contagious enthusiasm. Vibe coding I can understand, you can see bad output in the final result. Vibe coding still manages to change something in my mind: knowing what I donât want.
I donât mind people using AI at all, I use it alllll the time. Writing with LLMs is no just fun. All this prompting and almost nothing changes in my mind. When an AI rearranges your thoughts it does not rearrange your brain.
Leave a comment