proomt

Search

Search posts, papers, and topics

All posts

Zach Holman2 min readintro

As Someone Who Has Written This Blog Post,

Read on zachholman.comHN 3·0 comments

Summary

Zach Holman complains that AI‑generated cold outreach now spouts shallow facts from a target’s bio, sounding fake. He argues that genuine, specific anecdotes beat generic LLM‑crafted messages.

  • AI‑generated outreach often pulls trivial bio facts, making messages feel inauthentic.
  • Overly generic personalization is a clear Turing‑test failure and reduces response rates.
  • Real, unexpected personal anecdotes (even absurd ones) resonate more than scripted fluff.

Anyone doing outreach or recruiting should care because AI‑driven generic messages are ineffective and damage credibility.

4/10
llmairecruitingmarketingcold email

Related reading

  2. Verifiable Social Reasoning for LLM Assistants

    The paper introduces Fuse, a multi‑agent simulation that gives LLM assistants a verifiable ground‑truth task for social reasoning by hiding a target agent’s motive and letting a user‑mediated conversation infer it. Experiments on 12 LLMs show user mediation makes reasoning harder, models are biased by user framing, need more detail than humans, and longer chats don’t always help.

    Hugging Face Daily Papersarxiv.org1 minpaper

  3. Prompts aren’t Real

    The talk argues that prompt engineering is a dead‑end and proposes building large evaluation/optimization pipelines (pass^k testing, adversarial scenario generation, automated prompt optimization) to make LLM agents reliable. It describes a workflow: generate tests, run them with/without a new “skill”, feed results to a genetic optimizer that mutates prompts, validate on hold‑out tests, and itera…

    Hacker News front pageevaluation.club24 mintalkHN11757

  4. When AI Reviews Train AI Reviewers: Scientific-Judgment Collapse and Mitigation

    The authors show that training LLM reviewers on synthetic reviews leads to a compression of rating distributions and loss of semantic diversity, a phenomenon they call scientific-judgment collapse. They mitigate it with TrustReviewer, which uses curated training data and activation steering to preserve judgment diversity.

    Hugging Face Daily Papersarxiv.org1 minpaper

  5. I don't want to read what you didn't write

    The essay laments the unreadability of AI‑generated design docs, PR summaries, and other engineering writing, citing a survey where 78% of readers quit when they suspect AI involvement. The author finds AI useful only when they control the prompt and context—e.g., for grammar checks, citation generation, and diagram creation while writing a paper—but not for producing the core narrative. He highl…

    Hacker News front pagecolinbreck.com13 minHN387133