proomt

Search

Search posts, papers, and topics

All posts

Josh Sherman2 min readintro

Rediscovering Long-Form Email

Summary

The author, an email expert, advocates for a return to long-form, personal email conversations to foster deeper human connections. He argues this contrasts with fragmented social media, LLM-generated content, and formulaic cold emails, promoting more meaningful communication.

  • Fragmented social platforms hinder consistent collaboration, making email a viable alternative for deeper connection.
  • Long-form email enables more thoughtful conversations than short-form chat or templated cold emails.
  • The prevalence of LLM-generated content devalues genuine, human-crafted long-form writing.
  • Modern cold email often relies on scripted, impersonal templates, losing the essence of communication.

This piece offers a perspective on the value of thoughtful, long-form digital communication in an era dominated by short-form content and AI-generated text.

5/10

Related reading

  1. Article: Beyond Relevance: A Governance-First Architecture for Enterprise Personalization

    The article proposes a governance‑first architecture for enterprise personalization, where policy‑driven steps (memory, journey graph, AI routing, scoring, trust checks, outcome simulation) shape the recommendation before it is returned. A reference FastAPI implementation demonstrates the pattern with external YAML policies and optional LLM assistance.

    InfoQinfoq.com19 min
  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. Thirteen years of blogging

    The author reflects on 13 years of blogging, noting a significant decline in traffic attributed to LLMs, but emphasizes the continued value of writing for personal skill development and authentic communication. He also provides updates on his products and academic work.

    Vlad Mihalceavladmihalcea.com5 min
  4. Do LLMs Have the Memory of a Goldfish?

    The article explains that LLMs don’t have persistent personal memory; all “memory” is supplied by the surrounding application via the context window, summaries, or external storage. It outlines the distinction between trained weights, working‑memory (token context), and persistent application memory, shows how to construct API calls to preserve conversation state, and discusses the cost and laten…

    ByteByteGobytebytego.com12 min