Work in progress: 181,232 of 181,233 sites checked so far, more every week · updated 2 Nov 2026Missing a blog? Tell us

Top all-time · #20125

J

Jiquan Ngiam

Personal blog · jngiam.bearblog.devaiprogramming

Jiquan Ngiam writes jngiam, a personal blog at jngiam.bearblog.dev about ai and programming. Since 2025, 3 different Hacker News readers have linked it 8 times, most often “MCPs, CLIs, and skills: when to use what?”. It is still writing: the last post was on 2026-03-12, and you can follow it by feed.

Visit the blog
8mentions?
3HN people?
2025–2026first – last linked?
Links on Hacker News per year · peak 4 in 2025

Too few sampled comments (1) to say how often HN recommends it.?

Why HN links it

HN readers link Jiquan Ngiam's blog for posts on LLM tool use with large data, arguing that code orchestration is simpler and more effective than LLM function calls that do not scale.

Summarised by Claude from a sample of 1 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.

Jiquan Ngiam's bear blog, co-founder Lutra AI, previously at Google Brain, Coursera, Stanford. linkedin @jngiam x/twitter @jiquanngiam lutra ai su...

Most-linked posts?

  1. MCPs, CLIs, and skills: when to use what?
    2 people · 2 mentions · first linked 2026-03-12
  2. LLM function calls don't scale; code orchestration is simpler, more effective
    2 people · 2 mentions · first linked 2025-05-21

What Hacker News says?

  1. Looks familiar, it seems to share some ideas with this one: LLM function calls dont scale, code orchestration is simpler, more effective Source: https://jngiam.bearblog.dev/mcp-large-data/ HN: https://news.ycombinator.com/item?id=44053744

    Comment linking /mcp-large-data/

    on “Tools: Code Is All You Need”
  2. Submitted LLM function calls don't scale; code orchestration is simpler, more effective as a story · 282 points

    HN discussion
  3. Submitted Making agentic tool calling robust: 3 engineering patterns we use as a story · 5 points

    HN discussion
  4. Submitted MCPs, CLIs, and skills: when to use what? as a story · 4 points

    HN discussion
  5. Submitted MCPs vs. APIs: Why designing tools for LLMs is different as a story · 3 points

    HN discussion
  6. Submitted MCPs, CLIs, and skills: when to use what? as a story · 1 points

    HN discussion
  7. Submitted Using LaTeX is a great hack for generating PDFs with Claude Code as a story · 1 points

    HN discussion
  8. Submitted The instruction that turns Claude into a self-improving system as a story · 1 points

    HN discussion

Search all of HN for jngiam.bearblog.dev