Top all-time · #5606
Nicolas Bustamante
Personal blog · nicolasbustamante.comaistartups
Nicolas Bustamante's personal blog at nicolasbustamante.com covers ai and startups. Since 2021, 14 different Hacker News readers have linked it 25 times, most often “The LLM Context Tax: Best Tips for Tax Avoidance”. It is still writing: the last post was on 2026-05-30, and you can follow it by feed.
Too few sampled comments (3) to say how often HN recommends it.?
Why HN links it
HN readers link Nicolas Bustamante's posts on moving beyond RAG, agentic search, and preventing drift in AI-modified software, which they cite as lessons from building AI systems.
Summarised by Claude from a sample of 3 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Nicolas Bustamante's personal website.
Most-linked posts?
- The LLM Context Tax: Best Tips for Tax Avoidance3 people · 3 mentions · first linked 2026-02-11
- Model-Market Fit2 people · 2 mentions · first linked 2026-01-20
- Lessons from Building AI Agents for Financial Services2 people · 2 mentions · first linked 2026-01-26
- The Crumbling Workflow Moat: Aggregation Theory's Final Chapter2 people · 2 mentions · first linked 2026-02-04
- The RAG Obituary: Killed by agents, buried by context windows2 people · 2 mentions · first linked 2025-10-01
What Hacker News says?
Here's an interesting read on the evolution beyond RAG: https://www.nicolasbustamante.com/p/the-rag-obituary-killed-... One of the key features in Claude Code is "Agentic Search" aka using (rip)grep/ls to search a codebase without any of the overhead of RAG. Sounds like even RAG approaches use a similar approach (Query Generation).
Comment linking /p/the-rag-obituary-killed-by-agents
on “Production RAG: what I learned from processing 5M+ documents”Submitted The RAG Obituary: Killed by agents, buried by context windows as a story · 290 points
HN discussionCentral banks have fueled malinvestment for centuries. That's a disaster. I wrote another article about the manipulation of money and credit: https://www.nicolasbustamante.com/p/money-and-credit-manipul...
Comment linking /p/money-and-credit-manipulation-ask?s=w
on “Panic in Startupland”Submitted Panic in Startupland as a story · 96 points
HN discussionhe forgot model market fit https://www.nicolasbustamante.com/p/model-market-fit
Comment linking /p/model-market-fit
on “AI on Australian travel company website sent tourists to nonexistent hot springs”Submitted The End of My Crypto Explorations as a story · 32 points
HN discussionI'm having trouble parsing exactly what you're seeking but maybe this post is worth a look https://www.nicolasbustamante.com/p/lessons-from-building-ai... Specially the part around temporal. If you have drift and sufficient hops, at some point quality won't hold to your expectations so can you "break the cycle" through observability and failure correction?
Comment linking /p/lessons-from-building-ai-agents-for?open=false
on “Ask HN: What invariants matter most to prevent drift in AI-modified SaaS apps?”Submitted The Crumbling Workflow Moat: Aggregation Theory's Final Chapter as a story · 3 points
HN discussionSubmitted Model-Harness-Fit as a story · 2 points
HN discussionSubmitted Burning Billions: The Gamble Behind Training LLM Models as a story · 2 points
HN discussionSubmitted Look How Big My Funding Amount Is: I Raise Therefore I Am as a story · 2 points
HN discussionSubmitted My agent stack for automating my personal life as a story · 1 points
HN discussionSubmitted Lessons from Building AI Agents for Financial Services as a story · 1 points
HN discussionSubmitted The LLM Context Tax: Best Tips for Tax Avoidance as a story · 1 points
HN discussionSubmitted The LLM Context Tax: Best Tips for Tax Avoidance as a story · 1 points
HN discussionSubmitted The LLM Context Tax: Best Tips for Tax Avoidance as a story · 1 points
HN discussionSubmitted Vertical SaaS Is Cooked: The Crumbling Workflow Moat as a story · 1 points
HN discussionSubmitted Lessons from Building AI Agents for Financial Services as a story · 1 points
HN discussionSubmitted Lessons from Building AI Agents for Financial Services as a story · 1 points
HN discussionSubmitted Model-Market Fit as a story · 1 points
HN discussionSubmitted But But, You Were Supposed to Be a GPT Wrapper? as a story · 1 points
HN discussionSubmitted What We Learnt Building the Largest GPT-Telegram Bot as a story · 1 points
HN discussionSubmitted Startups Selling Sand in the Desert as a story · 1 points
HN discussionSubmitted Physical Minimalism as a story · 1 points
HN discussionSubmitted The Impact of the Highly Improbable as a story · 1 points
HN discussion
