# 2026 W01 - 01-04

First time here ? Check the introduction [here]({% post_url hn_digest/2026-01-01-Init %})

# Articles 


## Model Training

- 434 pt  [[Link](<https://github.com/HarryR/z80ai>) / [HN](<https://news.ycombinator.com/item?id=46417815>)] Show HN: Z80-μLM, a 'Conversational AI' That Fits in 40KB 

## Coding Agents

- 438 pt  [[Link](<https://granda.org/en/2026/01/02/claude-code-on-the-go/>) / [HN](<https://news.ycombinator.com/item?id=46491486>)] Claude Code On-the-Go 
- 420 pt  [[Link](<https://twitter.com/bcherny/status/2007179832300581177>) / [HN](<https://news.ycombinator.com/item?id=46470017>)] The creator of Claude Code's Claude setup 
- 336 pt  [[Link](<https://exopriors.com/scry>) / [HN](<https://news.ycombinator.com/item?id=46442245>)] Show HN: Use Claude Code to Query 600 GB Indexes over Hacker News, ArXiv, etc. 
- 202 pt  [[Link](<https://balajmarius.com/writings/vibe-coding-a-bookshelf-with-claude-code/>) / [HN](<https://news.ycombinator.com/item?id=46420453>)] Show HN: Vibe coding a bookshelf with Claude Code 
- 167 pt  [[Link](<https://github.com/mutable-state-inc/ensue-skill>) / [HN](<https://news.ycombinator.com/item?id=46426624>)] Show HN: Stop Claude Code from forgetting everything 

## Personal Blogs / Opinions

- 450 pt  [[Link](<https://simonwillison.net/2025/Dec/31/the-year-in-llms/>) / [HN](<https://news.ycombinator.com/item?id=46449643>)] 2025: The Year in LLMs 
- 263 pt  [[Link](<https://bits.logic.inc/p/ai-is-forcing-us-to-write-good-code>) / [HN](<https://news.ycombinator.com/item?id=46424200>)] AI is forcing us to write good code 
- 116 pt  [[Link](<https://zekcrates.quarto.pub/deep-learning-library/>) / [HN](<https://news.ycombinator.com/item?id=46454587>)] Build a Deep Learning Library 
- 56 pt  [[Link](<https://teodordyakov.github.io/brainfuck-agi/>) / [HN](<https://news.ycombinator.com/item?id=46418966>)] Asking Gemini 3 to generate Brainfuck code results in an infinite loop 

## Politics / Strategy

- 291 pt  [[Link](<https://manus.im/blog/manus-joins-meta-for-next-era-of-innovation>) / [HN](<https://news.ycombinator.com/item?id=46426534>)] ManusAI Joins Meta 

## News

- 182 pt  [[Link](<https://www.pentestpartners.com/security-blog/eurostar-ai-vulnerability-when-a-chatbot-goes-off-the-rails/>) / [HN](<https://news.ycombinator.com/item?id=46492063>)] Eurostar AI vulnerability: When a chatbot goes off the rails 
- 154 pt  [[Link](<https://www.theguardian.com/business/2025/dec/29/uk-accounting-remote-exams-ai-cheating-acca>) / [HN](<https://news.ycombinator.com/item?id=46420289>)] UK accounting body to halt remote exams amid AI cheating 

## Others

- 143 pt  [[Link](<https://github.com/nibzard/awesome-agentic-patterns>) / [HN](<https://news.ycombinator.com/item?id=46491244>)] Agentic Patterns 
- 135 pt  [[Link](<https://newsletter.semianalysis.com/p/how-ai-labs-are-solving-the-power>) / [HN](<https://news.ycombinator.com/item?id=46444020>)] How AI labs are solving the power problem 
- 109 pt  [[Link](<https://arxiv.org/abs/1803.03635>) / [HN](<https://news.ycombinator.com/item?id=46470513>)] The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks (2018)