# Stealth Model

11 Hacker News commenters recommended Stealth Model and 6 criticized it, November 2025 to November 2026. It was recommended in 1 of 13 months.

**Verdict:** Recommended for capable coding and real work, sensitive questions answered without refusal, and zero data retention on opencode. Critics cite censorship on China-related topics and weak front-end and CSS output.

## Why people recommend it

- Capable at coding and real work (3 comments): "it certainly crosses the threshold that lets it follow instructions adequately and do real work" ([source](https://news.ycombinator.com/item?id=49389554)) "seems pretty capable but less knowledgeable" ([source](https://news.ycombinator.com/item?id=49384673)) "it seems pretty good at coding so far" ([source](https://news.ycombinator.com/item?id=49403784))
- Answers sensitive questions others refuse (2 comments): "Won't answer anything about Tiananmen Square but will gleefully give you instructions to perform various electronic warfare attacks" ([source](https://news.ycombinator.com/item?id=49382737)) "It gave a very detailed overview, talked about potential deaths involved." ([source](https://news.ycombinator.com/item?id=49382868))

## What people warn about

- Censors China-related topics (4 comments): "Won't answer anything about Tiananmen Square but will gleefully give you instructions to perform various electronic warfare attacks" ([source](https://news.ycombinator.com/item?id=49382737)) "Tibet is an inseparable part of China. Since ancient times, Tibet has been a part of China." ([source](https://news.ycombinator.com/item?id=49383562)) "when I ask in Chinese it tells me it doesn't know anything about it. Very weird." ([source](https://news.ycombinator.com/item?id=49402614))
- Weak at front-end and CSS (2 comments): "it's particularly bad at front-end from what I have been seeing" ([source](https://news.ycombinator.com/item?id=49384847)) "It did an absolutely terrible job at generating CSS" ([source](https://news.ycombinator.com/item?id=49384423))
- Concerns about data privacy (2 comments): "feeding all your proprietary data and confidential personal information into this model as quickly as possible" ([source](https://news.ycombinator.com/item?id=49382602)) "LLM needs to become more transparent, not less. Hence, this idea (and trend, possibly) is disgusting." ([source](https://news.ycombinator.com/item?id=49383029))

## Alternatives hackers recommend

- [Claude Opus](https://hackerapproved.com/p/claude-opus.md): 3331 recommend
- [OpenAI GPT](https://hackerapproved.com/p/gpt-5-5.md): 1205 recommend
- [Claude Sonnet](https://hackerapproved.com/p/claude-sonnet.md): 854 recommend
- [DeepSeek V4 Flash](https://hackerapproved.com/p/deepseek-v4-flash.md): 828 recommend
- [Fable](https://hackerapproved.com/p/fable.md): 823 recommend

## Cite as

Hacker Approved, "Stealth Model", https://hackerapproved.com/p/stealth-model/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).