# TimeCapsuleLLM

6 Hacker News commenters recommended TimeCapsuleLLM and 2 criticized it, November 2025 to November 2026. It was recommended in 1 of 13 months.

**Verdict:** Free experimental language model trained only on 1800-1875 text, valued as a novel idea. Critics say its output is unusable and resembles a Markov chain.

## Why people recommend it

- Interesting idea: talk to a period model (2 comments): "I think talking to a legit trained LLM from a different era would be rad" ([source](https://news.ycombinator.com/item?id=46595624)) "This will be something good" ([source](https://news.ycombinator.com/item?id=46590629))
- Responses improving across versions (2 comments): "the responses improved from there" ([source](https://news.ycombinator.com/item?id=46600314)) "This will be something good" ([source](https://news.ycombinator.com/item?id=46590629))

## What people warn about

- Output unusable, close to Markov chain (3 comments): "all of the output they demo over the course of the various versions is unusable" ([source](https://news.ycombinator.com/item?id=46597876)) "this doesn't look like it's nearly there yet, with the output looking closer to Markov chain than ChatGPT quality" ([source](https://news.ycombinator.com/item?id=46593341)) "Looks a lot like the output from a markov chain" ([source](https://news.ycombinator.com/item?id=46593901))

## 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, "TimeCapsuleLLM", https://hackerapproved.com/p/timecapsulellm/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).