TimeCapsuleLLM
Shares rank 66 of 72 language models by recommenders
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.
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.
8 people gave an opinion
- recommend it
- 6
- criticize it
- 2
- approval share
- 75%
Recommended in 1 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: recommended
- February 2026: not recommended
- March 2026: not recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 6 people recommend itNeeds 10 or more, not met.
- 3 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 1 of 13 monthsNeeds 4 or more, not met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Interesting idea: talk to a period model
“I think talking to a legit trained LLM from a different era would be rad”
Comment from 12 Jan 2026 in “TimeCapsuleLLM: LLM trained only on data from 1800-1875” “This will be something good”
Comment from 12 Jan 2026 in “TimeCapsuleLLM: LLM trained only on data from 1800-1875” Responses improving across versions
“the responses improved from there”
Comment from 13 Jan 2026 in “TimeCapsuleLLM: LLM trained only on data from 1800-1875” “This will be something good”
Comment from 12 Jan 2026 in “TimeCapsuleLLM: LLM trained only on data from 1800-1875”
What people warn about
Each mark is one comment
Output unusable, close to Markov chain
“all of the output they demo over the course of the various versions is unusable”
Comment from 13 Jan 2026 in “TimeCapsuleLLM: LLM trained only on data from 1800-1875” “this doesn't look like it's nearly there yet, with the output looking closer to Markov chain than ChatGPT quality”
Comment from 12 Jan 2026 in “TimeCapsuleLLM: LLM trained only on data from 1800-1875” “Looks a lot like the output from a markov chain”
Comment from 12 Jan 2026 in “TimeCapsuleLLM: LLM trained only on data from 1800-1875”
Other language models people recommend
The four most recommended other language models, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Claude Opus | 3,331 | 2,746 | 55% | 13 | 4 mo156 owners | — |
| OpenAI GPT | 1,205 | 987 | 55% | 13 | 6 mo47 owners | — |
| Claude Sonnet | 854 | 586 | 59% | 13 | 6 mo46 owners | — |
| DeepSeek V4 Flash | 828 | 223 | 79% | 8 | 1 mo24 owners | Approved |
| TimeCapsuleLLMThis page | 6 | 2 | 75% | 1 | — | — |
What people said
All 8 comments that mention it, newest first. Each links to the original comment.
“the responses improved from there”
“all of the output they demo over the course of the various versions is unusable”
“the execution really isn't that great”
“I think talking to a legit trained LLM from a different era would be rad”
“Looks a lot like the output from a markov chain”
“this doesn't look like it's nearly there yet, with the output looking closer to Markov chain than ChatGPT quality”
“the information that is recorded and in the training data here is heavily skewed to those intelligent/recognized enough to have recorded it”
“This will be something good”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.