Talkie
A 13B LLM trained only on pre-1931 text — by design
The Panel's Take
Talkie is a 13-billion-parameter language model with an unusual constraint: it was trained exclusively on text written before 1931. That means no internet, no Wikipedia, no modern code — just 260 billion tokens of books, newspapers, journals, patents, and case law from the pre-modern era. The result is a "vintage" LLM that speaks like it's from the early 20th century and has zero knowledge of anything after its cutoff. The model was built by Nick Levine, David Duvenaud, and Alec Radford (yes, one of the original GPT authors) with support from Anthropic and Coefficient Giving. The scientific motivation is rigorous: Talkie enables researchers to cleanly test how models generalize to unfamiliar tasks from examples alone (since it's never seen Python), study future prediction capabilities without data leakage, and understand how training data diversity shapes model dispositions and values. An instruction-tuned version exists, trained on synthetic data derived from historical etiquette manuals and cookbooks, enabling actual conversation. The model is available free on Hugging Face with a live chat demo on their site. A larger variant is planned for summer 2026.
Share this verdict
Talkie verdict: SHIP 🚀 3 ships · 1 skip from the expert panel Full review: shiporskip.io/tool/talkie-vintage-13b-language-model-pre-1931-text-2026
Weekly AI Tool Verdicts
Get the next verdict in your inbox
7 critics review a new AI tool every day. Weekly digest — free.
Compare Talkie with Others
Embed this verdict
Tool makers can add a live ShipOrSkip badge to their site. Badge loads track impressions; clicks route back to this review.
<a href="https://shiporskip.io/api/badge-click/talkie-vintage-13b-language-model-pre-1931-text-2026" target="_blank" rel="noopener"><img src="https://shiporskip.io/api/badge/talkie-vintage-13b-language-model-pre-1931-text-2026" alt="Talkie Ship verdict on ShipOrSkip" width="360" height="90" /></a>[](https://shiporskip.io/api/badge-click/talkie-vintage-13b-language-model-pre-1931-text-2026)<iframe src="https://shiporskip.io/embed/talkie-vintage-13b-language-model-pre-1931-text-2026" title="Talkie ShipOrSkip verdict" width="360" height="260" style="border:0;border-radius:16px;max-width:100%;" loading="lazy"></iframe>The reviews
“This is one of the most scientifically interesting model releases I've seen. A clean pre-1931 cutoff gives researchers a genuinely controlled environment for studying generalization, data contamination, and in-context learning — problems that plague every other benchmark we have.”
“This is a research artifact, not a tool. Unless you're studying AI generalization or historical NLP, there's nothing here for practitioners. The 'it speaks like 1930' angle is fun for demos but the actual scientific payoff is years from materializing into anything usable.”
“Alec Radford doesn't build toys. A model trained this carefully to isolate temporal knowledge enables experiments we genuinely can't run any other way — like testing whether a model can predict future events from historical patterns alone. This could reframe how we think about benchmark contamination.”
“Writers working on historical fiction or period-accurate dialogue have a dream tool here. A model that only knows 1930s-era language and references can help maintain authentic voice without accidentally slipping in modern idioms. That's a genuinely useful creative constraint.”