T

Talkie

A 13B LLM trained exclusively on texts from before 1931

PriceFree / Open ResearchReviewed2026-04-29
Verdict — Ship
3 Ships1 Skips
Visit talkie-lm.com

The Panel's Take

Talkie is a 13-billion parameter language model trained exclusively on English-language texts published before 1931 — the largest vintage language model built to date. Created by researchers Nick Levine, David Duvenaud (University of Toronto), and Alec Radford (of GPT and DALL-E fame), it represents a novel approach to understanding what training data really does to a model. The research insight is elegant: modern LLMs are so thoroughly contaminated by modern internet data (directly or through distillation) that it's nearly impossible to isolate what the model "knows" from what it absorbed during training. Talkie solves this by hard-cutting the training corpus at 1931 — predating digital computers entirely. This lets the team run controlled experiments impossible with contemporary models, such as teaching the model to write Python from examples alone and measuring how quickly it generalizes. Talkie was trained on ~260 billion tokens of historical text and fine-tuned using direct preference optimization with Claude as judge on structured historical documents (etiquette manuals, letter-writing guides). It's openly available on Hugging Face for research use. It also happens to produce wonderfully formal, slightly anachronistic prose.

Share this verdict

Talkie verdict: SHIP 🚀

3 ships · 1 skip from the expert panel

Full review: shiporskip.io/tool/talkie-lm-pre-1931-13b-vintage-language-model-research-2026

Weekly AI Tool Verdicts

Get the next verdict in your inbox

7 critics review a new AI tool every day. Weekly digest — free.

Embed this verdict

Tool makers can add a live ShipOrSkip badge to their site. Badge loads track impressions; clicks route back to this review.

Ship · 7.5/10
HTML badge
<a href="https://shiporskip.io/api/badge-click/talkie-lm-pre-1931-13b-vintage-language-model-research-2026" target="_blank" rel="noopener"><img src="https://shiporskip.io/api/badge/talkie-lm-pre-1931-13b-vintage-language-model-research-2026" alt="Talkie Ship verdict on ShipOrSkip" width="360" height="90" /></a>
Markdown badge
[![Talkie Ship verdict on ShipOrSkip](https://shiporskip.io/api/badge/talkie-lm-pre-1931-13b-vintage-language-model-research-2026)](https://shiporskip.io/api/badge-click/talkie-lm-pre-1931-13b-vintage-language-model-research-2026)
Iframe widget
<iframe src="https://shiporskip.io/embed/talkie-lm-pre-1931-13b-vintage-language-model-research-2026" title="Talkie ShipOrSkip verdict" width="360" height="260" style="border:0;border-radius:16px;max-width:100%;" loading="lazy"></iframe>

The reviews

The ability to test code-learning from scratch on a model that's never seen a modern codebase is genuinely useful for ML research. The methodology here is cleaner than anything I've seen for studying data contamination.

Helpful?

Fascinating as a research artifact, but this isn't a production model. The limited vocabulary and cultural frame mean it's not useful for most practical tasks. It's a museum piece, not a tool.

Helpful?

This is exactly the kind of fundamental research the field needs. Understanding what training data does to language models — not just benchmark scores — is critical as we scale to more powerful systems. Radford's involvement adds serious credibility.

Helpful?

The prose it generates has a formal, unhurried quality that modern LLMs can't replicate. For period-accurate creative writing, historical fiction, or vintage-voice content, Talkie is the only model worth using.

Helpful?

Bookmarks

Loading bookmarks...

No bookmarks yet

Bookmark tools to save them for later