AI tool comparison
Perplexity vs Talkie
Which one should you ship with? Here is the side-by-side panel verdict, pricing read, reviewer split, and community vote comparison.
Search & Research
Perplexity
AI research platform with cited answers, deep research, and shareable pages
100%
Panel ship
—
Community
Free
Entry
Perplexity evolved from search-with-citations into a full research platform. Deep Research runs multi-step investigations that take 2–5 minutes and produce comprehensive reports with sources — replacing hours of manual research. Perplexity Pages creates shareable, structured research documents anyone can read. Pro Search includes access to Claude, GPT-4o, and Sonar models for different task types. Shopping mode surfaces product comparisons with price tracking. The answer engine that replaced Google Search for research-heavy workflows.
Research
Talkie
A 13B LLM trained only on pre-1931 text — by design
75%
Panel ship
—
Community
Free
Entry
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.
Reviewer scorecard
“Deep Research is legitimately impressive for technical evaluation — comparing libraries, auditing security postures, understanding architecture decisions. What used to take 2 hours of reading docs and Stack Overflow now takes 5 minutes and comes with citations I can verify.”
“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.”
“Citations remain the core differentiator vs ChatGPT. Every claim is sourced and you can click through. Hallucination risk drops dramatically when the model knows it has to cite. Deep Research is good but sometimes slow — it works best when you have a few minutes, not seconds.”
“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.”
“Perplexity Pages is the underrated bet — turning AI research into shareable documents is how knowledge workers will collaborate in the future. The roadmap (Deep Research, Pages, shopping, Pro with multiple models) is building the AI-native knowledge platform, not just a better search engine.”
“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.”
Weekly AI Tool Verdicts
Get the next comparison in your inbox
New AI tools ship daily. We compare them before you waste an afternoon.