PFNs train from scratch for tabular data, while post-trained LLMs hit limits fast
roydanroy · x · 2026-07-26
A reply thread discusses PFNs versus post-trained LLMs for tabular problems.
The key claim is that PFNs do not post-train LLMs; instead, they use architectures that natively handle numbers without tokenizing strings and are trained from scratch. In contrast, the thread says post-trained LLM approaches such as TabuLa-8B remain toy-like on very small datasets and start to underperform once the dataset grows beyond only a few rows.
Related event: Researchers Discuss PFNs vs Post-trained LLMs for Tabular Data(4 posts)→
More from Research
- UW study finds agent memory can keep prompt-injection payloads armed for the next session — rohanpaul_ai · 2026-07-26
- Oxford study finds AI can out-persuade world-champion debaters in controlled tests — Justgototheeffinmoon · 2026-07-26
- 36 engineers converge on a missing contract layer for AI workflows — Trout_dev · 2026-07-26
- New OCTO text tool is used to analyze AlphaFold 2 citations in ATLAS release — JMateosGarcia · 2026-07-26
- Orca opens a shared stack for dexterous hand research and teleoperation — tensorqt · 2026-07-26
- Weekly AI paper roundup covers world models, embodied AI, and self-improving agents — _akhaliq · 2026-07-26