The short version
A tabular foundation model for predictive tasks without prompting a general-purpose LLM.
From the HackerLinks archive
A tabular foundation model for predictive tasks without prompting a general-purpose LLM.
The short version
A tabular foundation model for predictive tasks without prompting a general-purpose LLM.
Why it caught our attention
It surfaced as a developing alternative for tabular work, with a clear inference-speed caveat.
Where it surfaced on Hacker News
“TabPFN [1] is also working in this area and getting better and better. The inference time is still much worse than any of the more traditional models (xg/catboost etc).”
woofwoofwoof · recommendation
Direct HN comment
Why Large Language Models Fail at Tabular Prediction
Also surfaced in this discussion
Why Large Language Models Fail at Tabular Prediction
2026-08-05