{"slug": "tabpfn", "name": "TabPFN", "category": "ai", "category_name": "AI models and assistants", "description": "", "recommenders": 3, "commenters": 4, "warners": 0, "score": 2.805, "rising": 0.35, "first": "2025-11-06", "latest": "2026-08-04", "why": "there is TabPFN [1] which also has time series capabilities.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 3, "neutral": 0, "compare": 1, "warn": 0}, "spark": [1, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "there is TabPFN [1] which also has time series capabilities.", "kind": "", "icon": true, "domain": "priorlabs.ai", "github_repo": null, "official_url": "https://priorlabs.ai/", "pricing": "", "aliases": ["TabPFN"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 786710768, "item_id": 49169423, "url": "https://news.ycombinator.com/item?id=49169423", "by": "dist-epoch", "date": "2026-08-04", "stance": "recommend", "quote": "Non-LLM transformers beat tree boosting - TabPFN, TabFM", "excerpt": "Non-LLM transformers beat tree boosting - TabPFN, TabFM https://research.google/blog/introducing-tabfm-a-zero-shot-foundation-model-for-tabular-data/", "context": "", "use_case": "Tabular prediction model", "switched_from": "", "story": "Why Large Language Models Fail at Tabular Prediction"}, {"id": 761350992, "item_id": 47584437, "url": "https://news.ycombinator.com/item?id=47584437", "by": "chwzr", "date": "2026-03-31", "stance": "recommend", "quote": "there is TabPFN [1] which also has time series capabilities.", "excerpt": "there is TabPFN [1] which also has time series capabilities. [1] https://priorlabs.ai/tabpfn", "context": "", "use_case": "time series forecasting", "switched_from": "", "story": "Google's 200M-parameter time-series foundation model with 16k context"}, {"id": 733436704, "item_id": 45839794, "url": "https://news.ycombinator.com/item?id=45839794", "by": "TheTaytay", "date": "2025-11-06", "stance": "recommend", "quote": "Looks really cool.", "excerpt": "Looks really cool. In reading through the FAQ, it says this: Q: \"How are text features handled?\" A: \"In the local package version text features are encoded as categoricals without considering their semantic meaning. Our API automatically detects text features and includes their semantic meaning into our prediction. The local package version encodes text as numerical categories and does not include semantic meaning.\" ", "context": "", "use_case": "tabular data prediction", "switched_from": "", "story": "Show HN: TabPFN-2.5 \u2013 SOTA foundation model for tabular data"}]}], "caveats": [], "who": [], "tags": [], "use_cases": ["tabular prediction model", "time series forecasting", "tabular data prediction"], "compared": [], "makers": [{"id": 798967952, "item_id": 49935497, "url": "https://news.ycombinator.com/item?id=49935497", "by": "noahho", "date": "2026-10-02", "stance": "recommend", "quote": "TabPFN v2 was published in Nature and set a new state of the art", "excerpt": "Prior Labs | Berlin, Freiburg, NYC | ONSITE | Full-time | Technical PM, ML Infra, Research Scientist/Engineer, Backend, Full Stack We build foundation models for tabular data. Deep learning transformed text and images but mostly skipped tables, which are still the data behind most clinical trials, financial models and scientific experiments. The reason is structural: no natural sequence, no spatial structure, no shar", "context": "", "use_case": "Tabular foundation model", "switched_from": "", "story": "Ask HN: Who is hiring? (October 2026)"}, {"id": 792601344, "item_id": 49537584, "url": "https://news.ycombinator.com/item?id=49537584", "by": "noahho", "date": "2026-09-02", "stance": "recommend", "quote": "TabPFN v2 was published in Nature and set a new state of the art", "excerpt": "Prior Labs | Berlin, Freiburg, NYC | ONSITE | Full-time | ML Infra, Research Scientist/Engineer, Backend, Full Stack We build foundation models for tabular data. Deep learning transformed text and images but mostly skipped tables, which are still the data behind most clinical trials, financial models and scientific experiments. The reason is structural: no natural sequence, no spatial structure, no shared vocabulary ", "context": "", "use_case": "Tabular prediction model", "switched_from": "", "story": "Ask HN: Who is hiring? (September 2026)"}, {"id": 786645648, "item_id": 49165353, "url": "https://news.ycombinator.com/item?id=49165353", "by": "noahho", "date": "2026-08-04", "stance": "recommend", "quote": "TabPFN v2 was published in Nature and set a new state of the art", "excerpt": "Prior Labs | Berlin / Freiburg / NYC | ONSITE | Full-time | Multiple Roles | https://priorlabs.ai Deep learning transformed text and images but mostly skipped tables - the data behind most clinical trials, financial models, and scientific experiments. The reason is structural: no natural sequence, no spatial structure, no shared vocabulary across datasets, so the architectures and scaling laws behind LLMs don't trans", "context": "", "use_case": "tabular data prediction", "switched_from": "", "story": "Ask HN: Who is hiring? (August 2026)"}, {"id": 780116528, "item_id": 48757283, "url": "https://news.ycombinator.com/item?id=48757283", "by": "noahho", "date": "2026-07-01", "stance": "recommend", "quote": "We started with TabPFN. v2 was published in Nature and set a new state of the art on tabular benchmarks", "excerpt": "Prior Labs | Berlin / Freiburg / NYC | ONSITE | Full-time | Multiple Roles | https://priorlabs.ai/ Deep learning transformed text and images but mostly skipped tables, even though they're behind most clinical trials, financial models, and scientific experiments. The reason is structural: no natural sequence, no spatial structure, no shared vocabulary across datasets, so the architectures and scaling laws behind LLMs ", "context": "", "use_case": "Tabular foundation model", "switched_from": "", "story": "Ask HN: Who is hiring? (July 2026)"}, {"id": 773767248, "item_id": 48360453, "url": "https://news.ycombinator.com/item?id=48360453", "by": "dill_1", "date": "2026-06-01", "stance": "neutral", "quote": "We started with TabPFN.", "excerpt": "Prior Labs | Berlin / Freiburg / NYC | ONSITE | Full-time | Multiple Roles | priorlabs.ai Deep learning transformed text and images but mostly skipped tables, even though they're behind most clinical trials, financial models, and scientific experiments. The reason is structural: no natural sequence, no spatial structure, no shared vocabulary across datasets, so the architectures and scaling laws behind LLMs don't tra", "context": "", "use_case": "Tabular foundation model", "switched_from": "", "story": "Ask HN: Who is hiring? (June 2026)"}, {"id": 767744608, "item_id": 47984038, "url": "https://news.ycombinator.com/item?id=47984038", "by": "noahho", "date": "2026-05-02", "stance": "recommend", "quote": "We built TabPFN, the first foundation model that actually understands tabular data", "excerpt": "Prior Labs | Berlin / Freiburg / NYC | ONSITE | Full-time | Multiple Roles Tables power every financial model, clinical trial, and scientific experiment, but deep learning has mostly ignored them. No natural sequence, no spatial structure, no shared vocabulary across datasets. LLM architectures don't transfer. We built TabPFN, the first foundation model that actually understands tabular data (published in Nature, 3M+", "context": "Works at Prior Labs", "use_case": "", "switched_from": "", "story": "Ask HN: Who is hiring? (May 2026)"}], "threads": [{"url": "https://news.ycombinator.com/item?id=49166442", "title": "Why Large Language Models Fail at Tabular Prediction", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=49922569", "title": "Ask HN: Who is hiring? (October 2026)", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49522897", "title": "Ask HN: Who is hiring? (September 2026)", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49156683", "title": "Ask HN: Who is hiring? (August 2026)", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48747976", "title": "Ask HN: Who is hiring? (July 2026)", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48357725", "title": "Ask HN: Who is hiring? (June 2026)", "mentions": 1}], "sentiment_by_month": {"2025-11": {"recommend": 1}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {"recommend": 1}, "2026-04": {}, "2026-05": {}, "2026-06": {}, "2026-07": {}, "2026-08": {"recommend": 1, "compare": 1}, "2026-09": {}, "2026-10": {}}, "quotes": [{"id": 786749232, "item_id": 49171827, "url": "https://news.ycombinator.com/item?id=49171827", "by": "woofwoofwoof", "date": "2026-08-04", "stance": "compare", "quote": "The inference time is still much worse than any of the more traditional models", "excerpt": "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). [1] https://github.com/PriorLabs/tabpfn", "context": "", "use_case": "", "switched_from": "", "story": "Why Large Language Models Fail at Tabular Prediction"}, {"id": 786710768, "item_id": 49169423, "url": "https://news.ycombinator.com/item?id=49169423", "by": "dist-epoch", "date": "2026-08-04", "stance": "recommend", "quote": "Non-LLM transformers beat tree boosting - TabPFN, TabFM", "excerpt": "Non-LLM transformers beat tree boosting - TabPFN, TabFM https://research.google/blog/introducing-tabfm-a-zero-shot-foundation-model-for-tabular-data/", "context": "", "use_case": "Tabular prediction model", "switched_from": "", "story": "Why Large Language Models Fail at Tabular Prediction"}, {"id": 761350992, "item_id": 47584437, "url": "https://news.ycombinator.com/item?id=47584437", "by": "chwzr", "date": "2026-03-31", "stance": "recommend", "quote": "there is TabPFN [1] which also has time series capabilities.", "excerpt": "there is TabPFN [1] which also has time series capabilities. [1] https://priorlabs.ai/tabpfn", "context": "", "use_case": "time series forecasting", "switched_from": "", "story": "Google's 200M-parameter time-series foundation model with 16k context"}, {"id": 733436704, "item_id": 45839794, "url": "https://news.ycombinator.com/item?id=45839794", "by": "TheTaytay", "date": "2025-11-06", "stance": "recommend", "quote": "Looks really cool.", "excerpt": "Looks really cool. In reading through the FAQ, it says this: Q: \"How are text features handled?\" A: \"In the local package version text features are encoded as categoricals without considering their semantic meaning. Our API automatically detects text features and includes their semantic meaning into our prediction. The local package version encodes text as numerical categories and does not include semantic meaning.\" ", "context": "", "use_case": "tabular data prediction", "switched_from": "", "story": "Show HN: TabPFN-2.5 \u2013 SOTA foundation model for tabular data"}]}