Agentic AI will transform every enterprise–but only if agents are trusted experts. The key: Evaluation & tuning on specialized, expert data. I’m excited to announce two new products to support this–@SnorkelAI Evaluate & Expert Data-as-a-Service–along w/ our $100M Series D!. ---

RT @dmizrahi_: Excited to share our new work: “Language Models Improve When Pretraining Data Matches Target Tasks”. Yes, it sounds obvious….

RT @zihengh1: LLM judges are powerful for automated evaluation but expensive and biased.📣 Meet PAJAMA, a new framework that distills LLM ju….

Ready to build expert data at scale?

For more - check out

Grok 4 results are now in for our latest multi-turn, agentic benchmark, Finance Reasoning. Grok 4 ranked #7, with performance constrained by our 50-turn cap. On completed traces- it showed clear improvement over Grok 3. Efficiency matters in agentic settings!. Links in 🧵👇

RT @ajratner: Excited to share our latest @SnorkelAI Leaderboard on Finance Reasoning – a realistic but challenging agentic benchmark invol….

And - if you’re ready to build expert data at scale, let’s talk!

For more info on this benchmark and other, check out .

You can try a sample task on HuggingFace 👉

Excited to share our latest @SnorkelAI Leaderboard on Finance Reasoning – a realistic but challenging agentic benchmark involving tool use, reasoning, and document analysis over 10-Ks with a top score of just 51.9% accuracy. For LLM agents to thrive in the enterprise, they need

And - if you’re ready to build expert data at scale, let’s talk!

To see more details on this benchmark as well as other ones, check out

You can try a sample task on HuggingFace 👉

RT @fredsala: Heading to #ICML! I’ll be representing SprocketLab at @UWMadison and @SnorkelAI. Reach out if you want to chat about data-cen….

RT @karimatiyeh: Finance teams waste hours chasing receipts and answering weird policy questions. Now they don’t have to. Introducing our….

RT @SnorkelAI: Working with @AWS to push what’s possible in financial services: from AI agents for underwriting to data-driven copilots. W….

RT @JieyuZhang20: Tokenization kickstarts every Transformer pipeline—shaping how models digest data. Our latest work introduces semantic, g….

Excited for this!.

RT @albert_ge_95: Online data mixing reduces training costs for foundation models, but faces challenges:.⚠️ Human-defined domains miss sema….

RT @SnorkelAI: We just dropped a benchmark dataset on Hugging Face to test AI agents on real-world insurance underwriting tasks—built with….