Introducing Tenet, our first model post-trained for legal.
Tenet is a Kimi K3 base that we post-trained with @FireworksAI_HQ on a corpus of publicly available legal data, synthetic data, and human expert data simulating long-horizon legal work.
Training increases Tenet's all-pass rate by 82% on LAB and 22% on LAB Contracts relative to the Kimi K3 base model. It achieves state-of-the-art performance on LAB Contracts and places second on LAB.
These gains generalize to other leading agentic benchmarks including @mercor's Apex Agents - Corporate Law, @crosbylegal's Redline Bench, and @scale_AI's Professional Reasoning Bench.
Tenet is also optimized for token efficiency, operating at less than a fourth the cost of leading foundation models.
We additionally post-trained three specialist models for Tenet to use as subagents:
1) M&A Diligence: post-trained with @baseten on our LAB Diligence environment in an RLM harness, this model is optimized for high-scale, long-horizon tasks.
2) Review Tables: trained with @appliedcompute on our Review Table environment, this model is state-of-the-art and cost-effective at high-volume document review and structured data extraction.
3) Firm Knowledge: trained with @EngramLab on our synthetic law firm environment, this model is optimized to learn and search over a firm's knowledge via memory and structured notes.
More details on model training, environment design, benchmarking, results, and more in the article by @gabepereyra below.
What's next for Harvey’s research?
- Scaling LAB to more jurisdictions, practice areas and workflows
- Scaling compute to bring new generalist models and capabilities to Harvey
More to come soon.
High-Performance Teams in the Age of AI 🔥
I've spent a lot of time thinking about what makes teams move incredibly fast while others get stuck.
What I've seen is that performance in the age of AI has surprisingly little to do with credentials on paper and increasingly everything to do with mindset.
Here are a few observations from Lovable:
We removed ~80% of the Claude Code system prompt for our newest models, this is what we've learned about writing system prompts, skills and Claude.MDs for them. https://t.co/6DZwSrZjE9
The fastest way to improve your life is to sign up for a physical side quest. It could be a race, competition, event. Really anything. Maybe a marathon, Hyrox, long hike, or a weekend rafting trip. Something that scares you just a little bit. Just enough to spark action. Your day becomes more structured with the training for the side quest. You sleep deeper because you're tired from the training. You eat cleaner because your body wants the healthy fuel. You look better from the movement. You feel better from the momentum. Everything falls into alignment around the one small decision to sign up for that event. So, what's your side quest going to be?
So much of being a founder is overcoming fear.
Fear of launching
Fear of talking to users
Fear of rejection
Fear of ambiguity
Fear of charging money
Fear of looking dumb
Fear of doing the hard thing
What are you avoiding because of fear? Don't let it control your company.
Open-weight models are essential to a healthy AI ecosystem. Together with others across our industry, we are outlining a path for open-weight models to strengthen American competitiveness and expand economic opportunity, while protecting national security. https://t.co/Tr0sAzAxTD
Two new ways to bring your health data into Perplexity.
Perplexity now connects to Apple Health on iPhone. Use your sleep, activity, and HRV data in Computer.
Function is now available in Perplexity Health. Add labs and ask about biomarkers, blood draws, or panel results.
The biggest mistake young founders make is a variant of this: to build something you imagine people want, instead of studying them and figuring out what they actually do want. But the hack for beating this is to roll with your solipsism and make something for yourself.
Bridgewater used their unique financial knowledge and partnered with us on @tinkerapi to fine-tune a model that helps their analysts focus on what's important. Experts improving AI that empowers experts.
https://t.co/6RJITMG2BJ