Brandon

data junkie @micro1_ai, grad @ucla_law, retired sneaker botlete

[Brandon @brandonvalafar]

@aliansarinik best part of the job

[Brandon @brandonvalafar]

Awesome to see a model post-trained specifically for legal & micro1's work on RedlineBench featured here!

[Harvey @harvey]

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.

[Brandon @brandonvalafar]

@chrisbarber @ariansadeg @bercankilic @joinshift @aliansarinik @babugi28 @Rush26agarwal @joshavata @jasontheutopian @mog3n @NotDeu @philippswu Great!

[Brandon @brandonvalafar]

@aliansarinik

[Brandon @brandonvalafar]

@basedgunnar Eve pre-proxy era might've been peak botting

[Brandon @brandonvalafar]

@micro1_ai generational team

[micro1 @micro1_ai]

We landed on this year’s Inc. 5000 list as one of the fastest-growing companies in the country.

Turns out building frontier AI models requires a ton of data.

[Brandon @brandonvalafar]

@micro1_ai Need the micro1 shirt asap

[micro1 @micro1_ai]

Collecting audio data in the real world.

Live music, real-world RL, good vibes across the city, and better tools made for musicians 🎵🌉

[Brandon @brandonvalafar]

Yet another reason why @micro1_ai is going to win

[Anna Tong @annatonger]

The AI arms race isn’t just being fought over Nvidia chips. Chinese labs are matching OpenAI and Anthropic by purchasing the exact same data from US vendors like @mercor and Surge AI (who also work with the US federal govt) https://t.co/C1LHTIw2Js

[Brandon @brandonvalafar]

@micro1_ai 🇺🇸

[Ali Ansari @aliansarinik]

human brilliance is needed more than ever. our mission is to ensure that's always true.

m1 in 🇬🇧

[adam bain @adambain]

Kimi K3 is another reminder that high-quality data is a core determinant of model performance.

@micro1_ai took an early, principled stand not to provide data to foreign adversaries.

I’m not convinced everyone else in this category made the same commitment.

Every company in the data ecosystem should publicly commit to this same standard. If you haven’t, why not?

[Brandon @brandonvalafar]

@aliansarinik 🇺🇸

[Brandon @brandonvalafar]

@kylejeong @vestucla @OpenAI @tryramp @Whatnot @paradigmai @Netic_AI @cerebras this is sick! go bruins🐻

[Ali Ansari @aliansarinik]

looks familiar

https://t.co/AEjYEUKxpG

[Brandon @brandonvalafar]

@aliansarinik

[Brandon @brandonvalafar]

@aliansarinik world-class

[Brandon @brandonvalafar]

@micro1_ai @reductoai 🤯

[micro1 @micro1_ai]

Today we're publishing LongExtractBench, a benchmark commissioned by @reductoai and independently validated by micro1.

We evaluated seven production document extraction systems across the same 225 complex enterprise documents. The benchmark was intentionally difficult: documents averaged 358 pages and contained roughly 88,700 ground-truth fields each. Every system was evaluated using the configuration documented in the benchmark methodology.

Key findings:
• Reducto Deep Extract was the only system to successfully complete all 225 documents.
• Direct frontier LLM baselines achieved substantially lower completion rates on long, complex documents.
• In this benchmark, dedicated extraction platforms achieved higher completion rates than the direct frontier LLM baselines.
• Recall was the clearest differentiator. Precision remained high across systems, but recall ranged from 33.8% to 99.6%, highlighting which systems consistently captured the information contained in long, complex documents.

The full report includes the benchmark methodology, limitations, and reproducibility resources. Check out the report and results in the comments below.