Turns out the future does have flying cars

An agent session ends. The work should carry forward. Worldline turns Claude Code and Codex sessions into a record of actions, changes, costs and open questions then links that record to the next run. Keep the context. Build on the work. getworldline.com

I really felt the AGI profoundly this time

What should the next person inherit from an agent run? More than a transcript: the evidence, decisions and unfinished work. An early look at what we’re building with Worldline.

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.

Palantir CEO Alex Karp predicts the future business landscape will be defined by companies that got sovereignty right competing against the frontier labs: “I am quite certain that the companies that get this right will just be the dominant companies, because de facto, it'll be you competing against a frontier lab.” “And you can win because you have access to things that are outside the spectrum, that are outside the model, that are proprietary, that only you understand.” “Or you can selectively use their models, but make sure that alpha is not being migrated out by using an application layer or what is commonly now called an ontology.”

Before this year ends, Grok Imagine will make a full-length movie of The Odyssey that is historically accurate and true to the art of Homer

Interesting take. The challenges today: 1. Most enterprises don't know how to make AI game changingly effective. As they embark on the journey, the use cases being addressed are "80%" single shot, semi deterministic use cases with multiple guardrails or humans in the middle. We are a little ways away from mass adoption of custom models. 2. More complex cases which require any multi agent orchestration and context retention are beginning to be conceived and tested. These cases will make model portability harder, requiring new evals and harnesses. One will have to commit to one structure and also commit to constantly updating and retraining your model.. 3. CIOs and CEOs aren't sure if the ultimate architecture is single stack, multi model - interoperable orchestration and context/harness/eval, or a custom model. Uncertainty causes slowdown on longer term decisions, which in this case is perhaps right. 4. Custom and Opensource come with the need to deploy on either your own GPUs or public cloud. "Interesting fact - if token prices fall as I hope - it will be cheaper to run frontier LLMs than open source on your own GPUs" 5. Generally horizontal solutions that can serve tens of thousands of customers make more money than vertical custom solutions, but maybe this time it's different? Even if we solve the model conondrum, the enterprises need to redefine workflows, collect more training data on each use case and rebuild the application in a simple UI flow, not everything will be done in a conversational window. But time will tell, this will continue to be a space to watch, lots of minds at work to solve this.