Pinned
Applied Compute
191 posts
Applied Compute
@appliedcompute
The best AI is built, not bought.
“A modelless company is sitting on shifting sand.” Our CEO @ypatil125 sat down with @mariogabriele to talk about why owning your model is the difference between building on bedrock vs on someone else’s roadmap. It’s the core of what we do at Applied Compute. We train better,"A modelless company is sitting on shifting sand." Yash Patil (@ypatil125) is the founder and CEO of @appliedcompute, a company that trains custom models on company data and serves them in production. His conviction: every organization has its own definition of what good looks
00:00- Applied Compute reposted
Harvey partnered with @appliedcompute to train a legal agent. We optimized each part of the agent stack: - eval loop - agent harness and compaction - post-trained GLM-5.1 using reward signal from our Legal Agent Benchmark (LAB) More in our agent-training deep dive: - Applied Compute reposted
Harvey partnered with @appliedcompute to train a legal agent. We optimized each part of the agent stack, including the eval loop, agent harness and compaction, and post-trained the underlying GLM-5.1 model using reward signal from Harvey's Legal Agent Benchmark (LAB). Check out - Applied Compute reposted
It was great collaborating with @nikogrupen, @ItsJulioPereyra, and @gabepereyra on a custom post-trained model for LAB. The rigorous work Harvey is doing to map out and build representative evals that reflect how real legal work gets done will pay massive dividends over time andWe partnered with @harvey to post-train the state-of-the-art legal agent on their LAB benchmark. It surpasses Opus 4.8 Max and GPT-5.5 xhigh.
00:00 - Applied Compute reposted
More evidence that the frontier is attainable with (1) high quality environments and domain expertise, of which @harvey has in abundance; (2) post training infrastructure to execute big runs. This ran on our Blackwell cluster without any issues, thanks to infrastructure thatWe partnered with @harvey to post-train the state-of-the-art legal agent on their LAB benchmark. It surpasses Opus 4.8 Max and GPT-5.5 xhigh.00:00 - Applied Compute reposted
If we’ve learned anything this past week it’s that GLM is a strong base for customization. Together with @appliedcompute, we focused on GLM-5.1 and have results that are a great example of what full-stack agent optimization looks like —> post-training + harness + verifier. Real - Applied Compute reposted
We partnered with @appliedcompute to train a legal agent. We optimized each part of the agent stack: - the evaluation loop - the agent harness - and post-trained the underlying GLM-5.1 model. The result? The agent achieved the highest rubric pass rate on our Legal Agent
- We partnered with @harvey to post-train the state-of-the-art legal agent on their LAB benchmark. It surpasses Opus 4.8 Max and GPT-5.5 xhigh.00:00Replying to @appliedcomputeWe rebuilt the agent harness to operate well in challenging long context environments. Legal source documents are huge, with the 90th-percentile LAB task carrying nearly 100k tokens and some exceeding 200k. We added compaction so the model summarizes its own transcript and
- Applied Compute repostedModel strategy for @harvey: We are working on the first model in our legal foundation model series, inspired by @cursor_ai's Composer. Two goals: 1. Allow us to serve frontier intelligence across our product surface areas at an affordable price and a strong security posture.
- Preserving entropy is critical for continued training; in modern post-training recipes, entropy is often a fixed resource that gets exhausted over the course of a training run, making it difficult for the model to improve and learn on new tasks. Adaptive entropy control methods
Replying to @appliedcomputeThe collapse also shows up in the answers themselves. Under various metrics of intra-prompt diversity, a policy trained with GRPO leads to less diverse responses than a trained with adaptive entropy control. Moreover, we observe that entropy allows response diversity to be tuned,
Read the full research report: - The workflows that make you different shouldn't run on the same general models everyone else rents. Our co-founder @rhythmrg on when to train your own.
- Applied Compute reposted
When we started Applied Compute this was our thesis in a nutshell. "Companies need to turn their workflows, domain knowledge, and accumulated judgment into AI systems that improve with each use. Private evals should capture whether a model is actually improving against outcomes
