www.appliedcompute.com/blog

Like our models, we keep learning

All [26] · Case studies [7] · Company [4] · Platform [5] · Research [10]

typedatetitleauthors
Case studySeptember 4, 2026Training a Specialist Code Search Agent with turbopuffer
ResearchAugust 28, 2026Frontier-scale RL with Kimi K3Raymond Feng, Lucca Bertoncini
PlatformAugust 25, 2026Applied Compute Agent Cloud
Case studyAugust 14, 2026Training Frontier Review Table Agents with Harvey
PlatformAugust 12, 2026Ari, Applied Compute's in-house AI research agentAniruddh Sriram
PlatformAugust 6, 2026Bring Your Own Harness to AC2Vinjai Vale
Case studyAugust 5, 2026Post-Training Collaboration with NVIDIA
PlatformAugust 3, 2026Productionizing self-distillation methodsCamron Sallade, Ben Scharfstein
PlatformJuly 28, 2026Scaling RL training in the age of multi-agent systemsRaymond Feng
ResearchJuly 3, 2026Predicting and Controlling Staleness in Fully Asynchronous RL TrainingChengyu Dong, Agastya Goel, Dylan Yu
ResearchJune 26, 2026Neural Cheat Sheets: Learning to Summarize with Reinforcement LearningApplied Compute
Case studyJune 22, 2026Training a State-of-the-Art Legal Agent with Harvey
ResearchJune 16, 2026Continued Training with Entropy Preserving RLNic Becker, Jacob Philips, Rhythm Garg
CompanyJune 10, 2026Moats Need ModelsSahar Solimano
ResearchJune 4, 2026Training an Agentic Router for Optimal Cost-Performance on SWE TasksNic Becker, Rhythm Garg
ResearchMay 22, 2026Bringing Capabilities in Distribution via Relevance-Masked Self-DistillationRaymond Feng, Pranav Vaid
Case studyMay 11, 2026Unlocking Real-Time Bug Detection at Cognition
ResearchMay 8, 2026Memory in the wild: how we use Context Engine on our own codeSam Denton, Dylan Yu, Raymond Feng
ResearchMay 1, 2026Remember, Refine, Retrieve: A Context Engine for Enterprise AgentsSam Denton, Ben Scharfstein, Vinjai Vale
ResearchApril 22, 2026Benchmarking Inference Engines on Agentic WorkloadsOam Patel, Linden Li
CompanyApril 10, 2026Unlocking the AI OverhangBryan Lee
CompanyApril 8, 2026The Advantage You OwnYash, Rhythm, Linden
ResearchMarch 24, 2026Speeding up RL with high-leverage samplesAgastya Goel, Linden Li
Case studyFebruary 24, 2026Building State-of-the-Art Agents with Mercor
Case studyFebruary 17, 2026Automating Merchant Onboarding at DoorDash
CompanyOctober 29, 2025It's time to get specificYash, Rhythm, Linden