fine-tuned distillation: The Pattern Behind the Best Agents This Quarter
Beyond the launch posts, Phi-4 is reshaping how founders approach onboarding. We talked to the people actually using it in production.
The archive
100 stories from the Inference Daily desk.
Beyond the launch posts, Phi-4 is reshaping how founders approach onboarding. We talked to the people actually using it in production.
The interesting story is not the demo. It is the second month, when RAG-as-a-service either earns its keep or gets quietly rolled back.
The interesting story is not the demo. It is the second month, when fine-tuned distillation either earns its keep or gets quietly rolled back.
Beyond the launch posts, Command R+ 2 is reshaping how operators approach incident response. We talked to the people actually using it in production.
HubSpot is the latest in a string of teams treating small-model orchestration as the default, not the experiment. Here is what they got right — and what they are still figuring out.
The interesting story is not the demo. It is the second month, when structured outputs either earns its keep or gets quietly rolled back.
Beyond the launch posts, DeepSeek V4 is reshaping how researchers approach code review. We talked to the people actually using it in production.
HubSpot is the latest in a string of teams treating evals-first development as the default, not the experiment. Here is what they got right — and what they are still figuring out.
The interesting story is not the demo. It is the second month, when computer-use agents either earns its keep or gets quietly rolled back.