Results for “context engineering”

…re-run the eval and expects the score to rise. Specs: 1M-token context, up from 200k for Haiku 4.5. Text and image input, text output. 5-minute cache writes cost $0.125 per 1M tokens ($0.625 above 100K). Other benchmark claims (mostly…

…our newest cohost from the Forward Deployed side of the AI Engineering world! We’ll be ramping up a new show with him and couldn’t pass up an interview with Modal’s CEO Eric on the occasion of their monster Series D!Two years ago, we spoke …

…Google’s AI teams, and why the next leap won’t come from bigger context windows alone, but from systems that give the illusion of attending to trillions of tokens. We discuss: • Jeff’s early neural net thesis in 1990: parallel training…

…the NYC AI Engineer Summit focusing on AI Leadership and Agent Engineering! If you applied, invites should be rolling out shortly. The search landscape is experiencing a fundamental shift. Google built a >$2T company with the “10 blue…

…AI research could reduce years of work to weeksReward engineering and what makes auto-research systems actually work The AI Economist and using simulations to test economic policy Whether LLMs can realistically simulate people and entire…

…foundation models and we <5% done on this journey Good AI Engineering requires genuine skill and is deepening enough to justify sub-specialization as a sub-industry of Software Engineering Companies and countries with better AI engineer…

…On-Device Models and Local vs Remote Agent Systems [00:51:34] Engineering at OpenAI and Leveraging LLMs [00:54:16] Structuring Codebases and Teams for AI Optimization [00:55:27] The Value of Engineers in the Age of AGI [00:58:42] Current…

…looking in general at the ecosystem of agent frameworks, the engineering quality is far below that of the rest of the Python ecosystem. There's a bunch of stuff that we have learned how to do over the last 20 years of building Python…

…for IQuest-Q1, a 320B MoE (15B active, 256 experts, 512K context) with 3:1 sliding/full attention and an MTP draft head. Photon 2.6: Moondream’s release runs Qwen3.5 27B at 400+ tok/s on B200. Agent-written kernels: Databricks reached #1 on…

…one of the five. We go deep on Poolside’s Model Factory: the engineering systems behind 10,000–20,000 experiments per month, streaming data directly into training, reproducible experimentation, low-precision compute, and agents that…

…It was just prohibitively expensive at the time. And the context limit was way too small. But yeah, I think it seems like a lot of people are taking it more seriously now, mostly because GPT-4 is way more capable. The context limit's like…

…with friends at Amplify to launch the first State of AI Engineering survey! Please fill it out (and tell your friends)! In March, we started off our GPT4 coverage framing one of this year’s key forks in the road as the “Year of Multimodal…