Morgan Linton·Oct 21How visiting Dali’s house on the coast of Spain made me think about LLm evals as artI learned something new about Dali, not his art, but how he saw people, in unique environments, as art
Morgan Linton·Oct 7I have become obsessed with building eval suites to challenge the frontier, and it’s insanely hardLike a lot of engineering teams, earlier this year we were struggling to figure out what model and effort levels we actually needed to do…
Morgan Linton·Sep 20Jev 101: understanding why the co-creator of ChatGPT isn’t building another LLMOver the last week, my timeline on X has been all Jev, all the time. I can’t remember the last time I saw engineers and researchers more…A response icon2A response icon2
Morgan Linton·Sep 16How I’m building an independent safety benchmark for coding agents, and why model effort mattersAs I build out the first eval suite, and framework for VulcanBench Safety v1, I wanted to share a little more about my approach. I think AI…
Morgan Linton·Sep 12Some thoughts on adding code quality scoring to llm benchmarksTwo weeks ago, Astra and Fable 5.1 were released, and I started benchmarking both the first day I got access. Then, as my benchmarks were…
Morgan Linton·Aug 20Some reflections on building evals and benchmarking frontier modelsBuilding eval suites for VulcanBench is really fascinating, and also so much more challenging than I was expecting.
Morgan Linton·Aug 14What I Learned Rethinking the Execution Layer in our Agentic Coding WorkflowI moved our engineering team over to agentic coding workflows in early 2025, not fully, but enough to really begin the foundational change…
Morgan Linton·Jun 18If you aren’t using models with different effort levels, you’re probably wasting tokens, and timeAfter spending a good chunk of time last week with Fable 5, it seems to have rewired my brain a bit, and it’s making me think a lot more…
Morgan Linton·Jun 11With Anthropic’s new Fable 5 model, low mode is the alphaSo I wrote a post about Anthropic’s new Fable model yesterday, and it ended up going viral on X, so I think it makes sense to build on it…
Morgan Linton·May 16Coming up with a better way to compare different agentic coding tools and modelsAs a CTO today I’m on a mission to help my team access all the best agentic coding tools out there. And, yeah — that mission is a complex…
