Research
The Great LLM Bake Off
Eight models, one prompt, one screenshot: rebuild the Superhuman UI in SvelteKit. Four free models, four paid ones, and the cost per attempt ranging from nothing to $1.18.
Topic
LLMOps
3 articles tagged “LLMOps”.
Engineering
How Do I Get Better LLM Uptime? A Reliability Playbook for AI in Production
Most LLM outages are not caused by the model. They are caused by the pipeline around the model. The retries, the routing, the fallbacks, the rate limits, the observability. A concrete playbook for hitting three-nines on an LLM-powered product.
Strategy
Why Your AI Project Is Actually a Data Project (and What That Costs You)
Most AI projects fail in the data layer, not the model layer. The slide deck is about agents and RAG; the work that decides the outcome is unglamorous data engineering nobody scoped or staffed.