What if your LLM woke in seconds, not minutes? Tested Ollama vs vLLM on Modal (Qwen3.6-27B). vLLM wins on cold starts and throughput. Post: setup, 3 snapshot bugs, CUDA graphs. How do you handle cold starts? buff.ly/e8LX5OE #llm #vllm
Who's Who of AI
ericmjl.bsky.social
Why follow
Practitioner with public evidence across AI research.
- AI signals
- 4 past 30d
- Sources
- 2 distinct domains
- Discussions
- 1 past 30d
- Latest signal
- 12h ago
Senior Principal Data Scientist, Moderna. Trying to follow Jesus.
What they're sharing
Ollama, vLLM, and SGLang on Modal ericmjl.github.io
Agents amplify expertise and ignorance ericmjl.github.io
My coding agent learned a lesson and patched its own skill ericmjl.github.io
My coding agent learned a lesson and patched its own skill buff.ly
Articles & links
Does AI widen the expert-novice gap? Live-demoed a Bayesian model with an agent. It amplified my judgment. For experts, a microscope. For novices, fast wrong answers. 'Vibe zones' and trust scaling with verification. What's your experience? #ai #datascience buff.ly/BVb49jC
What if your agent learned from its mistakes without you telling it to? I built a plugin that watches sessions, extracts lessons, and patches skills. 922 observations, 200+ reviews in 10 days. It patched a skill on its own. No babysitting. #opencode #aiagents ericmjl.github.io…
What if your agent learned from its mistakes without you telling it to? I built a plugin that watches sessions, extracts lessons, and patches skills. 922 observations, 200+ reviews in 10 days. It patched a skill on its own. No babysitting. #opencode #aiagents ericmjl.github.io…
Their network
In ericmjl.bsky.social's orbit
Center = ericmjl.bsky.social. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.