Sam Hogan 🇺🇸

@samhogan

ceo @inference_net | inference infra for AI-native teams

San Francisco, CA

inference.net

Joined May 2012

Replies Articles Media

Pinned
Sam Hogan 🇺🇸
@samhogan
Aug 6
We're releasing Inference AutoEvals⚡️ automatically find the best model for any agent by replaying traffic across a suite of models. works with every model/provider on average, AutoEvals cuts spend by 30% & improves accuracy by ~10% with a one-line code change Available now👇
Sam Hogan 🇺🇸
@samhogan
3h
Fun fact I bought the @inference NPM package off a guy I tracked down in a furry discord using Sherlock github.com/sherlock-proje…
Sam Hogan 🇺🇸
@samhogan
Aug 14
GLM 5.3 benchmarks look great, pretty substantial improvement over 5.2 on coding and cyber
Z.ai
@Zai_org
Aug 14
Introducing GLM-5.3: Built to Code. Ready for Cyber Defense. - Top-tier coding and agentic capabilities, achieved through post-training on the 743B base model - A major leap in cybersecurity, setting a new standard among open models Tech Blog: z.ai/blog/glm-5.3
Sam Hogan 🇺🇸
@samhogan
Aug 11
Interesting to see that the thinking traces behind frontier models basically sound like a caveman talking to himself
Amar Singh
@AmarSVS
Aug 11
I found out you can still extract model reasoning chains if you give them a deep_think tool with reasoning effort off. so I asked gpt 5.6 sol and opus 5 a bunch of dumb questions and published their reasoning responses reasoning-probes.pages.dev
Sam Hogan 🇺🇸
@samhogan
Aug 11
More fun ascii animations. Logos for @PlanetScale, @depotdev, @Railway, and @cursor_ai
00:00
Sam Hogan 🇺🇸
@samhogan
Aug 10
I had @cursor_ai oneshot a pipeline to generate ascii animations for model lab logos. It turned out pretty cool, going to add them to our model pages on inference.net/models