lol was thinking about just giving an agent a ramp card but this is better https://t.co/xkOEEkWJQe
— Yohei (@yoheinakajima) 11 mars 2026
lol was thinking about just giving an agent a ramp card but this is better
@yoheinakajima
-
Enthusiastic endorsement of StepFun 3.5 as a powerful tool
By
–
-
Enjoying StepFun 3.5 Software
By
–
I do a lot of one off tools and experiments. seems small but not having to set up a repo, manage PRs, set up DBs, or deployment gets me from zero to prototype much faster than w other tools (eg using GitHub Codex Vercel and Supabase – which is four separate tools I have to toggle
-
LMStudio: An Easy Way to Run llama.cpp
By
–
this is just playing around in the runway dev portal, haven't set up a hosted version yet
-
Author plans to update AI recommendations list
By
–
btw it took ~5 min to set up this demo, most of which was waiting for Gemini to generate a few Ghibli image of me, while having ChatGPT write a prompt based on what it knows about me (I’ve fed a lot of my granola transcriptions into it) https://t.co/7n2KHtZCYC
— Yohei (@yoheinakajima) 10 mars 2026btw it took ~5 min to set up this demo, most of which was waiting for Gemini to generate a few Ghibli image of me, while having ChatGPT write a prompt based on what it knows about me (I’ve fed a lot of my granola transcriptions into it)
-
Running Claude Code with Local Models on Home GPUs
By
–
I think langgraph/smith is generating solid revenue though last public report was a bit ago
-
Future AI Development and Fundraising Goals
By
–
haha the @runwayml real-time characters is great. i just spent 2 minutes pitching a ghibli version of myself a bladeless blender startup
— Yohei (@yoheinakajima) 10 mars 2026
it's only a 2 min demo, but the questions and tone are pretty solid. one question even threw me off a bit (the cleaning). asking which round… pic.twitter.com/QYoHVHDyTlhaha the @runwayml real-time characters is great. i just spent 2 minutes pitching a ghibli version of myself a bladeless blender startup it's only a 2 min demo, but the questions and tone are pretty solid. one question even threw me off a bit (the cleaning). asking which round
-
Building Tenstorrent Cluster for Mass AI Adoption
By
–
2022/2023 was langchain, llama index, LiteLLM, OpenRouter, crew ai, e2b (I’m missing a ton) so it was a lot more core ideas being introduced, vs now it’s more about how to hook these ideas up to make them work reliably and safely
-
RTX PRO 6000 as a baseline for local AI inference
By
–
huh just met someone building this. love when that works out
-
Switching AI LLM Tools: Ollama to llama.cpp, OpenClaw to Hermes
By
–
looks like we’re slowly improving (learning more about tikz now)
-
Safest Hardware Option: RTX PRO 6000
By
–
i haven’t dug in but I assume it documents available parameters, options, etc w some context that would help an ai agent use the “api” (like what the site is about)