Just in case you were thinking of signing up directly with Moonshot to use the service, they appear to train even on API use:
> We may use Content to provide, maintain, develop, support, and improve the Services, comply with applicable law, enforce our terms and policies, and keep the Services safe and secure. Customer who requires restrictions on the use of Customer Content for training or improving Moonshot AI models may contact Moonshot AI to discuss available enterprise arrangements or separate written agreements. Unless otherwise expressly agreed in writing, Customer Content may be used for the foregoing purposes.
I fed it my most-read blog post and asked it to identify me and it confidently asserted it was written by Kelsey Piper. Maybe some writers just take outsized importance in Opus' "mind".
This has been my experience also, so far. I like a lot about this and want to start using it, but beyond the initial awkwardness of key bindings feeling wrong, it just seems a bit too early for me. For example, most of the agents I tried to get working on my Arch system failed to connect, only Claude Code and Vibe worked. Most worked on MacOS (except Codex, even though it's installed on my system). But I need to be able to set the agent into Bypass Permissions mode, and when I do, I'm still constantly prompted with permissions checks. There also seem to be weird errors caused by fish shell. I'd also really like to be able to define my own custom agents (eg one use case I'd like is to be able to launch Claude Code but swapping out the Anthropic endpoint for OpenRouter's so I can try new models using CC's agent harness).
It's possible this is just part of the learning curve, but it is making me think I'll have to come back to this project in a month or two to see if there are fewer pain points. Great work so far though.
Hey there! I'm Rowan. I've built and led software teams (at a molecular diagnostics lab and for a political advocacy project), built an award-winning synthetic bio video game, and have worked with startups and major research groups like at Stanford Health. Recent work of mine: published a survey of semantic search engines for science, building out python client for the vector database Antfly.
I don't consider myself a font snob but that web page was actually hard for me to read. Anyway, it's definitely capable according to my long-horizon text-based escape room benchmark. I don't know if it's significantly better than o3 yet though.
Hey there! I'm Rowan. I've built and led software teams (at a molecular diagnostics lab and for a political advocacy project), built an award-winning synthetic bio video game, and have worked with startups and major research groups like at Stanford Health. Recent work of mine: published a survey of semantic search engines for science.
Willing to relocate: yes, to SF, NYC, Seattle, Berlin, London, and possibly other EU cities
Technologies and tools: Python, TypeScript, AWS (+ a few certs), React, llama.cpp, MCP, HIPAA certified, experience with HL7 and EMR/EHR, competent in a wetlab
Hey there! I'm Rowan. I've built and led software teams (at a molecular diagnostics lab and for a political advocacy project), built an award-winning synthetic bio video game, and have worked with startups and major research groups like at Stanford Health. Recent work of mine: published a survey of semantic search engines for science.
Willing to relocate: yes, to SF, NYC, Berlin, London, and possibly other EU cities
Technologies and tools: Python, TypeScript, AWS (+ a few certs), React, llama.cpp, MCP, HIPAA certified, experience with HL7 and EMR/EHR, competent in a wetlab
Hey there! I'm Rowan. I've built and led software teams (at a molecular diagnostics lab and for a political advocacy project), built an award-winning synthetic bio video game, and have worked with startups and major research groups like at Stanford Health. Recent work of mine: published a survey of semantic search engines for science.
Technologies: Python, TypeScript, AWS (+ a few certs), React, Ansible, MCP, HIPAA certified, experience with HL7 and EMR/EHR
Hi, I'm Rowan. Would love to hear from you if you're working on data retrieval for agents. Previously built and led software teams, currently working on composing / semi-autonomous LLMs and climate data knowledge retrieval.
Willing to relocate: yes, to SF, NYC, Berlin, London, and possibly other EU cities
Technologies and tools: Python, TypeScript, AWS (+ a few certs), React, llama.cpp / local LLMs, Ansible, HIPAA certified, experience with HL7 and EMR/EHR, competent in a wetlab
Hey there! I'm Rowan. I have ~8 years experience in life sciences startups and research: I built and led the software team at molecular diagnostics lab, built an award-winning synthetic bio video game, and have worked with startups and major research groups like at Stanford Health. Recent work of mine: published a survey of semantic search engines for science and soon to launch a climate data research & analysis agent.
Humans becoming domesticated by benevolent superintelligences are some of the better futures with superintelligences, in my mind. Iain M Banks' Culture series is the best depiction of this I've come across; they're kind of the utopian rendition of the phrase "all watched over by machines of loving grace". Though it's a little hard to see how we get from here to there.
Dogs offer humans no economic value, but we haven't genocided them. There are a lot of ways that we could offer value that's not necessarily just in the form of watts and minerals. I'm not so sure that our future superintelligent summoned demons will be motivated purely by increasing their own power, resources, and leverage. Then again, maybe they will. Thus far, AI systems that we have created seem surprisingly goal-less. I'm more worried about how humans are going to use them than some sort of breakaway event but yeah, don't love that it's a real possible future.
Willing to relocate: yes, to SF, NYC, LA, or Seattle
Technologies and tools: Python, TypeScript, AWS (+ a few certs), React, llama.cpp / local LLMs, Ansible, HIPAA certified, experience with HL7 and EMR/EHR, competent in a wetlab
Hey there! I'm Rowan. I have ~8 years experience in life sciences startups and research: I built and led the software team at molecular diagnostics lab, built an award-winning synthetic bio video game, and have worked with startups and major research groups like at Stanford Health. Recent work of mine: published a survey of semantic search engines for science and built a shared LLM playground on top of the chat platform Zulip.
Technologies and tools: TypeScript, AWS (+ a few certs), Python, React, llama.cpp / local LLMs, Ansible, HIPAA certified, experience with HL7 and EMR/EHR, competent in a wetlab
Hey there! I'm Rowan. I have ~8 years experience in life sciences startups and research: I built and led the software team at molecular diagnostics lab, built an award-winning synthetic bio video game, and have worked with startups and major research groups like at Stanford Health. I'm currently consulting and writing on the side (I have a forthcoming article on the state of semantic academic search platforms) and looking for a product-focused technical leadership role at an early-stage startup.
Technologies and tools: TypeScript, AWS (+ a few certs), Python, React, llama.cpp / local LLMs, Ansible, HIPAA certified, experience with HL7 and EMR/EHR, competent in a wetlab
Hey there! I'm Rowan. I have ~8 years experience in life sciences startups and research: I built and led the software team at molecular diagnostics lab, built an award-winning synthetic bio video game, and have worked with startups and major research groups like at Stanford Health. I'm currently consulting and writing on the side (I have a forthcoming article on the state of semantic academic search platforms) and looking for a product-focused technical leadership role at an early-stage startup.
Technologies and tools: TypeScript, AWS (+ a few certs), Python, React, llama.cpp / local LLMs, Ansible, HIPAA certified, experience with HL7 and EMR/EHR, competent in a wetlab
Hey there! I'm Rowan. I have ~8 years experience in life sciences startups and research: I built and led the software team at molecular diagnostics lab, built an award-winning synthetic bio video game, and have worked with startups and major research groups like at Stanford Health. I'm currently consulting and writing on the side (I have a forthcoming article on the state of semantic academic search platforms) and looking for a product-focused technical leadership role at an early-stage startup.
Okay, but there is a reason that lots of people on here are fans of Kagi. Are you saying you're tired of hearing people praise Kagi or are you just annoyed whenever there's enthusiasm for a product that costs money?