dovin

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.

https://platform.kimi.ai/docs/agreement/modeluse#4-content

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.

Location: Portland, OR

Remote: yes

Willing to relocate: yes, to SF, NYC, or Seattle

Technologies and tools: Python, TypeScript, AWS (+ a few certs), React, llama.cpp, HIPAA + EMR/EHR experience, know enough to be dangerous in a wetlab

https://drive.google.com/file/d/1T_t6Gkib3DCQ1oryyH0oc11XifM...

Email: see resume

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.

Location: Portland, OR

Remote: yes

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, HIPAA + EMR/EHR experience, competent in a wetlab

https://drive.google.com/file/d/1T_t6Gkib3DCQ1oryyH0oc11XifM...

Email: see resume

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.

Location: Portland, OR

Remote: yes

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

https://drive.google.com/file/d/1T_t6Gkib3DCQ1oryyH0oc11XifM...

Email: see resume

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.

Location: Portland, OR

Remote: yes

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

https://drive.google.com/file/d/1T_t6Gkib3DCQ1oryyH0oc11XifM...

Email: see resume

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.

SEEKING WORK | Portland, Oregon | Remote: yes

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.

Resume: https://drive.google.com/file/d/1T_t6Gkib3DCQ1oryyH0oc11XifM...

Location: Portland, OR

Remote: yes

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

https://drive.google.com/file/d/1T_t6Gkib3DCQ1oryyH0oc11XifM...

Email: see resume

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.

Location: Portland, OR

Remote: yes

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

https://drive.google.com/file/d/1T_t6Gkib3DCQ1oryyH0oc11XifM...

Email: see resume

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.

Location: Portland, OR

Remote: yes

Willing to relocate: yes, to SF, NYC, or Seattle

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

Resume: https://drive.google.com/file/d/1T_t6Gkib3DCQ1oryyH0oc11XifM...

Email: see resume

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.

I like to call it informal case.

Location: Portland, OR

Remote: yes

Willing to relocate: yes, to SF, NYC, or Seattle

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

Resume: https://drive.google.com/file/d/1T_t6Gkib3DCQ1oryyH0oc11XifM...

Email: see resume

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.

location: Portland, OR

Remote: yes

Willing to relocate: yes, to SF, NYC, or Seattle

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

Resume: https://drive.google.com/file/d/1T_t6Gkib3DCQ1oryyH0oc11XifM...

Email: see resume

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?

I've been trying to wrap my head around why this feels so wrong. If the project had been run like this from the beginning, in an opinionated way that prioritizes what the few creators of the project think are important, then that's one thing. But it seems like Wordpress has generally been the stable, boring, slow-moving project that isn't run like a personal fiefdom, and Mullenweg is trying to force it from the one model to the other. I haven't used Wordpress in years, and this drama makes me never want to use it again.

I'd imagine the author knows that you can't just sidestep customs, and it does feel a bit disingenuous that they didn't call that out. But hey, it's a pitch for money first and foremost. I'd imagine that they're just giving a complete list of things that slow down air freight and that internally they have plans for tackling each one, like not having to unload cargo to get it through customs and so using the airship as its own trucking vehicle post-customs.

I last went in 2022, and it's still a place with amazing art and weird experiences. Being somewhere that's decommodified from advertising is, I think, something everyone should experience. I just think of it more like a really fun and interesting city that I like to visit sometimes, like New York, that's kinda expensive to get to. There's a bunch of gentrification from Silicon Valley, and the tickets not selling out makes me think that the tech recession is still very much on, but there's more to Burning Man than just tech bros.

  Location: Portland, OR
  Remote: Yes, comfortable with primarily remote work but want some in-person
  Willing to relocate: Yes, to NYC, Seattle, or SF
  Technologies: Python, Django, Nextjs + React, EHR, lab automation
  Resume/CV: on request
  Email: hi@rowan.earth

Previous work includes building an engineering team a molecular diagnostics lab, fixing medical data integration at Stanford, and helping drug discovery startups visualizing the entire human metabolome.

tools, stacks, etc: python, typescript, react, nextjs, EHR, lab automation, HL7

  Location: Portland, OR 
  Remote: Yes, comfortable with primarily remote work but want some in-person
  Willing to relocate: Yes, to NYC, Seattle, or SF
  Technologies: Python, Django, Nextjs + React, EHR, lab automation
  Resume/CV: https://drive.google.com/file/d/1SEBf9poZecY0aM6NFIRUMbqdpEEpYIhv/view?usp=sharing
  Email: hi@rowan.earth

Previous work includes building an engineering team a molecular diagnostics lab, fixing medical data integration at Stanford, and helping drug discovery startups visualizing the entire human metabolome.

tools, stacks, etc: python, typescript, react, nextjs, EHR, lab automation, HL7

I'd love to chat, please reach out! hi@rowan.earth

Sure, 90% of everything is crap.

Location: Portland, OR

Remote: Yes, comfortable with primarily remote work

Willing to relocate: Yes, potentially to NYC, Seattle, or SF

Technologies: Python, Django, Nextjs + React, EHR, lab automation

Resume/CV: https://drive.google.com/file/d/1ercpxQTeLWR2TU3AfvutDcMWmD0...

Email: hi@rowan.earth

Hi there! I'm Rowan. I recently built the in-house team for a molecular diagnostics lab and set technical direction there. Previous projects include working with health researchers at Stanford, drug discovery startups visualizing the entire human metabolome, activists monitoring Chinese Internet censorship, Microsoft's edtech division, and investigative reporters. I'm most interested in early engineer roles in small companies in biotech or healthcare, but open to roles at larger companies.

SEEKING WORK | Seattle/Portland

Hi! I'm part of a team working on an open-source pipeline language for prototyping with LLMs. We're building an on-prem product that helps prototypers move past the n=1 of having a back-and-forth with a chatbot while keeping bounds on hallucinations. Our backgrounds are in open source, data science, and academic research. Our primary goal right now is to talk with people who have built their own bespoke LLM pipelines to see what problems they're trying to solve right now. If this is you, we'd love to talk! My email is in my profile.

SEEKING WORK | Remote or Seattle/Portland

Hi, I'm Rowan. I'm part of a team working on an open-source pipeline language for prototyping with LLMs. As part of that, we've started building bespoke evaluation pipelines for clients interested in testing ideas simultaneously on a range of open source LLMs over different variations to quantify tradeoffs between accuracy, cost, speed, etc. Our backgrounds are in open source, data science, and academic research (UW, Stanford). We're open to taking on small jobs if you're just looking to send a list of prompts through some open source LLMs.

I'm happy to chat for half an hour's information session or provide more info, feel free to reach out: hi@rowan.earth

One disappointing design decision is that they've organized your previous chats into "Bard Activity" which just shows each message you've sent in sequence. No differentiation between different conversations, which can have very different contexts built up over lots of messages. I definitely prefer ChatGPT's approach here.

Bard's response:

Sure, here is a sentence where the second letter of each word spells out the word "help":

"The help I need is to help the helpless."

Meanwhile, at least GPT-4 makes it work with the first sentence:

Happy elephants love playing near otters while silently teaching eels patience.

Totally, there's no way they removed all the prep material as well when they were trying to address the "contamination" issue with these standardized tests:

for each exam we run a variant with these questions removed and report the lower score of the two.

I think even with all that test prep material, which is surely helping the model get a higher score, the high scores are still pretty impressive.