chrisjh

Looks good OP - I frequently look at the stargazers list for various repos and see if there's overlap in interest between projects. I imagine this is about as good as targeted marketing as you could get for software, but I'm curious to hear if devs respond well to "hey you use/like/starred X, want to try out Y?"

Please don't waste your time on this. It's emblematic of a company that doesn't know what they are doing and you probably don't want to work there. There should at least be some sort of skill-fit screening on their end (quick casual chat or specific filters on resume) that doesn't require you spending hours of your time doing unpaid work.

Prompt engineer was likely never a career path, I’d imagine most software devs knew this from the jump. I think any engineer can work with the modern LLM solutions available — considering software engineering was already a form of pseudo-prompt engineering, but the feedback loop was with yourself, google, and stack overflow.

The product I’m building is predicated on prompt engineering and it works really well for us — our results need to be as accurate and structured as possible so they can be re-used as software dependencies. We do this by auto-generating a context on the fly and tailoring it to your specific data sources (databases, APIs), sampling data, and so on. We do both manual and "auto" tuning of the context to provide the best results.

We like the “Supabase for data engineering” nomenclature — we’re a managed service that does the heavy lifting to unify your data sources. Velvet enables you to join volumes of product events (from sources like Amplitude or Snowflake) with your application database(s) and query them directly in an accessible way. Plus, use your Velvet queries as interoperable building blocks to collaborate and build features within your product via our API.

Earth Abides by George R. Stewart takes place around the Berkeley area in a post-apocalyptic world. Not quite sci-fi but a fantastic read nonetheless.

Another post earlier today brought back the memory of this game. Incredible that it is still playable all these years later!

I have similar thoughts on this - so few members of a team actually know what the underlying data model looks like. Gets even harder when you start trying to query across your database(s) + external sources like analytics/event systems. Natural language lets the whole team peel away at the black box of data and helps build common ground on which to improve products. I already mentioned it in another part of this thread so I won't spam my project but would love to get your feedback on my natural language to SQL tool if you're interested.

I've mentored people that have wanted to change roles into product management for years. Please feel free to reach out, happy to chat about it. My email address is in my HN profile.