mshafir

yeah but to be fair, those all just show posts with the same title. This one actually come up with pretty good headlines and summaries based on the articles themselves and I think actually are quite good for LLM-written content. It probably took some effort to get it to match NYT tone/style in writing and I found some of the headlines much better than the original ones though some of the charm of HN is titles that are unclear enough to make you go to the article only to find it's not about what you thought.

Might appreciate a print version of this mailed to my house :)

Gave it a try, neat idea. I would like something better suited for more ad-hoc meetups that is less commercial feeling. - would like if the member map defaulted to my location - open in sidebar on the member map doesn't do anything for me in chromium and I feel like that should be the default when you click on someone - option to suggest new interests - Profile should have an edit button versus totally separate pages for profile and edit profile - Custom social links would be nice, would love to have my github there

Would love to see something like this get more traction!

How does that compare to Inngest? As I understand it it also executes inline and has a streaming connection to the inngest server. We ended up going with them over temporal because it was so much simpler operationally, but restate seems even lighter. I can appreciate how it's hard to tackle the enterprise market, but the temporal solution feels so bloated I really hope the industry can standardize on some simpler patterns

If it’s on my own cloud why wouldn’t I just vibe it myself? I want the organization of work to be multiplayer but I want to run the session myself especially because that means I can still use my subscription vs pay per token. There is so much competition in this space, you need more of a differentiator than your own cloud I think.

Thank you for this, as somebody with almost no background in chemistry, I can now appreciate just a bit more the complexity that goes into battery development. Where does one learn about this?

It resonated with me too, and even as a once fairly prolific coder that now uses agents to do all the coding, I feel like this is all relevant and does matter. The agent does whatever you ask and provides thin judgements based on what it thinks is your motivation and context, even feeding it the context it will often make bad generic choices. I think this is the part hard to optimize because it's not a verifiable reward, it's the feel of the software. I think Herdr is a great example, I've tried several dozen terminal multiplexers / session aggregators and they are all vibed and different, but this one felt so much better to use because of its choices and actually increased the number of parallel sessions I was able to keep going. My own projects I find I have to stress every detail, that is what makes the software good now is really diving into it, the experience feels like just as much of a craft as coding was and 'taste' captures the concept for me.