Something freeing to me that my wife said:

"If you get rid of clutter, there will be cases where you'll have gotten rid of something useful at that moment. It's not about avoiding that -- it's about accepting the right tradeoff between cleanliness and functionality."

Most of us here also work in tech and get paid pretty high salaries. It's pretty inconsequential for us to buy a replacement when we need it, and donate when we declutter.

Anyone know any interesting OSS Slack alternatives with a decent API?

I've heard Zulip is a good alternative

Not just a decent API, but fully open-source and self-hostable.

I know plenty of nondeterministic accountants

The lack of broad benchmark reports in this makes me curious: Has OpenAI reverted to benchmaxxing? Looking forward to hearing opinions once we all try both of these out

The -codex models are only for 'agentic coding', nothing else.

You could have to your chat give them direction

Have you checked out t3 stack? Curious which pieces are missing from that that you'd deem critical

Yes, it’s good, but not nearly as batteries included as it needs to be. Also all the dependencies move separately from each other in development

Most of us probably do the same thing when we read a HN comment about something specific: "This rando seems to know what they're talking about. I'll assume it as fact until I encounter otherwise."

Not doing this might actually cause bigger problems... Getting first-hand experience or even reputable knowledge about something is extremely expensive compared to gut-checking random info you come across. So the "cheap knowledge" may be worth it on balance.

I wish the source citing was more explicit. It would be great if the AI summary said something like, “almost no info about xyz can be found online but one GitHub comment says abc” (link)

Instead it often frames the answer as authoritative

Just to throw into the mix: apparently sitting in a hyperbaric oxygen chamber does. Who would've thought.

In case you find it interesting: I deployed an early version of a "lesson administering" bot deployed on a college campus that guides students through tutored activities of content curated by a professor in the "study mode" style -- that is, forcing them to think for themselves. We saw an immediate student performance gain on exams of about 1 stdev in the course. So with the right material and right prompting, things are looking promising.

Everyone ITT will hate me for saying this, but: T3 stack.