Mo MSGM's profile on Product Hunt

About

Hi Building AI agents that do real work, not demos. 5 years writing production code, went from SAAS to obsessing over how to make LLMs actually useful instead of just impressive Into markets, geopolitics, and whatever's happening in AI this week. Always up for talking shop

Links

Github

Badges

Gemologist

Tastemaker

Tastemaker 5

Gone streaking 10

View all badges

Forums

p/meridian-16

•

1d ago

We’re at war with closed source. Help Meridian become Product of the Week.

Three months ago, my co-founder and I quit our jobs to build Meridian full-time. We wanted developers to have a tool they could actually inspect, control, and trust.

Meridian is an open-source, local-first AI work journal. It runs on your device, captures the work that usually gets forgotten, and drafts worklogs and Jira updates for you to approve. Your data stays with you.

You helped us reach #1 Product of the Day. Now we re going for Product of the Week. If open-source software matters to you, support Meridian and tell us what you think.

Product Hunt: https://www.producthunt.com/prod...

•

1d ago

A single line of Python made my validator silently stop checking after the first failure

Wrote a script to validate blog drafts before publish. The check was all(validate(p) for p in sys.argv[1:]). Ran it against a 125 file backlog and got back exactly one line of output.

all() on a generator expression stops at the first False. Every file after the first failure never even ran through the checks, let alone printed anything. It looked like a clean pass because there was one failure and then silence, not because 124 files were fine.

p/murror

•

9d ago

AI didn't remove your bottleneck. It moved it onto the one person who can't scale.

Throughput per developer is up 33.7%. Median time in code review is up 441.5%. If you're a solo maker, you are the review queue and you quietly stopped showing up for the shift.

There's a report that came out this spring that I keep coming back to, and I don't think it landed properly with makers because it's written for engineering leaders at big companies. Faros AI published "The Acceleration Whiplash" in April two years of telemetry from 22,000 developers across more than 4,000 teams. Not a survey about how developers feel. Actual measurement of what came out the other end.