priyadarshy

Joined 13 years ago

Karma

245

Submissions

Member since

Jan 21

[ my public key: https://keybase.io/priyadarshy; my proof: https://keybase.io/priyadarshy/sigs/4FGDHxkhQ55PEe9skkC5XciNMnnNJV5GpYUxGX1lplc ]

e6e042

View on Hacker News

Recent submissions

Sorry, my software is better with agents macro.land

4 priyadarshy 4 months ago 1 comments

Comment · 5 months ago

I think we're all under-indexing on how important it is going to be to be able to play-test an agent's changes before shipping it as a hedge against slop. I don't think people will do it unless it feels effortless, like clicking a preview link from a GitHub PR. If there's any friction, people will just click merge PR and move on with their life and your product-level slop will acccummulate.

I think high-taste products require you to actually use the thing that was built to feel the gaps in your spec.

I routinely find I am doing something dead simple that an agent will one-shot, e.g. add a new sort by option in the panel that lists a user's Linear tasks. If I looked at the PR diff I'd immediately think it was perfect and ship it. It's only when I actually get in there and play around with a dynamic UI that I realize, "you know this option really belongs at the top" or "hm, there's enough options here now that this dropdown feels cramped and we might need to consider another option". Simple examples obviously but the principle is that when I am landing the last 10% of a fix or a feature that when I need to interact and play-test. At the speed agents can generate fixes to new bugs or customer requests, I am bottle necked just doing that last 10% of steering and even the basic git mechanics to try something locally are enough to get me to not want to do it.

Right now, it seems like the state of the art is to review PR diffs and just merge them in or if you are more sophisticated have your agent generate screenshots or screen recordings. Screenshots and images are moving in the right direction but if you are building something interactive, you've really got to interact with it to know if it feels great.

My dream was to start my day with an agent having handled every bug and small enhancement request that came my way that day, worked on, and ready for my review, so I could spend an hour each day just steering them to the finish line.

I could do this linearly, picking off a branch an agent worked on, testing it and iterating but most of these small fixes each day aren't big brain stuff, I can effectively multi-task them but when I've tried doing it on my own machine it's either worktree hell, git gymnastics, or agents deadlocking - one agent wants to self test with Chrome MCP but can't cause another is editing code causing hot reloads.

I ended up building a Desktop app version of what OP posted to do this for myself and my team at Sunsama, it's called Macro: - Website: https://macro.land - Demo: https://www.loom.com/share/89c273e3a92d45cfb6860790d7b78bf6

I had a couple other specific needs that these repos don't cover: - I want complete control of what MCP tools my team uses and the ability to control their input/output etc e.g. I don't want someone using the Intercom MCP to accidentally reply to a customer with an agent. - I don't want my engineers spending time configuring all the boring stuff (preview urls, mcps, chrome mcp, etc) - I wanted the ability to steer agents to the finish line together. In Macro, any user can join the chat and steer the agent e.g. a colleague with UI taste jumps into tweak the last bits - I want to see common failure agentic failure cases across my team so I can improve our Claude.md and agentic practices so all work flowing through one interface allows that

Comment · 1 year ago

The wildest thing I read was:

> Harvard will immediately report to federal authorities, including the Department of Homeland Security and State Department, any foreign student, including those on visas and with green cards, who commits a conduct violation.

Conduct violations at Universities are a pretty broad set of rules at universities and don't necessarily line up with what's legal or not but more with the university's cultural and social norms.

Comment · 1 year ago

Her sleep is terrible since she's breastfeeding, so even when she does get some sleep, it'll be while dozing off in some unexpected and ergonomically diabolical position.

For our first baby, I had that on-edge feeling, I woke at every hint of a cry but this time I can just sleep through it and rely on my wife letting me know if I'm needed. It's not fair but it means at least one of us has the emotional resilience to deal with our toddler during the day :)

Comment · 1 year ago

I've recently been on a five week streak of 100% sleep scores on my Whoop (couple days of 98%) by "volume" sleeping at consistent times. The five week streak started on the day we came home with our second child and we changed our sleep routine.

Me, my wife, my 2.5 yo, and newborn all get into bed (or bassinet) at 8 PM. From 8 - 9 PM we're juggling feeding newborn, reading to toddler, and signing toddler to sleep in whatever order is necessary for that night. Then we sleep around 9 PM till 7 AM with multiple wake ups for diaper changes in the night.

As the newborns gotten longer stretches of sleep, so have I and I can tell my sleep quality is better. I do see significantly higher REM/SWS times on a night where I do one diaper change versus 4 like the first week.

Subjectively, my sleep quality is bad - I feel tired but way less tired than with my first when I didn't try and "volume sleep". But my Whoop is happy to hand out 100% score because I've gamed the system with an insane amount of hours.

Given the circumstances, I'm sleeping as well as anyone could hope. And there might be some value in just "being in bed" longer if you can't guarantee sleep quality. I know I'm way less tired than I was with my first.

Comment · 2 years ago

Is the final image on the splash page demo (with the car) from Cal Ave in Palo Alto?