Opus directs and starts haiku/sonnet subagents. Much more efficient than opus reading it all.
Without this explicit direction, Opus burned through usage to create complicated regex parsers & 8 excel sheets.
9 karma · joined October 5, 2021
Opus directs and starts haiku/sonnet subagents. Much more efficient than opus reading it all.
Without this explicit direction, Opus burned through usage to create complicated regex parsers & 8 excel sheets.
ello looks great, great work
main comment was a bit tongue in cheek
True startups need only senior+ and big ones don't wanna interview often.
Now am laid off, and hard to find a job...
Only had basic python knowledge going in (new grad mech engineer on pumps/pipes). built on flask / python / heroic / GitHub.
Small team, some awesome people. Changed my life. for now, back to being laid off.
80%+ done MVP, for small business use & personal use. First go at full stack development with AI. useful features around voicemail, notifications, and spam prevention (whitelist, blocklist). Built to be robust, secure and available.
2. Intelligent understanding for videos, No MVP yet. Have an interface and use-case in mind that allows people to use understand videos with rich context quickly
currently on pause for leetcoding but I think there's potential here.
AI is not a feature of the product. GTM will be interesting, have some good ideas.
It's really up to you to be clever. I've never used Js/Ts/node/these apis etc. I started programming as a non-cs engineer to automate stuff and then got into SWE. This is truly an amazing time.
Does your software do anything fancy or is mostly for organization, good workflow, and being the central source of truth?
Did it require a lot of development after getting a few customers on boarded?
are you a 1 man show?
Instead of maintaining a catalog of tools like read_file, grep, list_dir, they just expose one run(command: str) tool and let the LLM compose Unix pipelines. It has access to one tool for shell commands: run(...)
I think you could use mcp-shell , written in Go instead of python subprocesses
Also, depends on who target user is.
AI can be used to build deterministic software
AI makes a ton of bad decisions too and it's up to you to work with it. If I had the knowledge of the dangers hidden in things I'm developing, I'd move even faster
Was able to make a great full web app, which I think is hardened for prod but it had to be refactored to do so. Which it happily did.
It's really about asking the right questions, breaking down tasks, and planning now. I'm going to tackle a huge project, hoping to share it here.
2 devs on teach team were truly 10x before AI; each has 15-25 yrs of exp on very small teams, great at so many things: code - infra - linux internals - networking - incredible debugging skills - keep up with good practices - great docs - and desire to do things the "right way" - IQ + horsepower.
The other good senior devs may do some of those things.
My title is Senior 2 b/c I negotiated a raise during interview, but am mid-level at best. Now laid off.
looked more into swing vision and there's so much to it, looks like a great tool
I'm very interested in working with DDOG. Would love to quickly chat to see if I'm a good fit and what I can do over the next few months to become a stronger candidate.
my summary: I have 3 years of reliability engineering as a mechanical engineer + 1 year in tech (python + aws + kubernetes + ci/cd)
Strong communication skills, growth mindset, entrepreneurial experience :)