Mari Luukkainen (@mariluukkainen) header
Mari Luukkainen (@mariluukkainen) profile picture

Building

Helsinki, Finland
Joined July 2010
Volume is pretty high when you give agents autonomy to find and fix or improve things. I have now (finally?) set up my VC-era laptop to just run improvement loops for everything. It finds bugs and errors and uses my own analytics and PostHog to find improvements autonomously. It also does regular browser checks, which seems to be a very optimal way for agents to find bugs and UI/UX improvements (instead of just reading code). I was kind of hesitant to give it this much autonomy, but with some iteration it actually seems to work very, very well. The future of code development is definitely this, that agents just take care of everything autonomously, and it is most likely the only way to keep up with agentic attacks too.
1
1
247
Open sourcing be like
122
Love how unhinged @bot is
1
151
Multilingual content site's autopilot on pangoling
142
Chili peanut sauce focaccia
1
6
274
Replying to @peer_rich
AI not slowing down anything
23
Meeting @sunrao had a slight boost on my Grok Bot activity 😄
173
Norwegian content site does well, even I don't speak Norwegian
194
Shipped 200 updates while taking a nap
3
1
19
1,692
Classic Stella Montis
157
Only site from my portfolio of 100+ the spam updates totally nuked. I tried to recover it, but it'll be easier just register a new domain and start over
243