burcsahinoglu
Re:Software is breaking down at a systemic level
on Monday November 16, 2026 @01:56PM (#50521404)
I agree with you. I can see how we might be accelerating decoherence with AI, but maybe it won't ultimately matter. I just don't know.
Re:Eclipse Mosquitto – An open source MQTT broker
on Sunday November 15, 2026 @03:37PM (#50510440)
I had a terrible time with a cluster of RabbitMQ servers, the cluster was partitioning often, impacting the application. It seemed like it was very sensitive to transient network problems.
At the end we moved from a cluster to a single instance running on a over provisioned machine, that worked pretty well.
Trust in Depth: Giving agents more autonomy without losing control
Re:Tesla Roadster
on Friday October 16, 2026 @04:14PM (#50123945)
it's a cat.
Re:500B Tokens Later: Letting AI Agents Decompile a First-Person Shooter
on Sunday October 11, 2026 @01:38PM (#50045712)
In my project I've been practicing a similar loop as you describe: an agent writes code, SMT solver checks against a spec. A few things I observed:
1. Solver is great at the bugs tests miss (overflow, off-by-one, empty inputs...), its output can be used by the agent to fix it.
2. Solver struggles where you'd assume: loops, non-linear arithmetic and pointer aliasing blow up solve time, floating point is painful.
So your step 2 would cover some of it well, but since the game code is a lot of floating point, SMT would probably have a hard time (get stuck/timeout).