mzhaase

Always comes back to fundamentals: defense in depth, principle of least privilege, patch your shit. Almost every security issue comes from violating one of those.

I've done that too and given up on it. They got longer and longer, the LLM started adding them itself despite specific instructions to not do that, and in the end it let to context bloat. Better of without them.

A significant part of the corpus is marketing copy.

A lot of those games are attempts at cheap cash grabs more than "I can finally make my dream game".

AI will bring on the biggest gatekeepers of them all: the ones that own the compute.

I see a different outcome.

- significant amount of money that used to be wages now paid to AI companies

- causing significant power shift to the owners of AI companies

- significant amount of people out of jobs, at the same time blue collar workers still have to work

- causing anger and resentment within society

- fueled by AI owners who will train their models to subtly argue in their favor

- protecting themselves with drones

- significant amount of countries simply go bankrupt or fall apart

- unable to let go of the basic capitalist mindset that cannot work when there simply is no available work for many people

Suffered from ADHD my entire life (undiagnosed). Fixed my chronic insomnia pre-diagnosis. Sure it helped a bit but not even close to medication.

It's already the case. I know a professor and he says most of his students PhD ideas are AI generated, meaning they are outsourcing the fun stuff.

My understanding, and I would love for someone to explain why, is that they measure current with a shunt resistor which is fine for inductive loads like a water heater, but not fine for a big motor for example.

Dashcams are banned for example in Germany.

Wow, 24 years of Linux, I never bothered to look it up. Thanks.

It is in Germany for example, same as sysadmin and IT-Electrician. They all go to trade school. Personally found it a bit useless though.

I've done that too, called it Decisions. Was happy for a while, but then the agent started to make decisions longer and longer, putting "x, not y" in there. It started to write them without asking. Suddenly in code review it would say "violates D-236". Some rule it made up that I never approved. Then I made very clear that it should never touch those files. Still does. Now it's just context bloat.

Do agents actually follow it though? Everything I tried that was not just simple instructions had the same failure mode : ADR, mnemonic, hindsight, code-review-graph, etc were simply ignored by agents after a while. They always fall back to their baseline: grep and Python.

I remember back in the late nineties / early 2000s drive failures really were pretty common. During my childhood I think I had three. I've never had a catastrophic failure since then, really came a long way.