This. So many of the matches are wrong. I’ve also tried a lot of these tools and they’re immature. I hate the SaaS model for consumer software but at least most hold a quality bar I can trust.
2,432 karma · joined August 8, 2014
Trump’s a smelly orange shit but the US at least pretends to have data privacy protections and we can’t legally compel companies to have back doors… yet. I think. It’s very hard to keep up with all the nonsense these days.
It doesn’t have to be better, it just had to be nearly equivalent. I’ve been doing a lot of vulnerability work lately (trying to get ahead of the bots finding exploits in our code) and the frontier models feel like a chaperone at a church dance: get too close and they show up with the ruler and enforce the safety margin. Using deepseek and glm and qwen, I’ve gotten nearly equivalent results without the constraints. I still use frontier models for things but outside of a company environment, I’m happy to spend 1/10 the money, get the same results, and not have try and trick the AI into working.
Didn’t need to vibe scribble a whole post to make the key point. Do what you do with your bots but keep them separate. Did AI make you forget the last 30 years of common sense?
We need to address violent tendencies in males and our ludicrous willingness to not see the reality of it.
Bias: I fought for things like Reader from the inside. If it doesn’t move needles, it goes away.
What I find really great is that we’re only a prompt or two away from proper docs for these novel solutions but we still don’t make them and if we do, we definitely don’t read them first.
EOM