I'm noticing more and more AI writing everywhere, from youtube to this article: From the subtitle: "Nothing complicated, answers only one question: " clearly LLM generated.
In 2026 a Junior Engineer is just Claude Code with a bad UI, higher latency, and extra steps. Literally.
I wouldn't even considering hiring a junior engineer at this point. The ROI was already barely breakeven for any but the top of the top junior engineers as they are likely to move on before they are meaningfully contributing.
With AI in the mix the ROI for Junior Engineers is strongly negative for 2 reasons:
1. (obvious) I can just have Claude Code do the work a junior engineer would have done with faster turnaround and generally better results.
2. (less obvious) Junior engineers are going to just turn around and use Claude Code, so now I'm talking to an AI and playing the telephone game, and the Junior engineer isn't going to learn much if anything in the process.
It's an extra 6 months or so, and it's almost certain a better solution won't be come available in that 6 months, and even if it did you are very close to death and unlikely to recover even if a miracle cure is developed. In the meantime you are in intense pain and suffering wild side effects.
While it's a useful scientific achievement, and I am not second guessing any individuals decision, and any time is likely tempting to take if even to have time to make arrangements, this still only gives about 1 year survival on average to the scenario being quoted in the title, and that year is gruesomely painful.
Yea this is great advice: the people who actually know how to build machine intelligence should go read the notes of the people who literally had no idea how to do it. While they are at it, we should have NASA go read Jules Verne so they can use his ideas in the next manned missions.
blah blah we know that blah neuroscience blah blah blah.
This isn't an argument you are making, it's just an assertion that you could make an argument if you are so inclined, but you won't be doing so at this time, but "science" is obviously on your side, but you can't be bothered to say how or even enough detail for someone to check what you are referring to. I can do that to, see my first sentence in this reply.
I don't know how LLM memory systems work. I do know that you don't have a lifetime of remembering everything with high precision. Not only do most people not remember the plot of most of the movies they have seen, they can't reliably list most of the movies they have seen. Not everyone has a good memory. My point is that it's not valid to reference a false model of how human memory works as a reason some specific LLM memory implementation isn't useful for solving some problems.
You don't remember a lifetime of smells. You don't have any memories from huge swaths of time. There are entire years of your life compressed down to vibes and a handful of events you largely misremember.
These libraries are not more human friendly. Humans can write GTK or win32 or QT or Cocoa code just fine. GUI frameworks are very complex and often have very in depth setup code that is required. It requires a huge investment to get an app up and running with a GUI framework, and AI makes setting that up approachable when it was a real challenge before.
Have you ever written GUI code using one of the big GUI frameworks?
Don't listen to anyone who knows what should be done without proof. If someone 'knows' what agents 'need' then that knowledge is worth millions of dollars right now. If they haven't built it they are probably just talking shit.
I think AI coding has made these "we dumb down a real UI framework for you" libraries obsolete. Anyone can get a GTK or QT app up and running now. This isn't a criticism, they were very useful to build GUIs in the past, but now they are just obsolete and more likely to introduce bugs or limitations you can't work around than to help much.