Many people say that AI hit its limit and peak
Oh probably not, but it is really really expensive to run. If they continue on with unlimited funding, they can eventually replace mid to upper level experts in most fields.
We’ve likely hit the limit for the current LLM approach. Training/Pruning/Distilling can’t get us much further on their own, so now we’re strapping on code, having it plan, parallel execute, test. Tokens are likely 10x less expensive on the market than they cost to generate. Every advance we make now is by making each request fire off many more requests. Improvements are getting exponentially expensive.
We’ll have to slow because financially * it’s not profitable. Maybe hardware will catch back up. Maybe they’ll find ways to make it more efficient. Maybe we’ll figure out a more elegant way to do the math for the weights. We just can’t keep making it more deeply complicated because it’s not cost/energy/time effective
edit: deleted a word
Wide scoping like that rarely ends well. Give it the list, tell it to spin a new agent for every single issue and operate on them separately. If any of those agents run out of context memory, it will just shit the bed. Clarify that you need the test to actually work and not be commented out, and that the tests themselves still need to be viable and indicate a healthy working app, not just report that it’s healthy. Trying to get tests happy in AI is like making wishes on a monkey’s paw. Then assign someone to look after it because that bastard will chew through 10’s of thousands of dollars to fix a laundry list of tests, which in my dev experience will be all broken and ignored in 2-3 minor releases.
You can generally get it to do things, even somewhat complicated things, but it’s not easy, and the shit it gives you back while you’re trying to convince it to do the job is the same stuff you’d fire an employee over.
My favorite thing is to make it make ansible tools, They’re easy to read, easy to lock down, keys and passwords go in a vault that it’s forbidden to read. Then I have it write runbooks on how to operate the playbooks. I then make an index of runbooks, and ask it to do them. It’s an ansible job, so I can read it easily and make sure it’s not able to delete my drive or my production database.
If I lose access to cheap tokens, everything I’ve making is still usable, and for now, I can spend my time working on stuff that’s not simple enough that it can handle it well.