I use both. Not because I am cool, but because it is cost effective for personal projects with two $20 / month plans. It is also nice to be able to see what the state of the art is like for both.
Personally, I find it very interchangeable. I open codex --yolo or claude with whatever there yolo flag is (have an alias).
I don't think it is meant to be objectively the most efficient interface. It is more about being remarkable in a Seth Godin sense. For me I just want things to be blazing fast inside the dashboard.
I've notice that as well. If you don't know how to do something having an agent with tools is great (in general, not just PH). But, its also quite slow and imprecise. I think that having the agent act more as both a teacher and "doer" is best.
What I don't understand is, what kind of legitimate criminal would not use such techniques? Are bank robbers planning things out on iMessage? If so, presumably they won't be criminals for very long. Therefore these types of initiatives only impact the innocent and inept but still active criminals.
Its hard to find a middle ground between fully understanding everything in a PR vs a vibe coding type approach. Can you understand "just a little bit" of a PR and merge it into a code base you really care about? Is it maybe fine to "mostly understand it" on the other hand? Its definitely a tough call and its impossible to argue that no trade off is being made.
LLMs are perfect for quick prototypes, speed runs, learning, etc., but if the code really matters its still not clear cut. I think the definition of what "really matters" is very project dependent of course As an extreme example you would want to understand every line of the code for the control system runs an MRI machine or a jet engine since bugs might mean life or death. Depositing money into the wrong account might not kill anyone but could lead to severe economic losses. But, then again, even problems in far less consequential software may be drastically sub-economic (i.e. saving $1000 on the implementation might cost $10000 if customers aren't happy and fails to re new). Pick your scenario I guess.
The problem is, this isn't going to change regardless of how well a new model scores on a benchmark. It seems actually AGI is needed.
A 2nd year project back in the day was to build a 4 bit CPU on a breadboard. We had the advantage of having an ALU IC but was still quite tough to get working!
I think a better metric these days is what percentage of code is not reviewed / understood by humans. That is the real bottleneck. Until we can stop looking at the code, AI barely matters - you are just trading quality for quantity.
Thats why it is so amazing for speed runs and prototypes. Here it is legitimately > 10X faster.
It doesn't help shareholders or customers in any way however so we should not celebrate it or even simply accept that this is "the way things are". It is an error to be corrected.
Personally, I find it very interchangeable. I open codex --yolo or claude with whatever there yolo flag is (have an alias).