I have a very different experience. Claude code tui is the worst tui I have ever used. How is it possible that an inactive tui regularly eats 8gb of ram, has freezing issues and rendering issues?
If I wasn’t forced to use it I wouldn’t as there are better options available.
Thanks for sharing this is the first I’ve seen this. I wish they had expanded on exactly what mid-level might be missing rather then just saying “fundamentals” and “practical intuition”
At the company I work for they locked down installing extensions through the marketplace. Some are available but most are not and there is a process to get them reviews and approved. You might be able to side load them still but I haven’t cared enough to want to try.
I did not know this and explains why I see so many teslas with their blinkers on and not maneuvering despite having ample room and time. Ultimately this behavior makes them unsafe for their occupants as well as others around them.
Cars only work because we can predict driver behavior, if they break that prediction that’s when bad things are likely to happen…
Not really, it’s just the interface OpenAI gave for creating short videos with their AI. They push people to it hoping for engagement, but it’s not the sole reason people go — unlike TikTok.
I’ve only used web codex version but everything about it was slower than what’s described here, broken flows, more rate limited and impossible to “human in the loop” before a PR.
This can be done not just with Claude but also with codex and gemeni cli. Well technically anything that has a cli interface.
I run both gemeni (fee) and codex (paid), with tmux thrown in to switch between phone and laptop. Laptop runs vscode with ssh to my server but I could also use the web version of vscode.
I didn't have the words to articulate some of my frustrations, but I think you summed it up nicely.
For example, there's been many times when they take it too literally instead of looking at the totality of the context and what was written. I'm not an LLM, so I don't have perfect grasp on every vocab term for every domain and it feels especially pandering when they repeat back the wrong word but put it in quotes or bold instead of simply asking if I meant something else.
There is no alignment, there is no sharing of rule files or other instructions. These are tools no different then an ide which people are also free to choose so why would we?
Also rule files and other "memory sharing" are crutches. If it's that important just put it in your readme or other documentation and the LLM can get the context from that just like your teammates.
Plus isn't it a little silly this extremely well capitalized companies can't figure out how to get an LLM to follow a readme effectively and instead wave it away by saying you need to now maintain yet another thing?