A new model drops, and my feed is once again flooded with one-prompt bullshit engagement bait. Exploration and experimentation are one thing, but it's painfully obvious when something was made purely for engagement.
I want to see ambitious, polished, shippable work that took real effort, skill, and creative direction, where AI helped make something possible that otherwise wouldn't have been.
Went back to codex desktop today to do some tax prep stuff and holy hell the ChatGPT desktop app is falling apart
There's so much here I like and want to use, but it's such a slow, janky, incoherent mess it's impossible
The new "spaces" feature is actually amazing. Such a good idea that I've been building a lot of my video pipelines around, the only problem is that buggy and the UX is a dumpster fire
It seriously feels like there are 5 companies all working on their own products who have to ship them all together in the chatgpt desktop app while not being allowed to talk to each other
Go back and look at Dev day, they shipped 30+ features. Almost all of these are dope and useful. The problem is you haven't heard of 80% of them and it's all just floating around in this blob that's chatgpt
This stuff is hard, I don't envy the position they're in. You have to keep shipping as fast as possible so you don't fall behind, but you also need time to polish and organize things. And this has to be coordinated across a bunch of teams and dozens of people and hundreds (thousands) of agents.
I could go through all the specific issues but 1) it'd take too long and 2) anyone who uses it already knows most of these (very laggy, sidebar sucks, features are too hidden, spaces "tabs" system is a mess, etc.)
Codex desperately needs a dictator with an actual coherent vision
i love writing. i never let agents write for me. whether it's docs, or tweets, or shitposts, or even prompts (okay maybe that one's harder as agents manage other agents)
there's a simple reason for that: i still strongly believe that writing is thinking. it's a skill i hope to never give up. it's also important to me that whatever i say is always authentic, mistakes and all. my favorite posts are the ones that i just full send without any editing
i suspect it also helps with prompting. being able to clearly express what i want, and knowing the vocabulary i need to be able to direct my agents does seem to make for more effective usage of agents. in the same way that engineers have an advantage when we prompt agents to write code, because we are intimately familiar with the words that make up the discipline
knowing the right word incantations to get an agent to produce a desired goal almost feels like spellcasting. as models get more capable, and that input box looks more and more like a magic box that can output anything, words become the interface between you and the genie
there may come a time when we give up the keyboard in exchange for brain-computer interfaces. but until then, i'm writing every word.
WHY does codex cli not share memory with chatgpt chat and work... should give us a unified memory layer between all surfaces so i can just point cli at a random chat i had