LLMs write. It sounds glib but it's what they do, and so every problem they encounter they will try to write their way out of it without lots of hand holding.
Yea I say something similar. LLMs have a tendency to add, because there are many more tokens than a stop token. They can remove, they can edit, but their bias is to add. My suspicion is that training them when to stop when it is best to stop is harder than training them to make a plausible sounding story.
And they always ask right when logging in which is the absolute worst time to ask anything.
If I'm logging in to your app or service it's because I want to do something. Throwing up a "hey would you like to setup this complicated auth thing before you're able to do anything else?" Is annoying at best.
Then they normally follow it up with a tutorial that blocks the part of the app you need, and a full screen modal to subscribe to their newsletter, and a cookie dialog asking to let you track them, and a popup asking you to rate them on the app store, and...
Only once I've beaten away all the interruptions am I finally able to use the damn app.
I finally connected my home assistant server up to Codex the other week, and it's been pretty incredible. I can just send a message to codex and in a few minutes my dashboard is updated, an integration added, an automation setup, and sometimes all of them together at once.
And I don't need to build or debug complex automations any more! I can just tell some AI to make it so it auto-locks the house door when my phone isn't tracked at home, but also to check the wifi and if there are people using the guest wifi then to instead send me a notification asking if I want to lock the house because guests might be there.
I really do think we are headed toward a world where stuff is hyper customized like that.
As a developer, it already feels like this with internal company tooling. Anything I have the source code to and a build pipeline setup for, I can just pop open a new tab and tell it what I want changed, and it just gets done for me.
Even my home assistant setup at home now, i hooked up codex to it via an MCP, and when we put out the blow up haloween lawn ornaments I was able to just pop open codex on my phone and tell it to throw together an automation to run them for me, and 5 minutes later it was done, with an override button on my dashboard. It's a shockingly nice workflow!
Wouldn't it be nice if you could just tell your app to reconfigure/rewrite itself to remove those "what the app will think I need at particular moment" features that you dislike? Maybe have it remove a bunch of the whitespace, getting rid of the lazy loading infinite scroll, whatever you want. It's the GPL dream, except you don't need any coding ability, just a subscription to a megacorp.
I do the same with Home Assistant and my many EspHome devices. HA works well, and it has a lot of nice features and extensive community-built integrations, but configuring and laying out the UI is a disaster. You can choose between WYSIWYG UI tools that are limited and cumbersome, or you can deal with raw YAML that stretches far beyond what YAML should be used for with deep nesting, and it's poorly documented to boot. It feels like a proprietary workflow engine, where you'd rather just write it in a real programming language.
Agents cut through all that crap and allow me to make changes without learning a new overwrought configuration language that thrashes syntax every few months. The fact that it is open and fully modifiable redeems it, because I can ignore all the annoying parts while achieving what all that was envisioned to allow.
As the saying goes, this is what radicalized me. If any one of us did anything close to this we would be treated like Aaron Swartz and given a 35+ year prison sentence.
But in the Sony case the DOJ didn't even threaten criminal charges.
I've been having a fantastic time telling it to use ASD-STE100 Simplified Technical English (or use a skill for it, I've been playing with [1])
It's a very clear and understandable way of writing that puts priority on clarity.
It gets rid of the flowery language, the dense jaron, and the weird corporate marketing speak they tend to do. It is a bit repetitive, and it sometimes doesn't always wfit well in every situation, but for technical writing or explanations it's been such an incredible breath of fresh air!
This just might save me. Claude has been driving me nuts with incomprehensible summaries after a long task, where it's actually really important to understand what was done (and what wasn't).
But I'd like that skill to only be used at the final step, when it finishes something.
agreed with "the final step". I worry adding commands like these might affect quality of responses at each step, which then stack up to result in an overall worse outcome.
