AIs that I find useful are still just LLMs and LLMs power comes from having a massive amount of text to work with to string together word math and come up with something ok. That's a lot of data that comes together to get things ... kinda right... sometimes.
I don't think there's that data set for "use an app" yet.
We've seen from "AI plays games" efforts that there have been some pretty spectacular failures. It seems like "use app" is a different problem.
Yes and no, I'd say. On one hand, apps tend to be used by even the most dumb person (they are "users" after all ;) ) and I'm sure there are more people out there who can use most apps enough than people who can beat Pokemon, even if one might generally be easier than the other.
It's kind of hard to judge though I guess, I played Pokemon (Red) last time when it launched in my country and I was like 8 or something, maybe I underestimate the average person but I feel like I overestimate people generally.
I think it depends on the situation.
Unit test can be done by Claude code. I use it everyday.
For E2E testing, browser-based tools are already pretty convenient. AI could definitely help by suggesting UX improvements, but setting up a smooth workflow is still tricky. You’d need to figure out things like where to put the AI’s feedback, when it should kick off testing, and who’s going to sort through all the suggestions it generates.
But technically it can be useful and quality is good enough.
I’m still torn on this. On one hand, memory could make ChatGPT more useful, especially for people using it regularly for work or coding. But on the other hand, the idea that it “remembers” me just feels a little uncomfortable.
I’d want more control over what’s remembered and when. Curious if anyone here has used this yet — is it actually helpful in practice?
> I’d want more control over what’s remembered and when. Curious if anyone here has used this yet
I use the "memory" feature of ChatGPT, and taking a look right now, it seems to have about ~30 items saved from me, some of them are like "Is using egui for a UI task, particularly related to configuring smooth automatic scrolling in a scrollarea." which is useful for maybe the ~3 chats I had about it, and also other things like "Prefers more accuracy in terminology and is looking to represent LLMs in a detailed and structured way." that are more broadly applicable.
Then you can obviously remove any of them, and also manually add by telling it explicitly you want something added.
I'm not sure of its usefulness, I guess it's nice that it correctly "knows" I'm mostly on Arch Linux most of the time but have my servers with NixOS, so if I ask it to create new unix commands I usually get something that works on both, or two versions. But sometimes it also incorrectly infers something because I didn't specify otherwise in the prompt and didn't think of it, but it could see something from the memories.
I’ve been trying it out recently, mostly for writing and summarizing research. The memory feels subtle so far — it doesn’t jump in unless you really build on past prompts.
That said, I totally agree about control. I wish there was a more obvious way to “pause” or “reset” memory mid-session instead of diving into settings. It’s useful, but still a little opaque.
They should totally be able to. If there's "vibe coding" there should be "vibe testing." We're working on just such a product (https://actory.ai); right now it only does websites but just imagine when we turn it on mobile/apps, etc. How cool would that be?
Thousands of users. 40+ GitHub stars. Original draft took 30 minutes. Added numerous feature requests and each took like 5 minutes a pop.
I never wrote a single line of that code.
Furthermore, my startup, https://gametorch.app/ has 110 sign ups, paying users, millions of impressions. Never wrote any of that code either. Typing it out at ~100 wpm is far too slow.
I generated tons of valuable code with a bunch of GitHub stars, paying users, hundreds of signups, millions of impressions. Just chipping in my anecdote.
https://engineering.fb.com/2018/05/02/developer-tools/sapien...
AIs that I find useful are still just LLMs and LLMs power comes from having a massive amount of text to work with to string together word math and come up with something ok. That's a lot of data that comes together to get things ... kinda right... sometimes.
I don't think there's that data set for "use an app" yet.
We've seen from "AI plays games" efforts that there have been some pretty spectacular failures. It seems like "use app" is a different problem.
Yes and no, I'd say. On one hand, apps tend to be used by even the most dumb person (they are "users" after all ;) ) and I'm sure there are more people out there who can use most apps enough than people who can beat Pokemon, even if one might generally be easier than the other.
It's kind of hard to judge though I guess, I played Pokemon (Red) last time when it launched in my country and I was like 8 or something, maybe I underestimate the average person but I feel like I overestimate people generally.
I’d want more control over what’s remembered and when. Curious if anyone here has used this yet — is it actually helpful in practice?
I use the "memory" feature of ChatGPT, and taking a look right now, it seems to have about ~30 items saved from me, some of them are like "Is using egui for a UI task, particularly related to configuring smooth automatic scrolling in a scrollarea." which is useful for maybe the ~3 chats I had about it, and also other things like "Prefers more accuracy in terminology and is looking to represent LLMs in a detailed and structured way." that are more broadly applicable.
Then you can obviously remove any of them, and also manually add by telling it explicitly you want something added.
I'm not sure of its usefulness, I guess it's nice that it correctly "knows" I'm mostly on Arch Linux most of the time but have my servers with NixOS, so if I ask it to create new unix commands I usually get something that works on both, or two versions. But sometimes it also incorrectly infers something because I didn't specify otherwise in the prompt and didn't think of it, but it could see something from the memories.
That said, I totally agree about control. I wish there was a more obvious way to “pause” or “reset” memory mid-session instead of diving into settings. It’s useful, but still a little opaque.
It works without AI, but there's a MCP and stuff, so you should be able to connect Claude etc with your emulator/device now.
Current AI is not even designed to do that. It is just a very sophisticated auto-complete.
It is sophisticated enough to fool some VCs that you can chop your round peg into square hole. But there is no ground to expect a scalable solution.
Thousands of users. 40+ GitHub stars. Original draft took 30 minutes. Added numerous feature requests and each took like 5 minutes a pop.
I never wrote a single line of that code.
Furthermore, my startup, https://gametorch.app/ has 110 sign ups, paying users, millions of impressions. Never wrote any of that code either. Typing it out at ~100 wpm is far too slow.