It's the first thing I tried, because Nano Banana 2 deteriorates the output with each turn, becoming unusable with just a few edits.
ChatGPT Images 2.0 made it unusable at the first turn. At least in the ChatGPT app editing a reference image absolutely destroyed the image quality. It perfectly extracted an illustration from the background, but in the process basically turned it from a crisp digital illustration into a blurry, low quality mess.
> Best forget about using Claude Opus models in Copilot.
I noticed this morning that Opus isn't even one of the models in the `/model` command in Copilot. Highest I can get (on the paid, but least expensive) tier is Sonnet 4.6. I'm pretty sure Opus was allowed recently, but not now.
I can’t say I’ve used it extensively enough to draw a conclusion, but it did seem similar to GPT 5.4 in Codex.
When I threw it at a difficult issue in an iOS app, it like GPT came up with wrongly guessed explanations. It only found the issue after I had it instrument the app and add extensive logs. Usually GPT 5.4 is the same.
Only that with GPT 5.4 it’s at least included in my subscription, while sending 3-4 messages to Opus 4.7 for this blew through my $20 plan limits and consumed $10 of extra usage on top. At that point I can’t help but bring up how much more expensive it is.
> Only that with GPT 5.4 it’s at least included in my subscription, while sending 3-4 messages to Opus 4.7 for this blew through my $20 plan limits and consumed $10 of extra usage on top. At that point I can’t help but bring up how much more expensive it is.
Rest assured OpenAI won’t want to leave that kind of money on the table…
I don’t know about rate limits, but I’ve been running into timeouts with Sonnet 4.6 after they don’t complete within 4-5 mins.
I have not encountered the same issues when using Claude Code.
Perhaps Copilot is on some sort of second rate priority.
Of course it’s the only thing available in our Enterprise, making us second class users.
Using the Copilot Business Plan we get the same rate limits as the student tier, making it infeasible to use Opus. Meanwhile management talks about their big plans for AI.
I know limits have been nerfed, but c'mon it's $20. The fact that you were able to implement two smallish features in an iOS app in 15 minutes seems like incredible value.
At $20/month your daily cost is $0.67 cents a day. Are you really complaining that you were able to get it to implement two small features in your app for 67 cents?
That last sentence didn't make sense so I'm not sure what your point is. But I'll run with the analogy.
You got into a taxi and they were charging you horse carriage prices initially. They're still not charging you for a full taxi ride but people are complaining because their (mistaken) assumption was that taxis can be provided as cheaply as horse carriages.
People are angry because their expectations were not managed properly which I understand.
But many of us realized that $20 or even $200 was far too low for such advanced capabilities and are not that surprised that all of the companies are raising prices and decreasing usage limits.
OpenAI is not far behind, they're simply taking their time because they're okay with burning through capital more quickly than Anthropic is, and because OpenAI's clearly stated ambition is to win market share, not to be a responsibly, sustainably run company.
Shortly after I ran out of credits in 15 min, they tweeted that they increased usage limits to compensate for the higher token usage, so perhaps it is not as bad now.
Codex, this afternoon, I was able to use for like two hours on the $20 plan. Maybe limits will be tighter in the future. But with new data centers, new GPU generations, and research advances it might rather get cheaper.
Anyway, as you said, this is all pretty cheap. I'll go with the $100 Codex plan, since I now figured out how to nicely work on multiple changes in parallel via the Codex app with worktrees. I imagine the same is possible in Claude Code.
It seems to me a bit naive to think OpenAI would not increase prices/decrease usage limits at some point. $20 might cover a very small fraction of the actual cost that is incurred over a month of sustained usage.
While that might be the case for now, as the offender would need access to a PC with a NVIDIA GPU, that will not hold for long.
Once you can run decent image generation models on your phone, what shall we do? Prohibit apps that allow you to run custom models? Add a mandatory safety check?
It seems like a pointless exercise to me - better punish the actual crime rather than try to regulate the tech.
Prohibiting apps from shipping with models that can nudify people seems reasonable. Custom models that can do it will be banned from search results and major sites. Just like child porn, they'll exist online but be quite difficult to find.
There is significant societal value in preventing crimes rather than just punishing them.
The prevention here would require to take down existing models that are already widely distributed and mostly used lawfully.
And even if you outlawed the distribution of uncensored models, we face the next question when you can do the fine tuning directly on the phone and someone makes an accessible app.
Do we then prohibit apps that allow you to fine-tune a model, do we mandate safety scans of the images in the dataset?
Not many existing models will do it or do it well.
> when you can do the fine tuning directly on the phone
Well you'd need millions of on/off nude samples to start with, so I don't think that's likely. And that's assuming we get a billionfold increase in mobile CPU performance or a billionfold decrease in fine tuning compute requirements.
You're reaching for things that, if they happen, are a decade or more out. It's ok to solve today's problems today. Perfect is the enemy of good.
LoRA training for recent Flux 2 Klein or Z Image Turbo models can be done on a consumer GPU in a few hours, often using datasets with fewer than a hundred images.
How much quality that gets you I don't know - perhaps the versions people publish are trained with larger datasets.
I know that one popular anime finetune of SDXL cost $180k in compute on 8xH100 for two months.
I guarantee that it won't improve significantly even after several major releases.
Resolve is designed to be controlled with their "panels", which have lots of dials and knobs to turn.
The software only interface is clunky at best, and they steadfastly refuse to fix basic usability issues lest that undermine the justification for buying their hardware.
For example, cropping and rotating media in Lightroom is a totally different experience compared to Resolve (photo or video, they're both bad!).
Lightroom lets you fine-adjust sliders by pressing shift so that instead of rotating an image by HUGE AMOUNTS BACK AND FORTH you can easily remove a 0.4% tilt without having to type in the numbers into an "angle" text input box like a savage.
Lightroom's crop and rotate controls do a "constrained crop" by default so that you don't get black wedges in the corners of the image. When the background is already mostly (but not perfectly) black, this can be infuriating to fix in Resolve by alternatively rotating, cropping (numerically!), rotating, cropping etc...
While I'm complaining about Resolve issues, it gets the color temperature scale wrong, as per this video, to the point where I find it nearly unusable: https://www.youtube.com/watch?v=WADuXiMZxq4
My 'For you' feed is almost exclusively Photography, science and tech news.
I believe it strongly depends on what you interact with.
At some point I also had a lot of US news in my feed, but once I stopped opening those posts and instead used the 'Not interested in this post' button or muted the author, they disappeared.
Probably following other accounts or liking photography posts also helped.
They're not on my For You feed, but anytime I watch a video on Twitter and it automatically jumps to a next video, it's always something that would never be on my feed. These days, it's usually bodycam footage from the United States (which I don't live in).
Meh, this borders on victim blaming. You can't deny they've done something to turn it the last few years. And there is no one of my interest left to follow, they've all jumped ship. I checked the "following" tab now, and there is nothing of interest there, they've all left.
Honestly, I have tried to really cut down on my usage of 3rd-party dependencies when possible. In a way, it's kind of freeing. Whatever I still need, I write myself. If I cannot write it, then I try to find something FOSS. If I find nothing, then I consider purchasing something.
For example, I am rolling my own window manager (that needs some much needed TLC). I ditched Alfred for Spotlight. Though Alfred is better, I will survive just fine. And the list goes on.
I am not trying to take a dig at the OP. I am sure he or she put effort into this application. But I am genuinely curious -- does anybody actually need this software? Cmd+Tab, a decent window manager, and Spotlight would solve the same problems for free.
I fresh install to give myself a different perspective when I feel like I have too many 3rd party solutions to problems that no longer exist. Spotlight is better and I only casually use my macbook nowadays, so I don't need the power of Alfred. I don't need dock extensions because Stage Manager is mediocre but works well enough for the browser, chat / music apps, and whatever document I'm working with at the time.
ChatGPT Images 2.0 made it unusable at the first turn. At least in the ChatGPT app editing a reference image absolutely destroyed the image quality. It perfectly extracted an illustration from the background, but in the process basically turned it from a crisp digital illustration into a blurry, low quality mess.