Activity
- Added Works Offline as a feature to Wando Studio
Reviewed Wando Studio★★★★★I really like Wando Pro it's a hard to find combination of features. You don't have the raw painting power of Krtia like you do in Krita AI Diffusion, but I get much easier access to cloud generation and all the basic tools I need. I also love the fact it's a real program and not yet another electron app or local hosted web stack. Needs more help information, took some trial and error to learn, but worth it. It's still a really new program though and the dev says better help documentation is...
- Liked Wando Studio
Replied to a comment / review on bibisco
Reviewed Mountain Duck★★macOS 15/26 massive ram leaks and slow performance. Transferring 1GB of files over SMB used 9GB of ram and kept that ram used until Mountain Duck was restarted. It was also 1/10th the speed of native SMB. Trying to use it to sync backups to Backblaze was worse. Sync 5GB of data used 49GB of ram. This is a known issue from 2022 that is still unfixed in 2026. [https://github.com/iterate-ch/cyberduck/discussions/16431](https://github.com/iterate-ch/cyberduck/discussions/16431) When you contact...
You know, one of the best things and only reasons to actually have a Google AI subscription was because you got different pools of usage for the CLI and antigravity. I'm guessing one of the biggest reasons for this change is not because it's actually better, but because they wanted a good excuse for merging your pools.
The funny thing is, I was actually looking forward to seeing what new models Google released. Then whenever they started merging your quota pools and Removing your ability to...
Wow, now if only XYplorer would move on over that would be the last thing I miss on macOS vs windows. Though Bloom is making headway. No where close to XY but a vast improvement over finder.
It was a nice run while it lasted, but one of the key things will be how they start charging for usage after they switch over, because their models are still gimped compared to the official ones. So, if they go charging full official rates for them, there'll be absolutely no reason to use them, because the key reason to use Copilot was because you could get the thinking capacity of Frontier models for better prices, because Microsoft was tuning them down to be cheaper to run. Because You...
- Replied to a comment / review on Google launches Gemini 3.1 Flash Live with its most human-like sounding AI voice model yet
Trying to integrate it into a writing review app turned out to be a miserable failure. Its ability to understand fantasy words are virtually non-existent. Which is a similar problem ran into with a lot of dictation programs as well. If you can't train words into them, they're about useless, whenever it comes to creative writing.
🎉 Critical website for finding great alternatives. AIs still can't suggest even 1/10th as good of alternatives to most apps. Every time I try to get an AI to suggest an alternative to a program I roll my eyes wonder why I tried asking and come here for real results.
My overall experience with it has been fairly good. It's been a solid upgrade over 5.2 codex. It tends to write code faster and more compactly with fewer tokens, handles large refactors well, and is better at spotting potential issues. Overall, I've been comparing it to Opus 4.6 lately and 5.3-codex is pretty much solidly beating it in everything that I throw at the two. Opus 4.6 Can get a little more creative with solving a problem, which makes it better for intense troubleshooting, but thus...
A comment was removed from RightNote- A comment was removed from RightNote
Even as someone who uses quite a lot of AI tools on a daily basis (including 3 that I made myself) I still haven't figure out what all the rave/excitement about Clawbot/Openclaw is... Anything useful it says it does can be done better with specialized tools. Thus far after reading about it and watching a couple youtube videos on why it's awesome the only thing I got is that a lot of people only what to use AI if they can talk to it in their favorite IM/Chat system and like the idea of an...
- Replied to a comment / review on OpenAI launches new GPT Image 1.5 model with faster editing and Apple Music integration
That didn't last long already #2 under Gemini 3 less than 48 hrs later...
- Replied to a comment / review on Anthropic launches Claude Haiku 4.5: faster, safer, low-cost AI for all users
if the price is actually $550-650 then maybe there's a chance, but given the specs vs current Mini PC hardware I'd expect it to be $1,000+ which won't compete. Though mayve the new steam controller will be what really sales it? If they bundle the controllers with it and they get super hype and getting the console is the only way to get them for a long time. it's not impossible for it to succeed, just unlikely. Especially with just lightly custom stuff unless they either have some major magic...
- Replied to a comment / review on Anthropic launches Claude Haiku 4.5: faster, safer, low-cost AI for all users
My first experience with Hiku 4.5: Sonnet 4.5 has failed to fix this 5x... this is getting expensive. May as well switch to Hiku... Hey it fixed it on it's first try! Cool. /usage ... Still seems to have used the same amount of my weekly usage as sonnet 4.5 though...
They already have my ID, CC numbers and face scan because I used advanced API features and of course have a subscription, if they make me do some silly age verified thing in December I'm going to roll my eyes so hard.
Reviewed Devin Desktop★★[Highly time period relevant review e.g. Take with huge grain of salt x months from the review.]
I don't understand how they make it so bad... GPT-CODEX in the Codex CLI is amazing! Supernova on Kilo Code works pretty good then I use them in Windsurf and with the same prompts that work great in other places I get subpar results and it chugs along like an exhausted snail. Sonnet 4.5 in Claude-Code CLI is another one that is just... wow I blow through my 5hr usage limit on the CLI fast and...
Liked SwarmUI- Added SwarmUI
