radio879

You know what I found this past year was that I could NOT find any way, to turn off anti-aliasing, for text inside a webview. I made a whole entire custom terminal app just for myself in Rust, Tauri, xterm.js and spent a ton of time trying to un-blur the text but failed. I redid the entire thing (well, Codex/Claude mostly) using a rust graphics library (egui) and now the text is finally sharp! and its fast. I am growing more and more anti webview with these AI coding tools.. they can almost one-shot convert a slow webview app into something that uses 1/10th the ram and 10x as fast. The text looks soooo much better, all fonts look better. In xterm.js, text looks super fat all the time (to me).

There are companies that sell people's home ip address as a VPN/Proxy for anyone who wants to use it for anything. They call it "residential ip's". People use them for web scraping, but probably tons of illegal stuff too. AI companies use them to not get blocked.

I've heard that they put it in IoT devices, free Android apps that people use on their TVs, free phone apps, games, prob lots more.. The companies advertise it like its super safe only legit normal people borrow the internet from these people but then in fine print it'll say its not our responsibility etc.

What I have been wondering is - since they don't seem to care or check what people are using the "residential ip's" for, what happens when someone does a bunch of illegal stuff on some random person's home IP and ends up raided by cops?

I feel like the world is going in these directions.. the excuse is always "well, they clicked Yes on the Terms of Service! They agreed to it!"

I notice... the newer models, they seem like they want to just "give up" much faster, and you have to put a bunch of extra programming around it (harness, for loops and if then's etc to force it to keep trying)

i am on just the $20 plan and I am using it literally almost all day, 2-3 different projects at the same time, and I am failing to run out! I am naturally always trying to be efficient, its a weird personality trait I have, where I don't try to but I willingly choose to use GPT-6-Luna most of the time now (well 5.6 before that) More Sol lately and for most tasks.. they seem to have the same output, its only super hard things where I kick it up to Astra.

I am so used to doing planning with the best models and switching to Luna, Deepseek 4.1 Flash (really, the cheapest model, and often much better results for lots of things) really people are limiting themselves when they only use one company's models. You really gain a TON by treating each one more like different people with diverse range of personalities, passions, skills, and knowledge.

Today, ChatGPT desktop app was tasked with making 7 variations of new versions of some existing websites of mine - and they all kinda looked the same. I did get lazy with it though.... I can solve that probably, with skills/changing the default frontend skills but also just sending the same task to Reasonix Code w/ deepseek, and some other models, gets some good wide range of outputs.

I was wondering if I should try to create my own pseudo filesystem with FUSE for easy copy-on-write/snapshots, a native feel, and automated secrets filtering/swapping. I might as well combine that with good/easy isolation.

The whole “what sandbox/VM/microVM/thing is best?” question has been bugging me a lot lately, and I no longer trust any of these AI companies to keep data safe.

I’ve been testing a bunch of sandbox-related projects. Sometimes I just use a full Fedora Workstation VM inside Windows 11 with a shared folder, copy a project into it, and run long agent tasks there. It’s not ideal, but it is pretty safe. Sometimes I run agents in different WSL2 distros and test different things inside those.

I did like gVisor from Google — it’s not quite a microVM, but it’s not really just a normal container either. It wasn't easy to figure out how to get it working tho. Lima Machines worked well too, and I don’t remember it being annoying. SmolVM... ugh. There are two projects with exactly the same name, and it got confusing enough that I gave up. One of them did work when I tried it, though.

The confusing part is that there are now hundreds of sandbox projects, and they all solve slightly different pieces of the problem. Some have filesystem isolation, some have networking controls, some handle credentials better, etc. Nono, for example, has a nice secrets filtering/swapping idea where real credentials can be replaced with dummy values, but there have also been GitHub reports about isolation gaps — data being accessible when it isn’t supposed to be. I’m trying to figure out which projects are worth using, which are worth skipping entirely, and which might just have useful pieces of code or ideas to borrow.

I’ve got GPT-5.6 in one window doing a fairly ridiculous analysis of the different approaches and the likely long-term reliability/adoption risk of each repo. Separately, I have a WSL2 distro running Reasonix with DeepSeek doing its own analysis so I can compare conclusions.

What I eventually want is a desktop GUI over whatever combination of sandbox technologies turns out to be reliable. Ideally I could just type:

“Spin up 5 sandboxes for project X. Put Claude Code in one, Reasonix in #2, Codex in #3…”

or:

“Create 3 sandboxes, put whatever coding agents in 1, 2, and 3, and then have each one run twice.”

If it’s AI-powered, it could automatically name folders and copy results back somewhere like `folderName_3a`, or use Git branches/worktrees if desired. I don’t always want to use Git.

Every sandbox CLI has its own syntax, code quality, reliability, ease/pain of getting it working, configuration format, mount rules, networking options, etc., and I don’t particularly enjoy memorizing another pile of commands just to isolate an agent.

I’ve tried quite a few of them. A lot of them are still rough enough that I hit errors quickly and move on. Some seem much more mature — Lima is one I like conceptually, although native Windows support would be nice but I guess not a huge deal.

Credentials are something I never cared much about (API keys and stuff like that) but now.... I'm more worried. I really don’t want to deal with any problems from that. Or something installing something that grabs SSH keys, browser passwords (FYI.. Z Code asks you "do you wanna import all the logins from chrome?) browser sessions, cloud credentials, or my whole home directory. That concern isn’t limited to Chinese software either. I don’t automatically trust US AI companies just because they’re US companies. Zuck, Elon...zero trust in those two.

So I’m increasingly thinking the “right” answer might not be one sandbox project at all. It may be a GUI/orchestration layer that combines more than one backend and more than one type of sandbox. There could be common default presets and combinations of Git worktrees plus containers and/or VMs. I also feel safer that Docker/Podman on Windows generally runs inside WSL2, because it’s basically containers inside a VM.

The goal would be strong isolation underneath — maybe even combining two or more layers so one failure doesn’t expose everything — plus explicit project-folder mounts with read-only or read/write options, rollback/snapshots, network controls, secrets substitution, disposable environments, and an easy way to fan the same task out to multiple agents/models.

I also like the idea of having an AI model in front of the whole thing, with the ability to save whatever setup it creates as a preset so the AI part can be skipped next time. And I want it to support not only parallel agents using different models, but also loops where the exact same agent setup runs several times.

I'm glad i'm not the only one that noticed w/opencode.. I tried it a few times, every single time... it immediately went bad, didn't work, can't do anything simple like simple file edits.. yet somehow, there are thousands on the internet ready to tell me how great it is! Opencode looks good in the terminal but that's really the only good thing about it.

There are people who do not have any words in their heads at all when they think, and there doesn't seem to be any reason to disbelieve them. It may have been proven or at least observed in fMRI. Some people think in visuals.

I think some of this was discovered somewhat recently

This is not new, but what is new is GPT 5.6, Terra and Luna, are the models right below Sol, are now included in the free daily tokens thing they do. Terra is better than GPT 5.5. I've been using it in Codex.

I have a couple things that run daily, experiments where it grabs stuff and updates a site in a loop. You can do a lot of free stuff with 2.5 million tokens... and its not going to be low quality. So I just wanted to share this in case people didn't know about some free stuff. (okay its not "free" when you have to agree to share the in/out for training.. so just don't send them anything you don't want out in the world i guess)

I don't remember where I read it, pretty sure it was in a book - my dad taught me science stuff starting young (like late 80s, early 90s) , I remember it and somehow I got really into altered states, psychedelics, etc so that really just stuck in my mind somehow (even though I think I read about that, before ever trying any psychedelics)

I have a very vivid dream life myself, and I have had 'out of body' experiences starting at age 6, so maybe I read it sometime after having some of those weird experiences and that's possibly why I remember reading it.

Right now I think GPT 5.4 beats Opus 4.6 and everything else. I get a lot from just the $10 Github Copilot, somehow it hasn't run out yet and i've been going at it insane everyday

Also, we can do thought experiments, simulations in our heads, that often are as good as doing them for real - it has limitations and isn't perfect though. But it does work often. Einstein used to purposely dose off in a weird position so that something hit his leg or something like that to slightly nudge him half awake so he could remember his half-dreaming state - which is where he discovered some things