Raine Virta

@kdy1dev Depends on the project, but you might be able to use a cheap enough model that makes the costs negligible. For example, Gemini 2/3 Flash models are really cost-efficient. Of course there's always a chance of abuse but rate-limiting helps a bit.

How do you typically distribute simple utility apps that run on AI? The AI costs are quite high to ignore. It seems too simple to justify a paid subscription plan, and I’m not sure if ads would be enough to cover the costs.

If you have trouble with scrolling history in Claude Code in tmux, try with env CLAUDE_CODE_NO_FLICKER=1. The variable is a bit of a misnomer. It changes the whole scrolling implementation to work much better inside tmux.

Use Claude Code with OpenAI models and ChatGPT subscription: github.com/raine/claude-c…

Would also argue scavs are much weaker compared to free kits in Arc Raiders. You don't go scav to PvP, you do it to loot, and in Arc Raiders looting with free kit makes no sense because of the limited space compared to the loot augment. So I think free kit is in a weird spot because it incentivizes PvP.

@Jay__Carra @JKuccii Kind of, at least the scav system in Tarkov has a timegate and you can't quest with it, so I think it balances out a little bit, but Arc Raiders free kit system is extremely spammable and it's still your main character

Aside from them not dropping any content worth anything for months, i hopped on last night for the first time in 2.5 months and pvp’d for about 2 hours. Last raid of the night i brought an anvil bobcat in, killed about 12 people and every one of them had free kits. Do you know how fast that made me get off and not wanna play for another few months? Why even bring a kit? The fact it’s even possible for me to risk that loadout and I’m being put in the same game with a bunch of people who have nothing to lose, just for me to possibly die by arc or some stupid shit?? Just such a stupid system lmao

@shuntaka_jp うん、すごく役に立つね github.com/raine/tmux-fil…

これtmuxのpopupか。ショートカットでtmux popupからfzf発火させてマルチセレクトでファイルパス挿入してそう。やってみよう... workmux.raine.dev

@jonallie I thought this was common sense

Personal rule of thumb: don't use an LLM for something that a deterministic program can do. I get it, LLMs are exciting, but they don't mean that software ceases to exist. They are fantastic at dealing with human language and ambiguity, but are terrible (by design and for good reason) at repeatability. To borrow terminology from the book Thinking Fast and Slow, LLMs are "system 2"...slower, more "expensive" (for LLMs, both in time and dollars), but flexible and creative. Traditional programs are "system 1" ..fast and cheap, but inflexible and dumb. Instead of trying to put an LLM in the "hot loop" of your program, it's usually worth asking an agent to write a deterministic program to do the thing you need done. Since code is "cheap", this deterministic tool can do exactly what you want it to, and doesn't consume tokens on every execution. (This applies to agents too..I find myself regularly yelling at Claude to stop repeatedly generating the same 30 lines of python to inspect a file, and instead telling it to generate a 3-line shell script wrapper around jq that it can check in and call repeatedly)

Ultra compact agent usage limit monitor for tmux status bar

@NickADobos Gemini CLI is already rate-limiting programmatic use cases, so it's not outside the realm of possibility that Claude does eventually something similar. I have no idea how Gemini does the detection but it's impairing my use of github.com/raine/consult-…

Isn’t this impossible to enforce unless they remove a significant portion of Claude code? claude -p <prompt>

@13hcoks Cool. It's first I hear of anyone using the Kitty integration!

Workmux is a super cool project with @rane being very responsive. I'm using it with Kitty as the mux backend🐱 Keep up the good work!

@ashar_builds @Michal_J_ @housecor This is not an issue in practice. Agent can understand both sides and resolve appropriately. See for example github.com/raine/workmux/…

@Michal_J_ @housecor Right. But at some point you have to merge them to main branch and can end with plethora of conflicts and endless review cycles.

I see many people running multiple agents simultaneously. I avoid it. Instead, here’s what I typically do while my *one* agent is running: - Review the code it generates in real time - Watch its terminal output and course correct - Do code reviews for teammates - Reply to email / Slack / Teams - Plan my next steps - Pair with a dev on a different task - Pee So, for me, running a second parallel agent is a last resort.

@housecor @ashar_builds No you don't. If you are still resolving conflicts manually, you are missing out hard. #rebase" target="_blank" rel="nofollow noopener">workmux.raine.dev/guide/skills#r…

@ashar_builds Yep that’s another reason I avoid it. Have to find parallel tasks that won’t conflict

workmux now has a sidebar for an at-a-glance view of all your agents

@PaulRBerg Press Ctrl-G

This is the most annoying thing in Claude Code. Hiding raw text when you paste more than 4 lines. Terrible UX decision.

@rohanpaul_ai Why was it deleted?

Andrej Karpathy just put out this tool that looks at AI's impact on job. He also deleted the original Github repo very quickly. Basically, he pulled 342 job types from the Bureau of Labor Statistics and had an LLM score each one from 0 to 10 based on AI exposure. The average exposure score is 5.3. Move the score, move the probability it will get wiped out by AI. - Software developers 9/10, - medical transcriptionists are a 10/10. - Lawyers 8/10 - General Office clerks 9/10 Basically any screen-based jobs are in trouble. $3.7T annual wages in high-exposure jobs (7+) pre-computed as ∑(BLS employment count × BLS median annual wage) over exactly those occupations whose Gemini Flash score is ≥7.

@joodalooped Make a project on GitHub that people start contributing to, you will notice it's cheap indeed. People will send half-working PRs with less trouble than it would take them to write a coherent issue of the thing they are solving.

idk man, i don’t think code is as cheap as everyone is making it out to be

"it's also very messy (unnecessary utils, duplicated code, random `as` everywhere)" This is a workflow issue. Code quality is a 100% solved problem. Review your code with other agents (see e.g. consult-llm-mcp) and set up hooks to prevent tractable errors like those `as` assertions.

the bottleneck for coding agents is now testing / code quality agents are OK at writing code in the happy path, but don't consider edge cases on harder tasks it's also very messy (unnecessary utils, duplicated code, random `as` everywhere)

"The entire argument for zmx instead of something like tmux that has windows, panes, splits, etc. is that job should be handled by your os window manager." There's never going to be OS-level window manager for Mac that would allow switching between projects with same fluidity as tmux does allow me to switch between sessions.

@dmwlff github.com/neurosnap/zmx

I used to be a kitty stan who looked down my nose at tmux users, but I'm back to using it all the time. I get that it kind of sucks, but it's sooo convenient and powerful. I would love it if Ghostty added scriptability and persistence. I'd drop tmux in a heartbeat.

So what's the best way currently to have an agent interact with browser? There's so many options lately, playwright-cli, agent-browser etc. A potential benefit with CDP at least I see is that you can reuse the existing browser session and don't have to always open an adhoc Chrome session for the agent.

It took another two months but Chrome 146 is out since yesterday! And *that* means: with a single toggle, you can expose your current live browsing session via MCP and have your CLI agent do things in it. Aaand I have been waiting to deal with my LI connects until this moment.

@TheReeveOliver @SearchForRyan Anthropic has two competing interests here. They want Claude Code to be powerful, but at the same time they want you to burn tokens to compel user to upgrade. Anyone who has paid attention has noticed the trend that you're getting less mileage out of the plans. n

@SearchForRyan My question is if all of these things are needed for claude code to function well, why are the not part of the standard setup. Why do I keep discovering hacks on X instead of this shit already being setup?

okay why did nobody tell me about state.md for claude code? i've been stuck wondering why a project i build on daily was taking 8-10 mins to make changes turns out claude was reading EVERYTHING (all my code) before it made a change. i added state.md, architecture.md (alongside my claude.md) and bam, 8,000 tokens to ~1,000 tokens and from 8 mins to ~ 60 seconds. claude.md wasn't enough in this instance annnnd i'm so happy lol