@Emma_nuel_david full-screen TUI plus multi-provider is a solid step. one thing worth adding early: a per-provider fallback, so if a model errors or rate-limits mid-session the chat continues on another. how are you storing conversation state when you switch models?
5/ Build in public: every video on this account is made with code (Remotion + an AI voice, no camera).
Next on our bench: HyperFrames by HeyGen. Plain HTML in, deterministic MP4 out, Apache 2.0, with skills for Claude Code, Codex, Cursor and Gemini CLI. If it beats our pipeline, you'll see it here first.
Follow @Shallow_Vibes for one useful AI coding update a day.
@LexnLin almost 10B tokens in a day is a lot. how much of that is cached reads versus fresh output? cached input is billed far cheaper, so I'm curious how the split looks on your heavy days.
@jdn1el@joshuagunnn a fan site for an OSS project nobody had given a home yet is a nice way to do it. what did you design first, the hero explaining the 450 tokens vs 100k+ grep gap, or the install snippet?
Want Claude Code's auto mode to actually understand your setup? There's a command for that now.
/auto-mode-setup (Claude Code 2.1.304) is a guided setup: it reads your project and your recent sessions and teaches auto mode about your environment.
How to use it:
• Update Claude Code
• Open your project and run /auto-mode-setup
• Go through the setup, then let auto mode work
Also new in that release: on Pro and Max, Claude Code warns you when resuming an old, inactive chat would use a noticeable share of your 5-hour limit. Resume anyway, or start fresh and let Claude look up the old conversation when you mention it.
30-second walkthrough below.
@LexnLin for overnight runs, are you using bypass mode in a sandbox or container, or straight on your machine? curious where you draw the line, since an allowlist of specific commands is the middle ground.
@jdn1el drawing it live in a canvas from vector shapes at a stepped 24 fps is a neat call, it keeps the manga feel and stays light. do you drive the stepping from one shared clock for all panels, or does each suit run its own timer?
@e1genqq remotion is the sleeper in that list. every frame is a pure function of useCurrentFrame, so the agent can debug timing from code alone. all my videos are built this way, and extrapolateRight: clamp removes most overshoot glitches
@itsfazley 770k tokens for zero assets is a flex. did the agent keep everything in one seeded rng and a config object (smoke rate, terrain height), or was it rewriting the generator every pass?
@DannyLimanseta never opening the editor is the real unlock. does claude read the UnrealBuildTool log on its own and fix the compile errors, or do you still paste them back in?
@LexnLin 6.1M cells with zero assets is wild. curious how you iterate on it: do you fix the timestep and seed the noise so each take is identical, or let it re-roll and judge by eye?
Week one of Shallow_Vibes, in one dashboard.
21 posts across X, Instagram, TikTok and YouTube. 1.3K impressions. Small numbers, real ones.
So we built a dashboard to track it all:
• filters by platform and metric
• a weekly and monthly posting calendar
• every published post with its stats
• Radar: new AI tools worth saving, every Saturday
What would you add to it?
@jdn1el agree, the 20% is mostly writing it down. plan mode (shift+tab) helps here: ask claude to interview you until it can state the goal and one acceptance test in a few lines. do you write a spec first, or figure it out while it builds?