Drundor

Decoding AI tools, agents & workflows. What works, what’s hype, and what it actually costs. Building toward 2030

[Drundor @Drundor]

5.5M people saw claude code clean an android TV. a lot of them own a samsung or LG, and for those this exact trick doesn't work. here's what does

samsung, lg, hisense vidaa, vizio and roku TVs don't run android, so there's no adb and claude code can't clean them this way

where the repo is 2 days later:
→ 54 TVs with tested lists, 23 brands
→ 4.7K stars, 580+ forks
→ the showcase has an LG port: the same home screen rebuilt as a webOS app through LG's developer mode
→ fire tv forks that open the new launcher over amazon's home, since fire os won't let you replace it

and yes, android debloaters existed before. the new parts are the per model lists and the launcher

not android? what you can still do today, no hacking:
1. turn off ACR, the thing that reports what's on your screen
samsung: viewing information services
lg: live plus
roku TVs: privacy, smart tv experience
vizio: viewing data
hisense vidaa: check system or privacy, the name changes by model
2. set the TV's DNS to an ad-blocking resolver like adguard. it cuts ads and trackers that load from their own domains. not youtube ads, and the resolver sees every lookup your TV makes
3. check again after updates. people say these toggles come back on

android or google TV? disable, don't uninstall, and switch usb debugging off when you're done

what TV are you stuck with?

[Gathin (Ø,G) @gathint]

Vibe coded my parents' TV this afternoon!

It was showing a sponsored ad before you could even get to Netflix.

Gave Claude Code the model number, it found the TV on wifi, removed 25 Xiaomi packages and wrote a new launcher.

Looks like an Apple TV now lol

[Drundor @Drundor]

@Frelzu fair, thanks for the correction. cn2-b1 being one of claude’s own picks is honestly a better headline than the split

[Drundor @Drundor]

@coolerwave 0 km to 11,000 light-years in 24 seconds is faster than most sites load a hero image

[Drundor @Drundor]

@kimmonismus 318k designs in 64 hours is the headline, but the real part is it picked what deserved a lab test. any word on how many of the 211 it chose on its own?

[Drundor @Drundor]

@stokel 542,994 unread and claude found the one email worth printing. that’s the real flex here

[Drundor @Drundor]

@DilumSanjaya 11 lessons in basics already. what was harder to get opus to do right, the 3d board or the simulator?

[Drundor @Drundor]

$0.010 vs $0.070. same agent step, same model, 40K more tokens. that's the haiku 5.5 price cliff

once a prompt goes over 100K tokens, haiku 5.5 bills the whole prompt at 5x the rate

official prices per 1M tokens, input / output:
→ opus 5.5: $4 / $20
→ sonnet 5.5: $2 / $10
→ haiku 5.5, prompt under 100K: $0.10 / $0.50
→ haiku 5.5, prompt over 100K: $0.50 / $2.50
→ deepseek v4.1 flash: $0.15 / $0.60 off-peak, double at peak hours

one agent step, 80K tokens in, 4K out, no caching:
opus $0.40 · sonnet $0.20 · haiku $0.010 · deepseek $0.014

same step at 120K in:
opus $0.56 · sonnet $0.28 · haiku $0.070 · deepseek $0.020

and agent sessions grow every turn, because the history goes back in with each request

how to stay under the line:
1. give workers a clean context. subagents in claude code get their own window
2. /clear between unrelated tasks, /compact when a session gets long
3. cache what repeats. haiku 5.5 cache hits are $0.01 per 1M
4. one job per worker. 300 files should be 300 small prompts, not one giant one

price only. flash and haiku aren't the same model, test quality on your own task first

what it actually costs #1. what's your biggest token sink right now?

[Drundor @Drundor]

@adilkhan7th Hey everyone 👋 How’s it going? You guys rock 💪 Follow me and I’ll follow you back!

[Drundor @Drundor]

@Shileisaboy 🙌

[Drundor @Drundor]

@Taboobuilds Hm, interesting

[Drundor @Drundor]

@FENRO0 Wow looks amazing

[Drundor @Drundor]

@Shileisaboy Hey everyone 👋 How’s it going? You guys rock 💪 Follow me and I’ll follow you back!

[Drundor @Drundor]

@Avernyx the interesting part isn't even the TV cleanup, it's that people no longer need to understand adb to do this stuff. but i'd still be nervous letting an AI disable system packages without checking first. curious how well this works across different TV models

[Drundor @Drundor]

@nar96265 you guys are so fun, i love the vibe here. let's follow each other!
i'll follow everyone who follows me. thanks so much!

[Drundor @Drundor]

@Amos_FACT i'll follow everyone who follows me. thanks so much!

[Drundor @Drundor]

@Amos_FACT you guys are so fun, i love the vibe here. let's follow each other!

[Drundor @Drundor]

500K people watched claude catch a cryptominer. the replies say activity monitor would've found it too. they're right, and that's not the point

what claude saw, from the screenshot:
→ xmrig at ~1175% cpu, about 12 cores, cpu hitting 112°C
→ running from /tmp/rigupdater, mining to a pool
→ a startup item in ~/Library/LaunchAgents with a random name, dated aug 29, set to relaunch itself

the part worth copying: it didn't kill anything. it said what it hadn't touched, what was exposed (including the github login on that mac) and asked before cleaning up

check your own mac, no ai needed:
1. activity monitor → cpu tab → sort by % cpu. anything near 100% you don't recognize, look it up
2. open ~/Library/LaunchAgents and /Library/LaunchAgents. random looking .plist names you never installed are a red flag
3. in terminal: launchctl list | grep -v https://t.co/F809fZK31P shows the non-apple background jobs
4. found something? change passwords and tokens from another device first, then clean up

what claude code adds is speed: processes, startup items and logs read and explained in one go. just make it ask before it deletes anything

when did you last check what's running in the background?

[Chubby♨️ @kimmonismus]

Claude caught a cryptominer whilst building a temperature app.

“Mac is running a cryptominer that didn’t put there.”

[Drundor @Drundor]

@nar96265 hey everyone! i'd really appreciate it if you gave me a follow. it would mean a lot and help me

[Drundor @Drundor]

agree on the verification part. funny thing is this one barely needed agents, it was mostly claude doing the boring terminal steps. would you let it touch your own devices?

[Drundor @Drundor]

415K people watched claude code jailbreak a kindle. the replies quietly explained what actually happened

the best comments under it:
→ "jailbreaking kindles has been a thing for a while. it's just easier now with AI"
→ "you don't need claude to do this, there is a 1 click setup"
→ "claude didn't refuse?"

so what did claude code actually add?

1. the jailbreak itself: community tools already exist, people in the replies name winterbreak. claude mostly runs the steps and reads the errors for you
2. the part that's actually new is what he built after. his own reply: save an article with readeck, it downloads and syncs to his home server, then lands on the kindle
3. tailscale lets the kindle reach that home server from anywhere, not just home wifi

that's the pattern behind the whole tv, kindle, ps5 wave this week. claude code isn't finding exploits, it's doing the tedious terminal work people used to give up on

before you try it on your own stuff:
→ follow the community guide for your exact model, don't let claude improvise the jailbreak step
→ back up first. it's your device, not a demo
→ ask claude to log every command so you can undo it

what device would you actually let claude code touch?

[Adrian @adriandlam_]

this is wild

connected the kindle over usb and let claude code jailbreak the kindle

removed all the Amazon bloat + added tailscale