irkiziza

@excalilburned wkwkw mgapa inii, gw nyaria fulltime disna

janji gak cabul? akwowkwowk

@ReadMaxx_ wtf. this is cooolll

Speed Reading, Built for iPhone

Guys ada yg punya rekomendasi website lain buat #kaburajadulu selain: tokyodev.com relocate.me go.104.com.tw Thanks in advance!

@mownohoes mo, you lost your edge

I finally got around to making a skill a lot of people have been asking me for: jeffreys-skills.md/skills/simplif… It basically helps to "de-slopify" and refactor code that's been written by agents, looking for ways to simplify and reduce the amount of code without changing the behavior. The difference between this and other skills or prompts in the same spirit is the lengths this one goes to in order to prevent the process from going off the rails and introducing bugs or security problems. It's a whole elaborate system spanning 98 files and one full megabyte of reference files, scripts, and subagents (see pic). You can run it over and over again and it will autonomously identify good opportunities for accretive simplification and do everything needed to implement the changes and prove that they didn't change the outputs. GPT-5.5 can explain better than I can how it does all that and what makes it so compelling and useful: --- The strongest thing about this skill is that it treats refactoring as a proof obligation. A normal “clean this up” prompt invites the model to follow taste. It sees repetition, long files, wrapper functions, stale types, try/catch clutter, _v2 files, and it starts cutting. Sometimes that works. Sometimes it silently changes error semantics, loses a side effect, removes a lifecycle hook, or deletes a file that looked unused but was actually the intended implementation path. This skill changes the frame. A simplification claim becomes: “this smaller program is observably equivalent to the larger one.” Then it makes the agent prove that claim. It starts with a baseline: tests, golden outputs, LOC, warnings, complexity. It maps duplication instead of eyeballing it. It classifies clones, because exact copy-paste, parametric duplication, semantic similarity, and accidental rhymes are completely different things. It scores each candidate by expected LOC saved, confidence, and risk. Low-score candidates get rejected and logged, which is important because future agents otherwise rediscover the same bad idea forever. The isomorphism card is the key move. Before editing, the agent has to answer boring but lethal questions: same ordering, same errors, same logs, same metrics, same side effects, same async cancellation behavior, same React hook identity, same serialization, same resource lifecycle. Those rows catch the kind of bugs that compilers and ordinary tests miss. Then the edit discipline is deliberately narrow: one lever per commit, no rewrites, no sed, no drive-by fixes, no deletion without explicit permission. Afterward, it verifies behavior again and records the result in a ledger. If the refactor did not actually preserve behavior, it does not get to call itself a refactor. What I like about it is that it matches the real failure modes of agent-written code. AI code tends to accumulate plausible junk: defensive branches for impossible inputs, duplicated wrappers, too many optional parameters, orphaned “improved” files, shallow happy-path tests, stale types, and comments that are really leftover task plans. The skill has a whole pathology catalog for those patterns, plus scripts and subagent roles to find them systematically. So the compelling part is not “make the code prettier.” The compelling part is leverage with brakes. You can send very strong models into messy codebases and ask them to reduce complexity aggressively, while forcing them to preserve the contract that matters: observable behavior. That is the difference between a refactor you hope is safe and a refactor you can audit.

Paste a URL. Get a DESIGN. md

@Mangroxian @IndoKnight219 fmhy.net

@IndoKnight219 Where should one get them? Just curious as an Indonesian oppressed by foreign government laws

>Ryuugames have fun with trojan lol

told gpt 5.5 to rebuild the nothing design bento grid from the skill

/make-interfaces-feel-better npx skills add jakubkrehel/make-interfaces-feel-better

Unicode Spinner finally live on @framer 150 unique loader animations with custom shape From minimal braille dot patterns to playful emoji sequences. no images, no svgs, no external dependencies. just pure unicode characters unicode.framer.website

@rangerbiru_17 @levifikri codex luwes banget, jauh lebih bajyak daripada limit claude.

@levifikri codex bermasalah limit yang terlalu nyekek ga? claude makin kesini makin parah ya. gua terakhir make itu kemaren dan limit sampe jam 7 semalem. terus pagi gua pake kan. baru 2 pertanyaan udah limit lagi bjir

Claude Opus dan Codex Wajib coba 2 itu untuk sekarang Sangat real gap antara yang maximize AI dan nggak. $20 itu beneran investasi yang sangat murah sih dengan value segitu. Kalau ada budget lebih, coba ke yang $100

@orielhaim @heyandras yooo this is so cool

@heyandras github.com/orielhaim/Stor… I got 21 stars the hard way... I had to send to people in a thousand places that are supposed to support "open source" but block every way to get started and only respect those who are already famous....

wtf

man, I love terminal spinners github.com/vyfor/rattles #rustlang #ratatui

@nayakayp dari si provider cloud yang oren oren itu kan mas?

Kl mau berusaha dikit alias effort ngumpulkan informasi sana sini, sebetulnya bisa aja dpt model LLM top tier terbaru (Yes, Opus 4.6) dg modal yg "hampir gratis" :) Tapi ini informasi bahaya, gak layak share di sini hehe

Sites on the internet for design inspiration. Web Design → curated.design Landing Pages → landing.love Saas Websites → saaspo.com Navbar → navbar.gallery CTA Sections → cta.gallery Animation → appmotion.design Mobile Apps → mobbin.com/?via=abraham Brands → rebrand.gallery Icons → hugeicons.com/?via=Abraham Design Systems → component.gallery

Agar tidak gatekeep. Daftar artikel saya soal kerja di LN: - Mencari kerja asepbagja.com/id/pribadi/men… - Relokasi atau remote asepbagja.com/id/pribadi/rel… - Cara belajar bahasa asepbagja.com/id/pribadi/car… - Pengalaman PHK asepbagja.com/id/pribadi/pen… - Relokasi bawa kucing asepbagja.com/id/pribadi/mem…

@levifikri coba pake iSH shell mas, harusnya lebih enteng dan open source 😆

Sekarang jadi sering coding di MRT/LRT & Grab :D via iPad Mini. SSH/Mosh ke VPS seharga $4* Prompting2 ke Claude Code di sana** Buat FE yang butuh preview, bisa buka SSH Tunnel***. Jadi bisa localhost:3000 di iPad, yang itu buka port 3000 di VPS Hasilnya? Jadi makin banyak commits, dan quota Claude Code cepet habis haha *Sebenarnya kalau /remote-control stabil, enak pake itu **Pake Zellij/Tmux biar bisa resume session pas di laptop ***Saya pake app Termius (free plan), di Android juga ada. Tapi enakan di layar gedean sih :)

Made an updated version this weekend Here's how you do it (raw notes) > Grab @karpathy's latest gist (in the first comment) > Download @steipete summarize CLI > Download yt-dlp > Download obsidian > Download @tobi qmd --> Setup a node or Golang CLI called "brain" --> Have it index all your youtube data, AI agent data (jsonl files) --> Get your X data by requesting an archive in your settings --> Setup vaults for each domain/topic area --> Ask questions with your agent and qmd