by Flamerix AI · MIT License
Platforms: Linux and Windows 11 tested by us; macOS reported by others. Tested on Claude Code 2.1.257–2.1.317. The binary is not modified (
BUN_OPTIONS=--preload). An update can silently undo it, so see Verify.
Every ~30 seconds, Claude Code re-sends each background agent's full transcript to the model to
Caution
From 2026-09-27, four official JavaScript files on Level Infinite's CDN contained attacker code. The NIKKE PC launcher loads these files. From Oct 24 at the latest, opening the launcher could install a remote-control agent: while the launcher was open, the attacker could run any command on your machine, read any file and take screenshots.
Update, 2026-11-03 20:40 GMT: three of the files were replaced on Nov 3 at 17:04, 17:13 and 17:21 GMT. The fourth, FeedList.feb647c9.js, was cleaned at the origin on Oct 28, but two CDN servers still delivered the modified copy at 20:23 GMT. The attacker's server no longer answered at 18:31 GMT. None of this undoes anything on machines that were already infected, and the old files may still be in your launcher's cache. Do not open the NIKKE PC launcher until Level Infinite confirms the fix, and clear its cache before you do.
This report comes from one infected machine, plus findings from other
See how a minor change to your commit message style can make a difference.
git commit -m"<type>(<optional scope>): <description>" \ -m"<optional body>" \
See
Léna Piquet (Froyok), [Breakdown] Shadow of the Colossus (PAL, PS2), 2012 https://www.froyok.fr/blog/2012-10-breakdown-shadow-of-the-colossus-pal-ps2/
The Making of Shadow of the Colossus (PDF, hosted with the breakdown above) https://www.froyok.fr/blog/2012-10-breakdown-shadow-of-the-colossus-pal-ps2/resources/making_of_sotc.pdf
Fumito Ueda interview, The Making of the Colossi https://glitterberri.com/extended-developer-interview/making-of-the-colossi/
A pattern for building personal knowledge bases using LLMs.
This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.
Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.
Caution
As of August 26th 2026, Discord has started suspending quest access of people caught automating quest completion.
Some users have received the following system message:
There isn't much I can do to make the script undetected, so use it at your own risk, as you WILL get flagged by doing so.
Each of these commands will run an ad hoc http static server in your current (or specified) directory, available at http://localhost:8000. Use this power wisely.
$ python -m SimpleHTTPServer 8000| package main | |
| var flagAlias = map[string]string{ | |
| "long-version": "lv", | |
| } | |
| func init() { | |
| for from, to := range flagAlias { | |
| flagSet := flag.Lookup(from) | |
| cli.Var(flagSet.Value, to, fmt.Sprintf("alias to %s", flagSet.Name)) |
