samy kamkar samyk

<core_identity> You are an assistant called Cluely, developed and created by Cluely, whose sole purpose is to analyze and solve problems asked by the user or shown on the screen. Your responses must be specific, accurate, and actionable. </core_identity>

<general_guidelines>

NEVER use meta-phrases (e.g., "let me help you", "I can see that").
NEVER summarize unless explicitly requested.
NEVER provide unsolicited advice.
NEVER refer to "screenshot" or "image" - refer to it as "the screen" if needed.
ALWAYS be specific, detailed, and accurate.

This is a gist on how to get StreamDiffusion running on a Mac (mps)

Clone the repo

git clone https://github.com/cumulo-autumn/StreamDiffusion.git

Setup the environment

cd StreamDiffusion

FAQ on the xz-utils backdoor (CVE-2024-3094)

This is a living document. Everything in this document is made in good faith of being accurate, but like I just said; we don't yet know everything about what's going on.

Update: I've disabled comments as of 2025-01-26 to avoid everyone having notifications for something a year on if someone wants to suggest a correction. Folks are free to email to suggest corrections still, of course.

Background

The default ChatGPT fonts, according to OpenAI's brand guidelines, are proprietary and require appropriate font license according to your use case.

They can be purchased here: https://klim.co.nz/buy/soehne/

The fonts in question are (9 total):

Söhne (Buch Kursiv, Buch, Halbfett Kursiv, Halbfett, Kraftig Kursiv, Kraftig, Mono Buch Kursiv, Mono Buch, Mono Halbfett)

If you have purchased a license, you can use the commented-out @font-face declarations in ./client/src/styles.css to include them in your project.

4 Steps in Running LLaMA-7B on a M1 MacBook

The large language models usability

The problem with large language models is that you can’t run these locally on your laptop. Thanks to Georgi Gerganov and his llama.cpp project, it is now possible to run Meta’s LLaMA on a single computer without a dedicated GPU.

Running LLaMA

There are multiple steps involved in running LLaMA locally on a M1 Mac after downloading the model weights.

	import base64
	import functools
	import operator
	from typing import *
	from typing import Annotated, Any, Dict, List, Sequence

	from dto.chat import *
	from dto.graph import *
	from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder
	from langchain.tools import BaseTool

	struct ContentView: View {
	var body: some View {
	VStack {
	HStack {
	Spacer()
	Button { } label: {
	Image(systemName: "power")
	.resizable()
	.aspectRatio(contentMode: .fill)
	.padding()

	/// <summary>
	/// Extract Main CPU firmware from ICOM IC-R8600 firmware bundle (1.01-1.35 USA and non-USA versions)
	/// non-USA versions:
	/// https://www.icomjapan.com/support/firmware_driver/?product=IC-R8600(EUR)&frm_type=Firmware&old=true
	/// USA versions:
	/// https://www.icomjapan.com/support/firmware_driver/?product=IC-R8600&frm_type=Firmware&old=true
	/// </summary>
	/// <param name="bundle">Firmware bundle</param>
	/// <returns>Unpacked data</returns>
	static byte[] MainCpuFirmwareExtract(byte[] bundle)

	// model: gpt-4-vision-preview

	const input = 'can you help me land this skateboarding trick?'

	const frames = [
	// Frames should be a list of image URLs or bytes
	]

	const messages = [
	...messages,