mmizutani

How the Grok Bot harness works - @gabefletcher

The Grok Bot host builds model requests, runs tools and saves the agent's state. Hosted services also handle identity, scheduling, sync and other features.

A message starts in the desktop app. The desktop sends it to the box host and shows the response. It also manages account connections and can run tools on the user's computer. The host builds the model's context, calls the provider, runs requested tools and saves the results. It then decides whether another model call is needed. The visible chat, model conversation and learned memory use separate stores. Changing the model provider leaves the other hosted service calls in place.

The original architecture sections cover public host 17e335e and desktop 0.52. The later comparison adds five-host source analysis, desktop .57.1 findings and isolated runtime measurements. Host and desktop have separate version number

mmizutani

How to use:

1. Clone https://github.com/miklschmidt/codex and build codex yourself.
   • i've added devenv in my fork, you can try devenv shell nix build .#packages.<system>.codex-rs (eg. devenv shell nix build .#packages.x86_64-linux.codex-rs)
   • when built, symlink the binary to ~/.local/bin/codex: ln -s $(pwd)/result/bin/codex ~/.local/bin/codex
2. Add the instructions (.md files) from this gist to .codex/ in the project where you want to test it.
3. Launch codex --profile orchestrator and ask it to do something.

mmizutani

#!/bin/bash
#
# init-firewall.sh - Egress Firewall for Development Container with Claude Code
#
# This script configures iptables to function as a strict egress firewall.
# Its primary purpose is to enhance security by restricting network access from
# within a development container to only a predefined list of essential services
# required for development, such as package managers (npm, Go), source control
# (GitHub), and specific APIs (Anthropic).
# Adapted from https://github.com/anthropics/devcontainer-features/blob/e09d1bb8d0f413fc8e6a5936478939cf2463deec/src/claude-code/init-firewall.sh

mmizutani

"""
A minimal, fast example generating text with Llama 3.1 in MLX.

To run, install the requirements:

    pip install -U mlx transformers fire

Then generate text with:

    python l3min.py "How tall is K2?"

mmizutani

require 'active_record/connection_adapters/sqlite3_adapter'

#
# Monkey-patch for disable foreign keys during `alter_table` for sqlite3 adapter for Rails 5
#

module ActiveRecord
  module ConnectionAdapters
    class SQLite3Adapter < AbstractAdapter

mmizutani

#!/bin/bash
SCRIPTNAME=$(basename "$0")

function realpath () {
  f=$@;
  if [ -d "$f" ]; then
    base="";
    dir="$f";
  else
    base="/$(basename "$f")";

mmizutani

This worked on 14/May/23. The instructions will probably require updating in the future.

llama is a text prediction model similar to GPT-2, and the version of GPT-3 that has not been fine tuned yet. It is also possible to run fine tuned versions (like alpaca or vicuna with this. I think. Those versions are more focused on answering questions)

Note: I have been told that this does not support multiple GPUs. It can only use a single GPU.

It is possible to run LLama 13B with a 6GB graphics card now! (e.g. a RTX 2060). Thanks to the amazing work involved in llama.cpp. The latest change is CUDA/cuBLAS which allows you pick an arbitrary number of the transformer layers to be run on the GPU. This is perfect for low VRAM.

• Clone llama.cpp from git, I am on commit 08737ef720f0510c7ec2aa84d7f70c691073c35d.

mmizutani

rule gen_injected_template_Word
{
    meta:
        description = "Detects injected templates in DOCX"
        author = "John Lambert @JohnLaTwC"
        date = "2020-05-03"
        hash1 = "a3eca35d14b0e020444186a5faaba5997994a47af08580521f808b1bb83d6063"
        hash2 = "a275dfa95393148bb9e0ddf5346f9fedcc9c87fa2ec3ce1ec875843664c37c89"
        hash3 = "ed4835e5fd10bbd2be04c5ea9eb2b8e750aff2ef235de6e0f18d369469f69c83"
        file_protocol_hash1 = "ac6c1df3895af63b864bb33bf30cb31059e247443ddb8f23517849362ec94f08 (settings.xml.rels)"

mmizutani

#
# Manually set the contents of an encrypted session cookie
#
# Uses the same encryption keys as the Rails app using devise
#
# Based off http://big-elephants.com/2014-01/handling-rails-4-sessions-with-go/
# Verified against https://github.com/rails/rails/blob/master/actionpack/lib/action_dispatch/middleware/cookies.rb
#
class TestSession

mmizutani

{
  "$schema": "http://json-schema.org/draft-04/schema#",
  "properties": {
    "node": {
      "properties": {
        "id": {
          "type": "string",
          "description": "An opaque node identifier for the Envoy node. This also provides the local\n service node name. It should be set if any of the following features are\n used: :ref:`statsd <arch_overview_statistics>`, :ref:`CDS\n <config_cluster_manager_cds>`, and :ref:`HTTP tracing\n <arch_overview_tracing>`, either in this message or via\n :option:`--service-node`."
        },
        "cluster": {