Relax, I only have one Sunday to work on idea, literally my weekend project. So I tried Deepseek to see if it can help. Surprisingly, it works and it saves me another weekend...
Just chat.deepseek.com (cost = free) with prompts adapted from this gist.
If you've used Emacs to interact with LLMs, you've probably encountered gptel. While it appears simple on the surface—just another chat interface—its internals reveal an elegant approach to managing LLM conversations that leverages Emacs' text property system. Let's dive into how it works.
One of the first things you notice in a gptel chat buffer are the prefixes—typically "### " for user messages in Markdown mode or "*** " in Org mode. What's interesting is that these prefixes are purely cosmetic. They're stripped out before any API calls using a simple but effective mechanism:
(defsubst gptel--trim-prefixes (s)
I stumbled on an incredible open source solution, Lima. In some ways, it has some of Hashicorp's Vagrant's resemblance, but in my opinion, it's so much superior in many ways as it doesn't use external dependencies such as Oracle's VirtualBox.
If you're used to docker on the command line but wanted to play with VMs rather than containers, then this is for you! No need to fuss with cloud-init as a user account (using your existing username in whoami) with a proper home directory would be auto-generated for you with full passwordless sudo privilege. SSH access to the VMs from the host is seamlessly integrated as well.
This quick guide is for those who need to set up virtual machines with modern Linux OSes (only few selected OSes are best supported) from scratch using only the command line. You can have a VM up and running within minutes from absolutely nothing.
NOTE: This was last tested using:
| (require 'llm) | |
| (require 'llm-prompt) | |
| (defvar llm-provider nil | |
| "The LLM provider to use for misc functionality") | |
| (llm-defprompt llm-context | |
| "The user is currently in Emacs. The following is part of the buffer they are looking at, which is a {{mode}} buffer. Their cursor is marked with '{{cursor}}': | |
| {{context}}") |
| { | |
| "$schema": "https://lnav.org/schemas/format-v1.schema.json", | |
| "caddy": { | |
| "title": "Caddy Server", | |
| "description": "Caddy Server JSON access logs format", | |
| "url": [ | |
| "https://caddyserver.com/docs/caddyfile/directives/log" | |
| ], | |
| "json": true, | |
| "timestamp-field": "ts", |
| /* | |
| Usage: you'll want to search for the strings <bucket> and <prefix>, and insert the S3 bucket where your access | |
| logs are being delivered. Use (or delete) <prefix> to filter to a subset of your logs. | |
| */ | |
| /* | |
| These commented out configuration settings you can either run yourself in the REPL and source this file using | |
| `.read parse_s3_access_logs.sql`, or you can uncomment them and supply values for yourself. |
| const std = @import("std"); | |
| pub fn build(b: *std.Build) void { | |
| // Standard target options allows the person running `zig build` to choose | |
| // what target to build for. Here we do not override the defaults, which | |
| // means any target is allowed, and the default is native. Other options | |
| // for restricting supported target set are available. | |
| const target = b.standardTargetOptions(.{}); | |
| // Standard optimization options allow the person running `zig build` to select |
| AWSTemplateFormatVersion: "2010-09-09" | |
| Description: >- | |
| openid-connect-app | |
| Testing creating an OpenID Identity Provider with Cognito | |
| Transform: | |
| - AWS::Serverless-2016-10-31 | |
| Resources: |
