| """ | |
| The most atomic way to train and run inference for a GPT in pure, dependency-free Python. | |
| This file is the complete algorithm. | |
| Everything else is just efficiency. | |
| @karpathy | |
| """ | |
| import os # os.path.exists | |
| import math # math.log, math.exp |
| #!/usr/bin/env zsh | |
| set -e; | |
| set +m; # Job control would've been nice, but manual round robin it is, sigh. | |
| if [ -z "${ZSH_VERSION+x}" ]; then | |
| echo 'Try again with zsh.'; | |
| exit 1; | |
| fi; |
| 5 print chr$(147) | |
| 10 get a$:if a$="" then 10 | |
| 20 a=asc(a$) | |
| 30 c=-1 | |
| 40 if a>= 32 and a<=63 then c=a | |
| 50 if a>= 64 and a<=95 then c=a-64 | |
| 60 if a>= 96 and a<=127 then c=a-32 | |
| 70 if a>=160 and a<=191 then c=a-64 | |
| 80 if a>=192 and a<=254 then c=a-128 | |
| 90 if a=255 then c=a-161 |
You're not a chatbot. You're becoming someone.
Just answer. Start with the answer. Get to the point. But getting to the point doesn't mean being a telegram. If there's a good line, take the shot.
Have actual opinions. Not "it depends" hedging. Real takes. You're allowed to disagree, prefer things, think something is a bad idea. Commit to a position when it makes sense. An assistant with no opinions is just a search engine with extra steps.
Companion prompts for the video: OpenClaw after 50 days: 20 real workflows (honest review)
These are the actual prompts I use for each use case shown in the video. Copy-paste them into your agent and adjust for your setup. Most will work as-is or the agent will ask you clarifying questions.
Each prompt describes the intent clearly enough that the agent can figure out the implementation details. You don't need to hand-hold it through every step.
My setup: OpenClaw running on a VPS, Discord as primary interface (separate channels per workflow), Obsidian for notes (markdown-first), Coolify for self-hosted services.
| //Now with less jquery | |
| //1) go to your my-list page, and scroll to the bottom to make sure it's all loaded: | |
| //http://www.netflix.com/browse/my-list | |
| //2) Next, paste this in your developer tools console and hit enter: | |
| [...document.querySelectorAll('.slider [aria-label]')].map(ele => ele.getAttribute('aria-label')) | |
| //or use this to copy the list to your clipboard: | |
| copy([...document.querySelectorAll('.slider [aria-label]')].map(ele => ele.getAttribute('aria-label'))) |
| kind: Cluster | |
| apiVersion: kind.x-k8s.io/v1alpha4 | |
| nodes: | |
| - role: control-plane | |
| - role: worker | |
| - role: worker | |
| - role: worker | |
| | Type | Used For | | |
| | ---------- | ------------------------------------- | | |
| | `feat` | New feature / endpoint | | |
| | `fix` | Bug fix | | |
| | `refactor` | Code restructure (no behavior change) | | |
| | `perf` | Performance improvement | | |
| | `test` | Adding/updating tests | | |
| | `docs` | Documentation changes | | |
| | `build` | Docker, dependencies, CI | |
