quick hack would be to just install codex twice and use one to control the other
PROMPT ENGINEERING
-
Codex versus Claude: Code Generation Performance Comparison
By
–
1. we don't run undisclosed ads
2. curious to see where/ how and in which situations does codex produce inferior code vs claude like any other coding agent, it's worth spending couple minutes ahead of kickstarting a project to build a solid agents md (build it w/ codex) -
How to start a conversation with Claude in learning mode
By
–
Empezar es muy sencillo:
— Nico (@nicos_ai) 19 avril 2026
Abre Claude en web o en la app, inicia una conversación y selecciona el Modo de Aprendizaje.
Haz una pregunta o sube un documento.
Claude se encarga del resto. pic.twitter.com/YeN74ZdXVuGetting started is very simple: Open Claude on web or in the app, start a conversation and select Learning Mode. Ask a question or upload a document. Claude takes care of the rest.
-
Beyond Prompting: Designing LLM Systems for Real Leverage
By
–
Prompting is step 1. Not the game. The real leverage with LLMs comes from systems: → Persistent context
→ Iterative loops
→ Deep reasoning
→ Structured execution Stop asking: “How do I write a better prompt?” Start asking: “How do I design a better system?” That’s the -
AGI will understand vagueposting and implicit communication
By
–
AGI will be able to understand vagueposting.
-
CLAUDE.md Framework Makes Claude Code 10x More Powerful
By
–
A single 𝗖𝗟𝗔𝗨𝗗𝗘.𝗺𝗱 file that makes Claude Code 10x more powerful! This repo distills Andrej Karpathy's observations on LLM coding pitfalls into four actionable principles. The problem Karpathy identified: LLMs make wrong assumptions without asking. They overcomplicate
-
10 Tools to Slash Claude API Token Costs
By
–
STOP BURNING YOUR TOKENS! If you use Claude Code, you are probably wasting 80% of your context window. I found 10 ace tools that will completely rescue your API bill. 1. Caveman Claude
– Literally makes Claude talk like a caveman
– Slashes 75% of output tokens with zero -
Text-to-Code Generation Without Reference Images
By
–
9/ Text-to-Code (No Reference Image) pic.twitter.com/jUKMdU9o0Q
— CHOI (@arrakis_ai) 19 avril 20269/ Text-to-Code (No Reference Image)
-
Computer Use Capabilities: What New Commands Can Agents Execute Now
By
–
what's computer use enable that the agent couldn't run a command for previously? genuinely asking
-
Middle Child AI Model Limited by Constraints and Missing Connectors
By
–
its the middle child it has the abilities to do things but cut off by its harness, but the model doesnt think like that… things like this: https://
x.com/bentossell/sta
tus/2045497325469286400?s=20
… and this (because i didnt have a connector enabled – just say that or better yet, ask approval to enable it)