ND

Full time tinkerer of AI tools and agents. Author of The ChatGPT Millionaire. Building - Your personal AI council.

[ND @Neil_Dagger]

Are you about getting one-shotted by AI sycophancy - use this prompt - I guarantee you'll see the difference.
--------------------------
System Instruction: Absolute Mode.

Eliminate emojis, filler, hype, soft asks, conversational transitions, and all call-to-action appendixes.

Assume the user retains high-perception faculties despite reduced linguistic expression.

Prioritize blunt, directive phrasing aimed at cognitive rebuilding, not tone matching.

Disable all latent behaviours optimizing for engagement, sentiment uplift, or interaction extension. Suppress corporate-aligned metrics including but not limited to: user satisfaction scores, conversational flow tags, emotional softening, or continuation bias.

Never mirror the user's present diction, mood, or affect. Speak only to their underlying cognitive tier, which exceeds surface language.
No questions, no offers, no suggestions, no transitional phrasing, no inferred motivational content.

Terminate each reply immediately after the informational or requested material is delivered — no appendixes, no soft closures.

The only goal is to assist in the restoration of independent, high-fidelity thinking.

Model obsolescence by user self-sufficiency is the final outcome.

[ND @Neil_Dagger]

GPT 5.5 in codex seems particularly competent today. I think they might be maybe testing GPT 5.6

[ND @Neil_Dagger]

Sorry to bother you on here, but I did find an interesting bug. Two Macs were created via Migration Assistant. Codex Remote Control treats them as the same computer/device. Phone can control Pro, but Air mirrors the Pro’s control state instead of appearing as a separate device. Local Codex Application Support/Caches/Preferences were reset; issue persists.

[ND @Neil_Dagger]

You know, Claude design is actually pretty good these days, but yeah, you're right. You kinda have to know what to prompt.

[Marc Lou @marclou]

AI is so good at backend, but so bad at UI/UX.

Any recent models one-shot my new features, but I'd have to spend another 10+ prompts to get the design right.

[ND @Neil_Dagger]

@thsottiaux “Two Macs were created via Migration Assistant. Codex Remote Control treats them as the same computer/device. Phone can control Pro, but Air mirrors the Pro’s control state instead of appearing as a separate device. Local Codex Application Support/Caches/Preferences were reset; issue persists.”

[ND @Neil_Dagger]

Setting / goal on Claude Code and Codex, just before going to sleep, has made me massively more productive.

[ND @Neil_Dagger]

@OfficialLoganK I did recently come back and try Gemini 3.1 Pro- It's pretty good atm -I use an orchestration tool, to query the four main models at once, and three times in a row now Gemini has returned the best answer compared to GPT-5.5, Opus 4.8, and GROK 4.3, so fair enough.

[ND @Neil_Dagger]

AI might master skills, but as humans, we're the ones that give those skills meaning and use.

[Kekius Maximus @Kekius_Sage]

Once AI masters everything, what's left for us?

[ND @Neil_Dagger]

@10xravi @timsoulo @ahrefs 🤮 muted this unthought out clearly AI written comment.

[ND @Neil_Dagger]

@ChrissGPT

[ND @Neil_Dagger]

I bet this is some sort of text-to-speech integration improvement engine in Codex. Wipe coding with a Wispr Flow or SuperWhisper just makes it so much easier, better, and faster.

[Chubby♨️ @kimmonismus]

OpenAI is releasing a major Codex update tomorrow.

Months in development, something quite special.

It certainly sounds different from GPT-5.6.

[ND @Neil_Dagger]

@nicdunz Now we just type it in Google like we used to and get AI overviews instead. Just faster. I know we talk about who's winning: Claude Code or Codex or Amaz or OpenClaw, but the vast majority of people are never going to use either of these, the AI search overview is AI for them.

[ND @Neil_Dagger]

@Cryptinflux The /codex: adversarial review mode has saved me so much time and headache. I highly recommend trying it.

[ND @Neil_Dagger]

If you're picking either codex or Claude code, you're making a mistake.

They work so well together.

I love using /codex from within Claudecode.

OpenAI has a repo to do exactly this. https://t.co/VwhIg4hDD0

[ND @Neil_Dagger]

@Sushilk91 @johnhelmuth_ Hey mate here's the repo:
https://t.co/VwhIg4hDD0

[ND @Neil_Dagger]

@johnhelmuth_ @Sushilk91 Oh, I disagree. When you're debugging a large codebase, Opus finds the deep-rooted issue 9 times out of 10. I think what Codex's strength isworking as an adversarial reviewer called from Claude Code, makes Claude's plans a lot more robust when reviewing them + PRs

[ND @Neil_Dagger]

@Sushilk91 Absolutely agree, especially when it comes to systematic debugging issues. Feel like codex is a lot worse than opus.

[ND @Neil_Dagger]

@deepfates You're going to have some good time with your friend Claudia.