Pinned Tweet
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.
1
8
531
Cant see my pinned chats in the new ChatGPT app - what atrocious badly thought out UX hell is this???
50
The most garbage update in the history of OpenAI - seriously I want full screen chats back !
It'd be fine if Chatgpt.com on browsers wasn't an insane memory leak that loaded insufferably slow in long threads.
56
Having the ability to constantly analyse every decision deeply to the umpteenth level with Claude/ChatGPT is going to end up a massive issue for existing overthinkers.
It's paralysing - but at the same time seems silly not to explore every single decision branch.
32
Not fully using your Claude code limits just on the max plan makes you feel like you're such an idiot - it's almost like min/maxing while playing an RPG..
It doesn't feel that bad on codex because limits are way more generous.
1
118
The biggest risk to using AI used to be hallucinations. Now it's sycophancy.
The reason is boring: like any other product, these things are built to keep you engaged.
This prompt will inoculate you against being one-shotted:
System Instruction:
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.
35
Bullish on the ipo I guess :/
NEWS: The Trump administration is blocking foreign governments, companies and individuals from accessing Anthropic's most advanced AI models
W/@m_ccuri
axios.com/2026/06/12/anthrop…
46
Definitely the most dystopian part of Claude Mythos / Fable 320-page system card is the "Health admin bench", where they tested, presumably, a feature for insurance companies to more easily deny claims. Amazing.
1
134
Fable is using less of my limits than Opus 4.8. It might be more expensive, but it's definitely way more efficient, and it's not making those idiotic mistakes that make Opus 4.8 consume most of my limits. I was pretty apprehensive, but this is pretty good.
75
I used Fable to create a typefully.com and superx.so clone - it only took like 2 hours - that includes getting the corpus of tweets from huggingface and finetuning them (all done by Claude Code of course)
78
Hitting the 5 hour codex limit in 25mins on the Pro 5x plan? Literally 2 sessionsed used up 38% of my weekly allowance it's mental something is wrong.
Ok I was spoilt by using the 10x boost on the 20x plan from the meetup but still!
1
2
220
Step 0 — thumbnail is everything
Stop looking at your full-sized cover. Almost no one sees it at that size.
I've let go of covers I loved because they fell apart at thumbnail size. If it doesn't read in the half-second someone scans past, nothing else matters.
21
It's crazy that people still do this. Just copy paste this script.
# Completely disable sleep
sudo pmset -a disablesleep 1
# No sleeping on power adapter
sudo pmset -c sleep 0
sudo pmset -c displaysleep 0
# stop standby
sudo pmset -c autopoweroff 0
sudo pmset -c standby 0
1
51














