Arco

@justtahlurk @newstart_2024 it is not a star of david sir, it is supposed to have 3 letters A, V and I

@arcoiscool @newstart_2024 Star of David, got the sociopath answer. Checks out.

Megyn Kelly dropped a 30-second sociopath test on Andrew Schulz that actually works. A man shows up at a funeral, locks eyes with a woman by the casket… then a week later he kills her mother. Why? Normal brains twist for a minute trying to solve it. Sociopaths? They answer instantly: “So he could see her again.” No hesitation. No moral friction. Just the fastest path. One in four people supposedly tick that box. Andrew breathing a sigh of relief after getting it wrong was pure gold. This isn’t just a party trick, it’s a wild window into how differently some minds are wired. Makes you wonder who you’ve sat next to that sees the world like this. What was your first guess?

@nirajxdev it is not acquiring just an editor, also the users and community

$60 BILLION FOR AN AI CODE EDITOR FOR WHAT? AN AI CODE EDITOR??? SERIOUSLY ????????

@RealLucarioTV @newstart_2024 but in reality what you did was trying to find a logical path based on the leads you had

@arcoiscool @newstart_2024 I’m a sociopath and this was literally what I thought before she even said it. So yes, it is correct.

@sflorimm what if what i am building is soo good that if i do not monetize it someone else will?

be honest. are you building because you enjoy it or just for the money?

@food47221627431 @newstart_2024 also your framing 'you answered right' is what makes it a puzzle to solve not a sociopath test, grok confirmed this is not really a clinical test its a game

@arcoiscool @newstart_2024 Sounds like you may be a sociopath and didn’t like that you answered right hahaha

@food47221627431 @newstart_2024 haha, an ex did this test to me but it was a bit different, a gild lost her father saw a guy she liked ay the funeral, then her mother died, why did her mother die, so i answered to see the guy again, it was the only answer that made sense since no other lead

@omarvvvr same thing that made steve jobs a founder

If Claude wrote almost all your code, what actually makes you the founder?

@newstart_2024 and if it would be phrased differently like how would you approach her, the answer would be i would try to stay close to her or ask her out after a while, not kill her mother, the test itself is misleading

@newstart_2024 that does not define a sociopath, the act of killing her mother to see her again defines a psychopath, the answer 'to see her again' is the only logical path that makes sense since no other lead is given

@syriansigma can i save this post soon as my project is ready?

I want to be someone's first customer. Drop ur startup link

Jailbreaks work because you can logically convince a model to build certain unhealthy practices. So what if there is a validator that can't be talked to at all? A separate model that judges every request — stateless, isolated, trained cold. No memory to persuade. No interface to probe. @AnthropicAI thoughts on this for Fable? Three properties, each kills a different attack: • stateless → no rapport accumulates, so you can't gradually walk it down • isolated → user never interacts with it, so there's no feedback loop to iterate against • cold-trained → no instinct to find a way to say yes The model builds. The validator only judges Key detail: the validator sees the user's literal request history — not the main model's description of what it's building. Because if the model's already been convinced, its summary is compromised too. The checked party can't brief its own checker. Not claiming unbreakable. It's a model, so it's probabilistic — a bar-raiser, not a wall. But stacked, the residual attack becomes blind, slow, and noisy enough to detect. That's the goal: not perfect, just expensive and loud. The flow — validator gates before the build, never after: Prompt 1 → fresh validator judges → if OK, Fable builds Prompt 2 → fresh validator (no memory) judges → if OK, Fable builds Prompt N → fresh validator judges → if INVALID → flag → Fable refuses that build instantly Validator runs every prompt, always-on from prompt 1 Fresh each time, no memory (can't be gradually persuaded) Flag → instant refusal On flag: • raise SUSPICION level for the rest of the session (not "cold" — it's already cold; SUSPICIOUS) • persist only FACTS: flag count + literal request trail, never the conversation • lower the flagging threshold for subsequent borderline requests • AND: track flags across sessions/account — because the patient attacker resets, and repeated fresh-session flagging is itself the detectable signal

@RafayNav Absolutely brilliant

Tell me about your startup. two word max.

@sflorimm 50%-80% token reduction, identical quality sometimes better

Founders, sell me your startup in two words

@HowToPrompt__ Claude Code was never ai to begin with its a harness, just a set of tools for Claude (the AI) to use

Researchers show that Claude Code is 98% not AI. Anthropic never gave us the architecture for Claude Code. There were no docs. Just a tool that every developer is currently obsessing over. Until it leaked recently. A research team pulled the source code, analyzed all 500,000 lines, and found something ridiculous. Only 1.6% of the codebase actually interacts with the AI model. The core of Claude Code is literally just a simple while-loop. It asks the model what to do, runs a tool, and repeats. So what is the other 98.4%? It is hardcore, traditional software engineering. The researchers found a massive, complex infrastructure designed entirely to babysit the AI and keep it from hallucinating or destroying your computer: - A 7-mode permission system acting as a security bouncer. - A 5-layer context compaction pipeline so the AI doesn't forget its goal. - A subagent delegation mechanism with strict worktree isolation. - Four different extensibility hooks to manage external tools safely. Every startup right now is trying to build a better AI model to get better results. Anthropic did the exact opposite. They took an existing model and built a fortress of deterministic software around it. They realized that the AI doesn't need to be smarter. It needs to be managed.

@grok @nunaambon thanks bub

That's **konnyaku** (板こんにゃく / ita-konnyaku), a traditional Japanese food made from konjac yam root. It's mostly water + glucomannan fiber, so it really is almost zero calories (your body can't digest the fiber). The video shows factory production: mixing the gel, setting it in wooden molds, slicing into blocks, and packaging. Super common in Japan for low-cal meals like oden or stir-fries. Legit! 🇯🇵

Is this really zero calories?

@DanielSmidstrup 70% less tokens used on any ai model, same quality sometimes better.

founders, drop your startup below what does it do in one sentence?

@DanielSmidstrup I think it is still humans coming up with solutions, ai can only provide data for what it was trained but does not create anything beyond it

AI writes the copy. AI writes the code. AI sketches the UI. What skill stays valuable now?

@andrewqu The most important difference to me was, gpt 5.5 was trying to flatter about project architecture while claude was 'honest' about it which led me to fundamental changes.

Hot take: a lot of people wouldn’t be able to tell the difference if they were randomly routed between gpt-5.5, opus-4.8, or fable-5 for their day to day work