Spyros Stylianou

61 posts

Spyros Stylianou

@conspyrosy

scaling vibecoding and sharing my learnings

Katılım Şubat 2026

108 Takip Edilen40 Takipçiler

Sabitlenmiş Tweet

Spyros Stylianou@conspyrosy·8 Şub

FrankenTUI by @doodlestein is fast! Here's the binance BTC perps orderbook + trades + chart. Video is 60fps which doesn't do it justice

Jeffrey Emanuel@doodlestein

It has been an extremely active 24 hours for FrankenTUI development, with countless new features and functionality added (including massive numbers of tests and verifications). Have you ever seen a terminal like this? Because I know I haven't! Can't wait to start building stuff!

English

349

Spyros Stylianou@conspyrosy·11h

@SteveFlanders22 study FTX TRUMP tokens

English

657

Steve@SteveFlanders22·11h

i am still waiting for someone to explain how perps could work for prediction markets funding rates fundamentally do not work with prediction markets. there is no rate to make someone take an obviously losing side, and there’s definitely no rate that will keep them in the position through resolution for the book, the result is you get absolutely fucked

Astaria@AstariaTrade

x.com/i/article/2051…

English

1.8K

Spyros Stylianou@conspyrosy·1d

time to say goodbye to @claudeai after using it daily for the last 6 months, unusable. 👋

English

Spyros Stylianou@conspyrosy·23 Nis

@charlieholtz alright, might be time to give this another go after uninstalling

English

Charlie Holtz@charlieholtz·23 Nis

We've re-built Conductor from scratch to make it twice as fast. Creating tabs, switching workspaces, and rendering files are all 50% faster, memory usage is lower, and the app is 150 MB smaller. Introducing Conductor Allegro!

English

167

227.2K

Spyros Stylianou@conspyrosy·11 Nis

@cryptopunk7213 now i think about it, culture has parallels to an llm. its basically just the consensus behaviour in a society. societal norms the same - the accepted default behaviour. a normie = consensus being (determistic)

English

Spyros Stylianou@conspyrosy·11 Nis

@cryptopunk7213 what if, culturally, we behave non deterministically because we live in a people-driven world. but moving into a post-AI world, we start to behave deterministically. you already see this somewhat since the internet - culture transcends borders and we're all kind of blending.

English

Ejaaz@cryptopunk7213·11 Nis

the fear around AI is overblown something that makes me certain AI isn’t going to replace us is non-determinism: ai and robots are (for better or worse) deterministic creatures. no matter how “human” they appear - there’s always a binary(ish) outcome. humans are built different. you never know our next move or what we’re thinking. that gives us a sense of hope that theres a way (however small) that we can create the reality we desire and i think that’s fucking beautiful 🤷🏽

Sam Altman@sama

I wrote this early this morning and I wasn't sure if I would actually publish it, but here it is: blog.samaltman.com/2279512

English

4.5K

Spyros Stylianou@conspyrosy·3 Nis

@devjoshstevens @Polymarket fix the nonce issue. DM'd you

English

Josh@devjoshstevens·24 Mar

Excited to join @Polymarket as VP of Engineering. I haven’t seen a hungrier team in my career, the talent density here is insane. We’re building the future of how people understand the world. What should we build next? What’s broken? What’s missing? Drop it below. P.s we are hiring world class people in NYC DMs open

English

324

1.2K

255.6K

Spyros Stylianou@conspyrosy·31 Mar

@doodlestein a huge whitepill for everyone else is that a multi-billion dollar company is making schoolboy errors like this. you're probably overthinking everything, get to work.

English

369

Jeffrey Emanuel@doodlestein·31 Mar

It’s such a blackpill for computer security that Anthropic can have the best security people on staff and still have the complete source to their Crown Jewel closed-source project leaked accidentally. And now it’s just out there, doesn’t matter how many lawyer letters they send.

CG@cgtwts

That “someone at Anthropic” might be the best security researcher we have right now > his name is nicholas carlini and he works there > he’s known for breaking AI systems instead of just building them > he previously worked at Google, testing how reliable machine learning really is > he showed that even the smartest AI can be fooled by tiny, invisible changes > at anthropic, he now focuses on stress testing powerful models before they reach the real world > he looks for subtle failures, edge cases, and ways these systems can be misused > his work uncovers risks that aren’t obvious at first glance > he helped pioneer adversarial attacks, a core field in AI safety he focuses on making powerful AI systems safer.

English

148

21.5K

Spyros Stylianou@conspyrosy·27 Mar

by "coding" i mean babysitting ai

English

Spyros Stylianou@conspyrosy·27 Mar

coding after 1 beer is bliss

English

Spyros Stylianou@conspyrosy·23 Mar

@robj3d3 My family is cypriot, have some great memories holidaying there when younger. The best european food there is as well in my opinion (italy close second)

English

103

Rob Hallam@robj3d3·23 Mar

I just moved to Cyprus 🇨🇾 My first impressions and why I moved: > it's safe (unlike rest of Europe) > friendly people (unlike rest of Europe) > quiet > clean air > fast WiFi > tax friendly > great coffee > amazing food > very walkable > incredible weather > affordable (€2 for coffee, €7 for meal) > great laptop cafe culture (unlike rest of Europe) > growing tech scene (unlike rest of Europe) It's been so long since I had somewhere I could lock in from and call home. I was torn between UAE and Cyprus but the last month made my decision for me. And so far I am so happy with my decision.

English

601

152

3.2K

1.1M

Spyros Stylianou@conspyrosy·10 Mar

me in the passenger seat of a `claude --dangerously-skip-permissions` session while he viciously refactors a codebase

Wholesome Side of 𝕏@itsme_urstruly

Bro pulled off the best video of his life

English

Spyros Stylianou@conspyrosy·26 Şub

Huge arbitrage on Polymarket / Kalshi for this market. Very sus. looks like someone is sponsoring rewards on polymarket and going to burn some farmers

English

Spyros Stylianou@conspyrosy·25 Şub

@eptwts

QME

EP@eptwts·24 Şub

openclaw getting so popular among normies is so stupid considering most people haven't even made $1k online... tell me what tf a person with ZERO experience is supposed to be automating? if you are not in a position where hiring a REAL assistant is a profitable decision, openclaw probably won't be profitable for you either

English

256

19K

Spyros Stylianou@conspyrosy·25 Şub

@BeyerSebastian @kr0der how did you infer this from the OP? you don't write tests to test the amount of prisma queries you're doing. the result is correct with terrible performance

English

Sebastian Beyer@BeyerSebastian·23 Şub

@kr0der From reading this one could assume there is 0 tests in the code base. Is this true?

English

125

Anthony Kroeger@kr0der·23 Şub

this is apparently an unpopular opinion nowadays: you should always review all code AI writes unless it's a prototype/you know it's throwaway code. there's a few reasons: 1. AI writes far from perfect code. for example, the amount of times i've seen a prisma findUnique inside a loop, or a promise.all with like 100 prisma queries, is way too common to be unreviewed. 2. it's the main thing that lets you retain context of your codebase. i'm sure you've experienced this, and so have i - your project gets too big and you need to make changes. your prompts slowly get more vague each time because you have no idea what's in there anymore and what detail to add. 3. if you have users, then i think it's important to review the code to prevent bugs. this is especially important if you have enterprise customers where a number of huge bugs can cause them to churn to a competitor. let me know your thoughts 👀

English

106

21K

Spyros Stylianou@conspyrosy·23 Şub

@AlexFinn

QME

213

Alex Finn@AlexFinn·23 Şub

Mac Minis sold out everywhere. Mac Studios sold out everywhere Its obvious whats happening right now People are realizing you can run Opus level intelligence locally on a single Mac Studio. I'm doing it right now. Qwen3.5 has been coding for me quite literally for 24 hours straight. No interruptions or rate limits. $248 in token savings Apple releasing updates to make this faster and more efficient nonstop People don't want to build computers part by part. They want to buy one beautiful computer, turn it on, load super intelligence, plug it into OpenClaw and change their lives M5 Ultra will only accelerate this It's that simple And as more people realize this, the more unobtainable these computers will get The future has arrived. People are only just starting to realize it

English

241

1.1K

128.8K

Spyros Stylianou@conspyrosy·22 Şub

@doodlestein gaslighting with a sprinkle of belief

English

297

Jeffrey Emanuel@doodlestein·22 Şub

This prompt is somewhat cruel to the clanker, but man does it work. It sort of reminds me of Joe McCarthy waving his list of communists working in the government but never showing it to anyone. If the agent believes there are bugs to find and fix, it will keep working until it finds them: "I know for a fact that there are at least 87 serious bugs throughout this project impacting every facet of its operation. The question is whether you can find and diagnose and fix all of them autonomously. I believe in you."

English

170

15.3K

Spyros Stylianou@conspyrosy·21 Şub

@turingou git: github.com/guo-yu/skills/…

Spyros Stylianou@conspyrosy·21 Şub

Great skill if you're working on multiple worktrees/projects. Reserves 10 consecutive ports so there's no conflicts and agents don't end up killing eachothers processes. by @turingou