Matumeister

1K posts

Matumeister

@matumeister

Curious engineer building stuff with AI. https://t.co/AoHX5nFiLC - find meme clips https://t.co/F8kacLrqKZ - AI native video editor in browser

building 👉 Katılım Mart 2025

245 Takip Edilen117 Takipçiler

Sabitlenmiş Tweet

Matumeister@matumeister·15 Mar

￣￣￣￣￣￣￣￣￣￣￣￣￣￣￣￣| | Vibe coding drains your IQ | |＿＿＿＿＿＿＿＿＿＿＿＿＿＿＿＿| \ (•◡•) / \ / —— | | _| |_

English

1.8K

Matumeister@matumeister·14h

@ryantalks1024 Let’s goooo

English

Ryan@ryantalks1024·14h

@matumeister This is a big deal!!! Huge win 😃

English

Matumeister@matumeister·15h

first 10 google search clicks 🥳 everybody needs to start somewhere

English

Matumeister@matumeister·6d

@AlexeyBalchunas I’m using both posthog and cloudflare to measure the traffic, works really nice I think around 3-4 months when I started to notice that

English

Aleksei Balchunas@AlexeyBalchunas·6d

@matumeister Oh, I did not know this. I assumed healthy SEO was enough - I will try it. How long did it take before ChatGPT started recommending you, and how are you measuring the traffic?

English

Matumeister@matumeister·6d

ChatGPT just recommended my video editor as its #1 pick. here's exactly what I did back in January: 1. added an llms.txt, a plain markdown file describing the product: features, pricing, tech stack, who it's for 2. added JSON-LD (SoftwareApplication + FAQPage) 3. rewrote the meta tags to say what the app actually does. deleted the fluff, even downgraded "4K" to 1080p because that's the truth ChatGPT describes Bernini as "AI agents edit timeline via prompts/MCP". that's not my tagline. it's lifted straight from the file I wrote for it. LLMs can't rank what they can't parse. give them something quotable and they'll quote it. Link to chat below 👇

English

Matumeister@matumeister·6d

Link to the chat: chatgpt.com/share/6a5a063d…

English

Matumeister@matumeister·14 Tem

trying to put a ps1 vibe version of Fletcher's face onto a blender model so far not getting the best results 😂

English

Matumeister@matumeister·13 Tem

I'm quite impressed with this psx shader and burning animation created with @threejs and Fable 5 + GPT 5.6 gonna experiment some more :D

English

1.2K

Matumeister@matumeister·7 Tem

@codedgar_dev Damn this looks amazing

English

Codedgar@codedgar_dev·3 Tem

wip of a threejs psx shader im working on :D

English

144

7.9K

Matumeister@matumeister·4 Tem

8d33ef08-befc-4a17-a7bd-7b5fd4d4678f -> Session ID

English

Matumeister@matumeister·4 Tem

Fable just burned my $100 5h limit in 17 minutes This actually feels crazy and more like another caching/billing bug 🥲 @trq212 Anyone else experienced something similar?

English

Matumeister@matumeister·13 Haz

@AnthropicAI @kentcdodds

GIF

QME

Anthropic@AnthropicAI·13 Haz

The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, including foreign national Anthropic employees. The net effect of this order is that we must abruptly disable Fable 5 and Mythos 5 for all our customers to ensure compliance. Access to all other Claude models is not affected. We apologize for this disruption to our customers. We believe this is a misunderstanding and are working to restore access as soon as possible. Read our full statement: anthropic.com/news/fable-myt…

English

12.5K

25.6K

88K

92.8M

Matumeister@matumeister·12 Haz

@tadasgedgaudas Fable produces much better polished and unique UI imo

English

TadasG 💻@tadasgedgaudas·12 Haz

idk about you guys but for me GPT 5.5 > Fable 5 for coding Fable 5 just does stuff that is way too over engineered

English

529

Matumeister@matumeister·16 May

@TJGameDev Looks lovely!

English

TJ - Making Tabletop Tavern@TJGameDev·15 May

It's finally happening. Tabletop Tavern launches June 11th! A medieval RTS roguelite I've been building solo since the pandemic. Total War scale battles, Slay the Spire run structure, one satisfying run per sitting. May your ale stay full and your enemies distant 🍻

English

154

589

9.5K

786.6K

Matumeister@matumeister·14 May

@IntCyberDigest Mythos is cooking

English

385

International Cyber Digest@IntCyberDigest·14 May

‼️🚨 MAJOR IMPACT: AI just found an 18-year-old NGINX critical remote code execution vulnerability. It has been disclosed on GitHub including PoC code. - Affects NGINX 0.6.27 through 1.30.0 - Triggered via the rewrite and set directives in config - Update NGINX ASAP - NGINX is a widely used HTTP web server, be sure to check its prevalence in other products

English

390

2.6K

952K

Matumeister@matumeister·22 Nis

You can't change the model in Claude Code if you're out of quota

English

Matumeister@matumeister·22 Nis

@krzyzanowskim Comic tragedy

English

Marcin Krzyzanowski@krzyzanowskim·21 Nis

Mythos can find all critical issues in the world. except at Anthropic, this one is impossible

Cyber Security News@The_Cyber_News

⚠️ Critical Anthropic’s MCP Vulnerability Enables Remote Code Execution Attacks Source: cybersecuritynews.com/anthropics-mcp… A critical flaw in Anthropic’s Model Context Protocol (MCP) exposes over 150 million downloads to potential compromise. The vulnerability could enable full system takeover across up to 200,000 servers. Unlike a traditional coding bug, this vulnerability is architectural, meaning any developer building on Anthropic's MCP foundation unknowingly inherits the exposure from the ground up. The flaw enables Arbitrary Command Execution (RCE) on any system running a vulnerable MCP implementation. Successful exploitation grants attackers direct access to sensitive user data, internal databases, API keys, and chat histories, effectively handing over complete control of the affected environment. #cybersecuritynews

English

115

1.6K

125.7K

Matumeister@matumeister·8 Nis

@klattkev @threejs Oh wow, the car drives so good! Great job 👏

English

Kevin Klatt@klattkev·7 Nis

GTA 6 if Rockstar had a $10 budget #crooktown #threejs #gamedev

English

244

27.5K

Matumeister@matumeister·23 Mar

@BradGroux @AnthropicAI I thought it was problem with tool calling on my custom mcp server, but seems like it’s w bigger issue 🥲

English

134

Brad Groux@BradGroux·23 Mar

Something is up with Claude Code usage today. $200 Claude Max, 0%, 52% to 62%, then 68%, 76% and 84% in 5-hour rolling window in the time it took me to write this tweet. WTF, @AnthropicAI? I'm working on one GitHub PR for regression testing. Not folding proteins to cure cancer.