dr.dimitru

@upen946 ostr.io — web services

@sflorimm Isn’t it called game of life

The simple secret to startups: don't die

@sflorimm Maybe… elaborate how it’s on your end

Anyone else found that working with AI agents is more mentally tiring than just doing the work yourself?

@brodieseo Bing had it for a while. I still don’t see this option in my GSC 😩 wish to compare

Massive SEO News: Google is launching the most requested report in Google Search Console ever. A new AI performance report! Here's what we know so far: • It will include dedicated reports for both Search and Discover • The data will be reflected within Search for AI Overviews and AI Mode, alongside AI features in Discover • The report will only be focused on impressions within generative AI features, not clicks • The rollout will start with a subset of websites, allowing thorough testing (so keep an eye out!) There are some major limitations to this initial testing phase, where the actual queries that users are searching won't show in the report, with only impressions for pages, countries, devices, and dates. Though the dataset will be limited, this is certainly a step in the right direction! I will be covering this rollout within my newsletter, so make sure to subscribe if you aren't already: serpalert.com

@naturedotcom Go sleep at sunrise and wake up with sunset

Give me the worst advice you can👇

@kaaaash____ Code? We are all vibin’ here

Be honest, How many hours you code daily??

@ViperChill Went to check for this new section, where do I find or enable it?

Woah. Quite a few limitations at first (no clicks, limited rollout) but this is a step in the right direction. Very cool. More details over here: developers.google.com/search/blog/20…

Are we doing well?

@suni_code ostr.io get me roasted

Drop your SaaS and I will rate it out of 10

@tommithetechie Best keyboard ever

From dial-up screeches and Y2K countdowns to flip phones taking over the world to today’s AI tsunami (disaster?) reshaping everything… I’ve been on every wave. But I keep coming back to retro tech. Even when I was a child, I was fascinated by tech history, and I still am.

@dark_coderz - started with: Notepad++ on win - then Espresso by MacRabbit once I got my first Mac in 2010 - then Sublime Text for at least 15 years - now Cursor is my driver

Your first code editor says a lot about when you started coding Be honest: Where did you write your first "Hello, World!"? Drop it below 👇

@nezbuilds ostr.io — web services from SEO to Analytics

Good morning builders 👋 It’s Wednesday, time to show the internet what you’ve been building. Drop your project + a short description below. I’ll be checking out projects, giving feedback and connecting with fellow founders throughout the day 👇

@sflorimm Mate, that hurts 😬😩

your obsession with clean code is why your competitors shipped the ugly version that actually works while you’re still refactoring

@DanielSmidstrup Got to live sometimes

@smart_egg What is a break=???=?=

Founders, what do u do when Claude hits limits?

@catalinmpit Damn… free rent and cheap food. Where’s tax line? How big of a cut do they take? Remove loans, buy cheap car instead of loan, and it will be very efficient

My monthly expenses living in Romania: - Rent: $0 - Electricity: ~$200 - Internet/mobile: ~$30-$35 - Groceries: ~$600 - Car lease: $700 (need to get rid of it asap) - Loans: ~$550-$700 - Software/subscriptions: ~$390 - Food delivery/restaurants: ~$250 Average total is $2800. And a big chunk of the remaining money are eaten by Romanian taxes (annoying) and house building.

@sflorimm My max is 8 on local dev

Does anyone actually run 10 agents in parallel?

@sflorimm It’s coming 😬

they shipped Opus 4.8 no drop GPT-5.6

@sflorimm For real

$200 AI plans will become the minimum very soon

@siya_twt_ Yes, but we all hyped before 5.6 release

Be honest, is Claude better than Codex?

@acadictive Codex, Claude, Cursor/Composer are all great with tight GH integration

I feel so betrayed by GitHub Copilot. Since June 1, they changed their pricing model, and based on my tests, the same tasks now cost roughly 20–25× more. Goodbye GitHub Copilot. Hello ___?

I used 4.6 and 4.7 always on “max” reasoning level. So many things have changed in 4.8, it glitched and though for hours on ”max”, so I had to try “xhigh” and then actually go to “high” as the default recommended reasoning level now. Since then I have good quality back and speed meets my expectations. Not sure if it’s good or bad, but these little readjustments take a lot of time when new release/model is out