Mădălin Ignișca (@MadalinIgnisca) header
Mădălin Ignișca (@MadalinIgnisca) profile picture

Solutions builder, empowering small businesses and public sector, with custom solutions. Building in public, also.

United States of Europe
Joined April 2009
Photo by Mădălin Ignișca (@MadalinIgnisca)Photo by Mădălin Ignișca (@MadalinIgnisca)Photo by Mădălin Ignișca (@MadalinIgnisca)Photo by Mădălin Ignișca (@MadalinIgnisca)Photo by Mădălin Ignișca (@MadalinIgnisca)Photo by Mădălin Ignișca (@MadalinIgnisca)Photo by Mădălin Ignișca (@MadalinIgnisca)Photo by Mădălin Ignișca (@MadalinIgnisca)Photo by Mădălin Ignișca (@MadalinIgnisca)Photo by Mădălin Ignișca (@MadalinIgnisca)
The licensing for a tv show or movie to be available in a country or not, it is the most anti-consumer stupid thing the gangs owning them set against us. This must end. I see a tv show, available in US on Netflix, but in Canada, EU, Australia, no. IDIOTS!
11
Using AI, it is not mandatory to use Artificial Intelligence. It can be using An Idiot too.
7
I ride with Fable 5 since last night and damn is good. Now, let's make money :-D Thank you all people from @AnthropicAI !!! cc @ClaudeDevs @claudeai
22
This morning I was reading some random post by somebody, saying that ChatGPT 5.5 felt like it's the first to match Opus 4.7... Well, right now I'm using Opus 4.8 and for sure I don't want the less powerful ChatGPT 5.5... #claude #ai #chatgpt
1
48
Let's see what's new in @Xcode
1
2
27
I can confirm, @claudeai #Opus 4.7 with 1M context working in @Xcode. What I was waiting for. Thanks @Apple , thanks @AnthropicAI
1
24
Poor @gitlab . Somebody give them some cents to pay for recaptcha...
1
38
Mădălin Ignișca retweeted
Memory on Claude Managed Agents is now in public beta. Your agents can now learn from every session, using an intelligence-optimized memory layer that balances performance with flexibility.
369
591
137
9,009
656,626
2026/2027 goal: Build, launch and maintain 5 mobile apps that do each: Minimum 5000 subscribers with minimum 5$/€ per year spending each. Apps must be simple, focused and do exactly what the user expects, and nothing more. #buildinpublic #apps4people
22
I think that it is OK that @claudeai has issues sometimes. It forces me to take a break, walk the dog that was staring at me for 2h now... 500 errors should be acceptable every 50 minutes for 10 minutes for the physical help of users.
28
So OpenAI's 5h limits are so small compared to Gemini that literally it makes me wonder if it worths to pay the subscription. Disclosure: _read the comments for disclosure_ #ai #vibecoding #BuildingInPublic #ClaudeCode #codex #GeminiAI
1
46
Codex? One trial, and I exhausted allowance of 5h... And I'm not even putting it to hard work, it only triggers reviews for 2 parallel repositories with a commit every 40-50 minutes...
1
22
Conclusion? #GeminiAI provided for more or less same amount of spending way more value and help for me to work compared to #codex Maybe @OpenAIDevs @OpenAI should review their limits compared to the competition as it's the worse in the AI big league.
28
COMPLETE SECURITY SCANNING TYPES: #GITHUB & #GITLAB A merged, deduplicated list of all security scanning capabilities available across both platforms, with recommended open source tools for each scan type. madalin.me/complete-security…
27