Łazzar

Crypto investor, Big Data, BI enthusiast, Digitalisation Consultant, Entrepreneur. #Bitcoin, Ł,

[Łazzar @LM_22]

@mrVassil Baba Vanga nephew is Mr Vasil , bangaranga

[Łazzar @LM_22]

@DerekNee @thsottiaux Ping @thsottiaux please restore whatever done to 5.5 or codex. Last days mostly buggy code and simple errors, this is not what we signed for. I had a huge app which got bricked and codex won't fix anymore

[Łazzar @LM_22]

@mrVassil I smell unicorn idea... well done 👏 when I get old I will use it

[Łazzar @LM_22]

@steipete Damn I like your mind. I do hardening pass after each change, .... make QA audit bla vla after each major change. Make it happen. I have tokens:)

[Łazzar @LM_22]

@BostonDynamics Skynet I am here to serve you

[Łazzar @LM_22]

@iotcoi Lol mine Z8 overheating if max out, spent 4 hours today trying to disable Secure Boot, deadlock looping after power outage. I love it and I hate it. Cmos battery replacement is my last hope as Gemma REAP is cool brain for OCR operations

[Łazzar @LM_22]

@CaptainInsightX The 🐐 himself @ggerganov

[Captain Insight @CaptainInsightX]

The man who killed the $10,000 GPU myth.
He did it alone, from Bulgaria, with one C file. 🤯

>Meet Georgi Gerganov.

>Bulgarian developer. Nobody had heard of him.
>In March 2023, Meta’s LLaMA model leaked online
>Within days he wrote a single C file
>Called it llama.cpp
>It ran a full AI model on a MacBook. No GPU. No cloud.
>The entire AI industry said you needed $10,000 GPUs to run LLMs 🔥
>He proved you didn’t. On a laptop. Alone.
>Also built whisper.cpp ~ same thing for voice AI
> His code is the foundation of Ollama, LM Studio, and GPT4All
>107,000+ GitHub stars. Fastest open-source AI project to hit 100K ever. 🚀
>In 2026 Hugging Face hired his entire team
>Still ships code. Still open source. Still free.

Every time you run AI locally, you’re running his work.

Absolute Legend 🐐

[Łazzar @LM_22]

@NousResearch Whole day only hermes integrations unfortunately when context grow I see similar problems like class or agent zero but still best workhorse

[Łazzar @LM_22]

@OpenAI Here we go, .. refractory everything now, make no no mistakes

[OpenAI @OpenAI]

GPT-5.5 is rolling out today for Plus, Pro, Business and Enterprise users across ChatGPT and Codex.

We’re also introducing GPT-5.5 Pro for Pro, Business, and Enterprise users in ChatGPT.

[Łazzar @LM_22]

@iotcoi Common man Kimi, GLM, Qwen or Gemma... i am tired boss , too many too choose from...

[Łazzar @LM_22]

@abhitwt CORS

[Łazzar @LM_22]

@thsottiaux Computer use on windows please

[Łazzar @LM_22]

@alexwtlf Codex is a beast got pro and regret wasted time with Plus, it's worth it go give them the cash we need AGI in Codex

[Łazzar @LM_22]

@thsottiaux Just got pro as 2 plus were not not enough ;)

[Łazzar @LM_22]

@iotcoi Is it better than Gemma 26b?

[Łazzar @LM_22]

@NousResearch Hermes now lives inside dockerized app, as sentinel who sees and knows everything, accessible only via docker cli, soon orchestrate all agents itinerary app.... One will rule them all. Advise whis GUI is bet for Hermes or just to vibe into so TS chatbot interface.

[Łazzar @LM_22]

@iotcoi Master any hints how to solve reCaptcha without paid api?

[Łazzar @LM_22]

@guntherjourney @LottoLabs Results?