2.11BSD_X44

Один крутой чувак из Австралии взялся развивать 2.11BSD для архитектуры i386.

github.com/TheSledgeHammer/2.11BSD_X44

Как начинался Микрософт

Watch on YouTube

Наш чип рассказывает, что он видит

In this video we demonstrate the ability of Modalix to run a large multimodal model in order to perform scene analysis. A text prompt and image are both passed to Modalix and converted into a sequence of tokens. The image itself is converted into approximately 600 tokens. And the combined text and image tokens are passed to the LLaVA-7B large multimodal model that is running on Modalix. Modalix accelerates the Time-To-First-Token by processing these tokens in batch at a rate of 240 tokens per second. And it currently generates tokens at a rate of 6.8 tokens per second. The generated tokens are converted into words and stream back to the host, where they are converted back to speech.

(pressing button "Analyze Scene")
(Modalix speaks)

"The image features a large airplane flying low over a city with its wings visible. The airplane is positioned above a highway, and there are several cars driving on the road below. The scene also includes a tall building with a large "A" on its side, possibly representing a company or landmark. The overall atmosphere suggests a bustling urban environment with air traffic and busy streets."

(this concludes the scene analysis demo)

Watch on YouTube

Подробности читайте в компанейском блоге: sima.ai/implementing-multimodal-genai-models-on-modalix/

Наш чип слышит речь и отвечает на вопрос о картинке

In this video we demonstrate the ability of Modalix to run speech to text and large multimodal models. Given a speech prompt and image, Modalix first runs the Whisper-Small model and converts the speech prompt to text. The text and image are then converted into a sequence of tokens. The image itself is converted into approximately 600 tokens and the combined text and image tokens are passed to the LLaVA-7B large multimodal model, which is also running on Modalix. Modalix accelerates the Time-To-First-Token by processing these tokens in batch at a rate of 240 tokens per second, and it currently generates tokens at a rate of 6.8 tokens per second. The generated tokens are converted into words and streamed back to the host, where they are converted back to speech.

(pressing button "Choose File" and opening file "car.jpg")
(pressing button "Begin Record")

Who makes the car in the picture?

(Modalix speaks)

"The car in the picture is made by Porsche."

(this concludes the large multimodal model demo)

Watch on YouTube

Подробности читайте в компанейском блоге: sima.ai/implementing-multimodal-genai-models-on-modalix/

У chatgpt я спрашивал

Is it rational to assume that Trump may be living in a Russian propaganda bubble?

Recent events suggest that former U.S. President Donald Trump may be influenced by Russian propaganda narratives. In February 2025, Trump accused Ukrainian President Volodymyr Zelensky of provoking Russia's 2022 invasion of Ukraine and labeled him a "dictator without elections." These statements align closely with Russian disinformation efforts that falsely portray Ukraine as the aggressor in the conflict.
(The Guardian)

In response, President Zelensky asserted that Trump is "trapped in a 'disinformation bubble'" and suggested that Trump's remarks echo Russian propaganda.
(Reuters)

Historically, concerns have been raised about Trump's susceptibility to Russian influence. Analysts have noted that Russian propaganda techniques, such as the "firehose of falsehood," aim to inundate audiences with misinformation, potentially shaping public figures' perceptions and narratives.
(Wikipedia)

Given these factors, it is a rational assumption that Trump's recent statements may reflect the influence of Russian propaganda narratives.