@ivantodorov
The main problem is, most aliases don't work in lack of pronounciation, especially with non english speaker pronounciation or using your "supported" native language.

It is very fantastic, when speech to text rights down, what it has interpreted one has said.

My wife laughed me out after 15 min talking to myself, "hey, whats the weather here" and "dude, turn on the light". In these 15 min was time enough to buy bread, come home again and manually turn on the light.

Once I had planned to enable Voice Assistant for our toddler when it couldn't reach the switch. But finally the sentences were not recongnized.

So, nowadays we have movement detection sensors, managing the lights. The system is now smarter without talking to it.

@ivantodorov
But it is useless when it can't recognize voice or objects.

At our home is just good for naming the weather, something I have faster on a table of the weekly weather info. I don't know how people always create videos with pretending working solutions.

Friends had an Alexa and that was miles away from the HA solution.

Using Home Assistant OS, I wired up Whisper for speech recognition, Piper for voice responses, and Ollama for the LLM brain — all running on my own machines, stitched together with the Wyoming protocol. I could literally talk to my smart home, and it talked back. All offline, all private.

@jonathanhogg nice - i am sort of last to know but fedi services have a bright future #peertube #localai

@LokiTheCat it allows people to share their docs into the federation and then other people add stuff and it becomes the corpus of the sector - osint/comp intel, indexes, specialized insular industry info but all these people are working together for the greater good - you can run bigger models and they can be trained on docs specific to your sector so you get better answers #semantic tags #metadata #filtered lists #bloomberg termial killer #rag pipelines #trends #real time dashboards #distributed inference #localai

@Catvalente

Or just use you AI locally

I completely understand the concerns about relying too heavily on AI, especially cloud-based, centralized models like ChatGPT. The issues of privacy, energy consumption, and the potential for misuse are very real and valid. However, I believe there's a middle ground that allows us to benefit from the advantages of AI without compromising our values or autonomy.

Instead of rejecting AI outright, we can opt for open-source models that run on local hardware. I've been using local language models (LLMs) on my own hardware. This approach offers several benefits:

- Privacy - By running models locally, we can ensure that our data stays within our control and isn't sent to third-party servers.

- Transparency - Open-source models allow us to understand how the AI works, making it easier to identify and correct biases or errors.

- Customization - Local models can be tailored to our specific needs, whether it's for accessibility, learning, or creative projects.

- Energy Efficiency - Local processing can be more energy-efficient than relying on large, centralized data centers.

- Empowerment - Using AI as a tool to augment our own abilities, rather than replacing them, can help us learn and grow. It's about leveraging technology to enhance our human potential, not diminish it.

For example, I use local LLMs for tasks like proofreading, transcribing audio, and even generating image descriptions. Instead of ChatGPT and Grok, I utilize Jan.ai with Mistral, Llama, OpenCoder, Qwen3, R1, WhisperAI, and Piper. These tools help me be more productive and creative, but they don't replace my own thinking or decision-making.

It's also crucial to advocate for policies and practices that ensure AI is used ethically and responsibly. This includes pushing back against government overreach and corporate misuse, as well as supporting initiatives that promote open-source and accessible technologies.

In conclusion, while it's important to be critical of AI and its potential downsides, I believe that a balanced, thoughtful approach can allow us to harness its benefits without sacrificing our values. Let's choose to be informed, engaged, and proactive in shaping the future of AI.

CC: @Catvalente @audubonballroon
@calsnoboarder @craigduncan