Zac Siegel
@zsiegel.com
Software Wizard. Writing about and building with Kotlin and Ollama AI models http://zsiegel.com http://youtube.com/@zsiegel87
Inspiring weekend cooking with Claude Code. Sharing some thoughts after spending $37 in tokens and building the beginning of my "personal" MCP server.
zsiegel.com/why-2025-fee...
zsiegel.com/why-2025-fee...
Why 2025 Feels Like 2005: AI and the Rebirth of Personal Computing
The release of Claude Code and other advanced AI software development tools marks a pivotal moment in personal computing—one that feels remarkably similar to the Web 2.0 revolution of the mid-2000s.
...
zsiegel.com
May 26, 2025 at 2:35 AM
Inspiring weekend cooking with Claude Code. Sharing some thoughts after spending $37 in tokens and building the beginning of my "personal" MCP server.
zsiegel.com/why-2025-fee...
zsiegel.com/why-2025-fee...
Really enjoyed this podcast with one of the founders of @tailscale.com
stratechery.com/2025/an-inte...
stratechery.com/2025/an-inte...
An Interview with Tailscale Co-Founder and CEO Avery Pennarun
An interview with Tailscale CEO and co-founder Avery Pennarun about Tailscale, and how he’s been learning to build a New Internet his whole life.
stratechery.com
March 16, 2025 at 1:56 AM
Really enjoyed this podcast with one of the founders of @tailscale.com
stratechery.com/2025/an-inte...
stratechery.com/2025/an-inte...
Spent some time recreating GPT alongside the video from @karpathy.bsky.social using the Apple MLX machine learning framework.
I found it to be a fun exercise and learned a ton!
github.com/zsiegel/mlx-...
I found it to be a fun exercise and learned a ton!
github.com/zsiegel/mlx-...
GitHub - zsiegel/mlx-gpt: Recreate GPT with Apple MLX framework guided by Andrej Karpathy
Recreate GPT with Apple MLX framework guided by Andrej Karpathy - zsiegel/mlx-gpt
github.com
January 29, 2025 at 3:11 AM
Spent some time recreating GPT alongside the video from @karpathy.bsky.social using the Apple MLX machine learning framework.
I found it to be a fun exercise and learned a ton!
github.com/zsiegel/mlx-...
I found it to be a fun exercise and learned a ton!
github.com/zsiegel/mlx-...
Reposted by Zac Siegel
🐋 Alert! DeepSeek Janus-Pro-7B
It’s multimodal and outperforms Dalle-E and StableDiffusion
Probably the biggest feature is it’s ability to generate text in an image that actually makes sense
They be cooking, I’m here for whatever is served
huggingface.co/deepseek-ai/...
It’s multimodal and outperforms Dalle-E and StableDiffusion
Probably the biggest feature is it’s ability to generate text in an image that actually makes sense
They be cooking, I’m here for whatever is served
huggingface.co/deepseek-ai/...
January 27, 2025 at 8:41 PM
🐋 Alert! DeepSeek Janus-Pro-7B
It’s multimodal and outperforms Dalle-E and StableDiffusion
Probably the biggest feature is it’s ability to generate text in an image that actually makes sense
They be cooking, I’m here for whatever is served
huggingface.co/deepseek-ai/...
It’s multimodal and outperforms Dalle-E and StableDiffusion
Probably the biggest feature is it’s ability to generate text in an image that actually makes sense
They be cooking, I’m here for whatever is served
huggingface.co/deepseek-ai/...
Anyone with experience using n8n or langchain?
Looking to run my own self hosted system for automations and agents. Seems like n8n has all the right integrations and then langchain has more AI sauce. Thoughts?
Looking to run my own self hosted system for automations and agents. Seems like n8n has all the right integrations and then langchain has more AI sauce. Thoughts?
January 26, 2025 at 3:37 AM
Anyone with experience using n8n or langchain?
Looking to run my own self hosted system for automations and agents. Seems like n8n has all the right integrations and then langchain has more AI sauce. Thoughts?
Looking to run my own self hosted system for automations and agents. Seems like n8n has all the right integrations and then langchain has more AI sauce. Thoughts?
The biggest difference I notice when using deepseek-r1 for coding tasks is that it examines and uses existing code so much better than previous LLMs.
That is a massive win for most developers who are working in existing large codebases.
That is a massive win for most developers who are working in existing large codebases.
January 25, 2025 at 7:13 PM
The biggest difference I notice when using deepseek-r1 for coding tasks is that it examines and uses existing code so much better than previous LLMs.
That is a massive win for most developers who are working in existing large codebases.
That is a massive win for most developers who are working in existing large codebases.
The extra money spent on 64GB ram on my M4 Max is very well spent.
Being able to run larger LLM models locally via Ollama for code assistance is wonderful.
Qwen coder and Deepseek R1 are both excellent for my daily use cases.
Being able to run larger LLM models locally via Ollama for code assistance is wonderful.
Qwen coder and Deepseek R1 are both excellent for my daily use cases.
January 25, 2025 at 2:24 AM
The extra money spent on 64GB ram on my M4 Max is very well spent.
Being able to run larger LLM models locally via Ollama for code assistance is wonderful.
Qwen coder and Deepseek R1 are both excellent for my daily use cases.
Being able to run larger LLM models locally via Ollama for code assistance is wonderful.
Qwen coder and Deepseek R1 are both excellent for my daily use cases.
Been debugging an issue for 48 where our apps built from CI pipelines break at runtime. But when we push to the App Store manually via a local machine it works.
Finally realized our CI machines are running a different version of Xcode than what we all are developing on. 🫠🫠🫠
Finally realized our CI machines are running a different version of Xcode than what we all are developing on. 🫠🫠🫠
January 25, 2025 at 2:22 AM
Been debugging an issue for 48 where our apps built from CI pipelines break at runtime. But when we push to the App Store manually via a local machine it works.
Finally realized our CI machines are running a different version of Xcode than what we all are developing on. 🫠🫠🫠
Finally realized our CI machines are running a different version of Xcode than what we all are developing on. 🫠🫠🫠
Been polishing up a "home AI" project that lets me use Llama 3.2 using Ollama to find anything in my personal documents.
Been a fun project trying out OCR tech, LLM tool calling, and different kinds of search and RAG techniques!
Been a fun project trying out OCR tech, LLM tool calling, and different kinds of search and RAG techniques!
January 19, 2025 at 1:11 AM
Been polishing up a "home AI" project that lets me use Llama 3.2 using Ollama to find anything in my personal documents.
Been a fun project trying out OCR tech, LLM tool calling, and different kinds of search and RAG techniques!
Been a fun project trying out OCR tech, LLM tool calling, and different kinds of search and RAG techniques!