Recent Posts

• Show HN: MCP server to index external repositories
  by lewqon 6/10/2025, 10:30:34 PM with 1 comment
• What R1 means for enterprise GenAI
  by lewqon 1/29/2025, 4:56:04 PM with 0 comments
• Running GenAI on Supercomputers: Bridging HPC and Modern AI Infrastructure
  by lewqon 12/20/2024, 10:51:46 AM with 0 comments
• GPTScript working with function calling on local Llama3.3:70B
  by lewqon 12/19/2024, 5:27:08 PM with 0 comments
• Building a Local LLM-Powered Kubernetes Debugger
  by lewqon 12/9/2024, 2:23:49 PM with 0 comments
• Test Driven Development (TDD) for your LLMs? Yes please, more of that please
  by lewqon 12/4/2024, 2:42:10 PM with 8 comments
• From ClickOps to GitOps: The Evolution of AI App Development
  by lewqon 11/21/2024, 12:22:38 PM with 1 comment
• Building in the Open: Revenue and Pipeline for Private GenAI
  by lewqon 11/20/2024, 3:28:28 PM with 0 comments
• The barriers to AI engineering are crumbling fast
  by lewqon 11/14/2024, 2:56:48 PM with 20 comments
• In which I nearly fuck up our product strategy
  by lewqon 11/12/2024, 7:22:26 PM with 1 comment
• CI/CD for cloud-native GenAI reference architecture
  by lewqon 11/12/2024, 2:40:07 PM with 0 comments
• Fuck OpenAI, DIY with open source models
  by lewqon 9/5/2024, 4:01:21 PM with 1 comment
• Helix 1.0 is multi-node Ollama with a version controlled app layer
  by lewqon 9/5/2024, 3:52:19 PM with 1 comment
• Show HN: Local "GPTs" with Knowledge and API calling, one-liner install
  by lewqon 9/5/2024, 3:38:27 PM with 0 comments
• Show HN: Helix apply -f deploy YAML GenAI with RAG and APIs on local open models [video]
  by lewqon 8/26/2024, 4:33:23 PM with 0 comments
• AISpec: Declarative config for LLM app patterns?
  by lewqon 7/5/2024, 5:47:37 AM with 3 comments
• Can we help you build an AI App?
  by lewqon 7/3/2024, 3:30:55 PM with 1 comment
• RAG, fine-tuning, API calling and gptscript for Llama 3 running locally
  by lewqon 5/24/2024, 3:54:39 PM with 5 comments
• Show HN: Smart website search powered by open models
  by lewqon 5/15/2024, 7:03:24 PM with 6 comments
• Deploy gptscript to prod with 'git push'
  by lewqon 4/21/2024, 8:11:07 PM with 1 comment
• Bootstrapped SaaS startup: New limits on fine tuning on Helix free plan
  by lewqon 4/13/2024, 6:40:35 AM with 0 comments
• How we got fine-tuning Mistral-7B to not suck
  by lewqon 2/6/2024, 7:12:19 AM with 12 comments
• Type error in AI? Can models be intelligent or are they the same thing as maps?
  by lewqon 12/31/2023, 7:34:34 PM with 2 comments
• UI for fine tuning Mistral and SDXL, GPU mem/latency optimization
  by lewqon 12/24/2023, 6:26:50 PM with 1 comment
• Show HN: Local fine tuning for Mistral and SDXL, GPU mem/latency optimization
  by lewqon 12/21/2023, 8:13:09 PM with 2 comments
• Understanding classifier-free guidance for style transfer
  by lewqon 3/7/2023, 6:38:58 PM with 5 comments