Hacker, entrepreneur. Founder & CEO at helix.ml.
- Show HN: MCP server to index external repositories
by lewq on 6/10/25, 10:30 PM, with comments
- What R1 means for enterprise GenAI
by lewq on 1/29/25, 4:56 PM, with comments
- Running GenAI on Supercomputers: Bridging HPC and Modern AI Infrastructure
by lewq on 12/20/24, 10:51 AM, with comments
- GPTScript working with function calling on local Llama3.3:70B
by lewq on 12/19/24, 5:27 PM, with comments
- Building a Local LLM-Powered Kubernetes Debugger
by lewq on 12/9/24, 2:23 PM, with comments
- Test Driven Development (TDD) for your LLMs? Yes please, more of that please
by lewq on 12/4/24, 2:42 PM, with comments
- From ClickOps to GitOps: The Evolution of AI App Development
by lewq on 11/21/24, 12:22 PM, with comments
- Building in the Open: Revenue and Pipeline for Private GenAI
by lewq on 11/20/24, 3:28 PM, with comments
- The barriers to AI engineering are crumbling fast
by lewq on 11/14/24, 2:56 PM, with comments
- In which I nearly fuck up our product strategy
by lewq on 11/12/24, 7:22 PM, with comments
- CI/CD for cloud-native GenAI reference architecture
by lewq on 11/12/24, 2:40 PM, with comments
- Fuck OpenAI, DIY with open source models
by lewq on 9/5/24, 4:01 PM, with comments
- Helix 1.0 is multi-node Ollama with a version controlled app layer
by lewq on 9/5/24, 3:52 PM, with comments
- Show HN: Local "GPTs" with Knowledge and API calling, one-liner install
by lewq on 9/5/24, 3:38 PM, with comments
- Show HN: Helix apply -f deploy YAML GenAI with RAG and APIs on local open models [video]
by lewq on 8/26/24, 4:33 PM, with comments
- AISpec: Declarative config for LLM app patterns?
by lewq on 7/5/24, 5:47 AM, with comments
- Can we help you build an AI App?
by lewq on 7/3/24, 3:30 PM, with comments
- RAG, fine-tuning, API calling and gptscript for Llama 3 running locally
by lewq on 5/24/24, 3:54 PM, with comments
- Show HN: Smart website search powered by open models
by lewq on 5/15/24, 7:03 PM, with comments
- Deploy gptscript to prod with 'git push'
by lewq on 4/21/24, 8:11 PM, with comments
- Bootstrapped SaaS startup: New limits on fine tuning on Helix free plan
by lewq on 4/13/24, 6:40 AM, with comments
- How we got fine-tuning Mistral-7B to not suck
by lewq on 2/6/24, 7:12 AM, with comments
- Type error in AI? Can models be intelligent or are they the same thing as maps?
by lewq on 12/31/23, 7:34 PM, with comments
- UI for fine tuning Mistral and SDXL, GPU mem/latency optimization
by lewq on 12/24/23, 6:26 PM, with comments
- Show HN: Local fine tuning for Mistral and SDXL, GPU mem/latency optimization
by lewq on 12/21/23, 8:13 PM, with comments
- Understanding classifier-free guidance for style transfer
by lewq on 3/7/23, 6:38 PM, with comments