Ask HN: What's Your Useful Local LLM Stack?

16 Jul 2025

🧠 Hacker News Digest: AI, Prompt Engineering & Dev Trends

Welcome! This article summarizes high-impact discussions from Hacker News, focusing on AI, ChatGPT, prompt engineering, and developer tools.

Curated for clarity and relevance, each post offers a unique viewpoint worth exploring.

📋 What’s Included:

  • Grouped insights from Hacker News on Prompt Engineering, AI Trends, Tools, and Use Cases
  • Summarized content in original words
  • Proper attribution: 'As posted by username'
  • Code snippets included where relevant
  • Direct link to each original Hacker News post
  • Clean HTML formatting only

🗣️ Post 1: Ask HN: What's Your Useful Local LLM Stack?

As posted by: Olshansky  |  🔥 Points: 66

https://news.ycombinator.com/item?id=44572043

💬 Summary

What I’m asking HN:

What does your actually useful local LLM stack look like?

I’m looking for something that provides you with real value — not just a sexy demo.

---

After a recent internet outage, I realized I need a local LLM setup as a backup — not just for experimentation and fun.

My daily (remote) LLM stack:

  - Claude Max ($100/mo): My go-to for pair programming. Heavy user of both the Claude web and desktop clients.

  - Windsurf Pro ($15/mo): Love the multi-line autocomplete and how it uses clipboard/context awareness.

  - ChatGPT Plus ($20/mo): My rubber duck, editor, and ideation partner. I use it for everything except code.

Here’s what I’ve cobbled together for my local stack so far:

Tools

  - Ollama: for running models locally

  - Aider: Claude-code-style CLI interface

  - VSCode w/ continue.dev extension: local chat & autocomplete

Models

  - Chat: llama3.1:latest

  - Autocomplete: Qwen2.5 Coder 1.5B

  - Coding/Editing: deepseek-coder-v2:16b

Things I’m not worried about:

  - CPU/Memory (running on an M1 MacBook)

  - Cost (within reason)

  - Data privacy / being trained on (not trying to start a philosophical debate here)

I am worried about:

  - Actual usefulness (i.e. “vibes”)

  - Ease of use (tools that fit with my muscle memory)

  - Correctness (not benchmarks)

  - Latency & speed

Right now: I’ve got it working. I could make a slick demo. But it’s not actually useful yet.

---

Who I am

  - CTO of a small startup (5 amazing engineers)

  - 20 years of coding (since I was 13)

  - Ex-big tech

🗣️ Post 2: Unlike ChatGPT, Anthropic has doubled down on Artifacts

As posted by: bewal416  |  🔥 Points: 49

https://ben-mini.com/2025/claude-is-kicking-chatgpts-butt

💬 Summary

Back in high school, I remember receiving an email for a study guide from a friend. Instead of the PDF coming attached, it was a link to a site called Dropbox. Upon opening the file, you create an account. From there you’re introduced to a feature stack that went well beyond any typical PDF: shared collaboration, comments, version history… the benefits of cloud computing- all within the familiarity of a PDF! Dropbox achieved strong network effects in the 2010s due to generous free tiers, easy file sharing, and one-click account creation. Last year, I wrote a blog post on network effects, guessing if (and how) they would be brought into the AI market. In the post, I argued two points:...

🗣️ Post 3: Billionaires Convince Themselves Chatbots Close to Making Scientific Discoveries

As posted by: maartenscholl  |  🔥 Points: 16

https://gizmodo.com/billionaires-convince-themselves-ai-is-close-to-making-new-scientific-discoveries-2000629060

💬 Summary

Generative artificial intelligence tools like ChatGPT, Gemini, and Grok have exploded in popularity as AI becomes mainstream. These tools don’t have the ability to make new scientific discoveries on their own, but billionaires are convinced that AI is on the cusp of doing just that. And the latest episode of the All-In podcast helps explain why these guys think AI is extremely close to revolutionizing scientific knowledge. Travis Kalanick, the founder of Uber who no longer works at the company, appeared on All-In to talk with hosts Jason Calacanis and Chamath Palihapitiya about the future of technology. When the topic turned to AI, Kalanick discussed how he uses xAI’s Grok, which went haywire last week, praising Adolf Hitler and advocating...

🗣️ Post 4: The campaign to make it illegal for ChatGPT to criticize Trump

As posted by: wredcoll  |  🔥 Points: 5

https://www.platformer.news/andrew-bailey-chatgpt-trump-jawboning-legal-case/

💬 Summary

The conservative pressure campaign against social networks was hugely successful — and now it's coming for AI This is a column about AI. My boyfriend works at Anthropic. See my full ethics disclosure here . Today, let’s talk about a prediction that came true. In December, as we looked ahead to the first year of the new Trump Administration, I forecast a new wave of political pressure on AI companies. “The first Trump presidency was defined by near-daily tantrums from conservatives alleging bias in social networks, culminating in a series of profoundly stupid hearings and no new laws,” I wrote . “Look for these tantrums (and hearings) to return next year, as Republicans in Congress begin to scrutinize the center-left...

🗣️ Post 5: ChatGPT made up a product feature out of thin air, so this company created it

As posted by: Stratoscope  |  🔥 Points: 5

https://arstechnica.com/ai/2025/07/chatgpt-made-up-a-product-feature-out-of-thin-air-so-this-company-created-it/

💬 Summary

On Monday, sheet music platform Soundslice says it developed a new feature after discovering that ChatGPT was incorrectly telling users the service could import ASCII tablature—a text-based guitar notation format the company had never supported. The incident reportedly marks what might be the first case of a business building functionality in direct response to an AI model's confabulation. Typically, Soundslice digitizes sheet music from photos or PDFs and syncs the notation with audio or video recordings, allowing musicians to see the music scroll by as they hear it played. The platform also includes tools for slowing down playback and practicing difficult passages. Adrian Holovaty, co-founder of Soundslice, wrote in a blog post that the recent feature development process began as...

🎯 Final Takeaways

These discussions reveal how developers think about emerging AI trends, tool usage, and practical innovation. Take inspiration from these community insights to level up your own development or prompt workflows.