I Know My LLM - Thanks!
Manifesto for spotting AI hype
What it does
A community-driven AI manifesto with 8 actionable principles for evaluating AI platforms. Evidence over promises, transparency over hype. Join the trustworthy AI community.
Does the same job
all alternatives →- AMAI ManifestoJun 2026 · danstroot.com · ▲5
With massive respect to Jeff Sutherland and all the thought leaders who met at a ski lodge in Snowbird, Utah, in 2001 and created the Agile Manifesto - it might be time to revisit / refresh / revitalize the Agile Manifesto in light of the emergence of LLMs. The scarce resource is no longer programming capacity, but organizational clarity and architectural coherence. As a thought exercise (and for fun) I took a stab at it. I would love to get some collaborative feedback to improve it. Of course I do not expect this to replace the Agile Manifesto but I'd like to use it when speaking…
- NHNo Hype AI – get oriented in using LLM tools for software engineering2025 · nohypeai.dev · ▲9
Hey HN! When I started looking into LLMs and agents for software development and introducing them at work, I quickly realised that a person new to the topic faces a real barrage: - all the hype (AGI, engineers getting replaced by AI etc.) - conflicting opinions in virtually every discussion—for every person saying they’ve 10x-ed their productivity, there is a comment decrying LLMs as an utter failure - a lot of jargon (MoE, MCP, RAG, distillation, quantisation etc. etc.) - a profusion of models, IDEs/IDE extensions, CLI agents, other tools etc. Sorting through all of this can be quite…
- IBI build a dedicated news site for AI developers (think HN for AI/ML)2023 · news.aiapipro.com · ▲8
Think of HackerNews, but only for AI content. Did build this out of the wish for easier discoverability of new technologies in the AI/ML space. Obviously, so far only a tiny small community, but maybe a few of you find it nice to be around and want to post a link there every now and then :)
- KAKnowing – an LLM tool built on concept hierarchies, not prompt-response2024 · ▲5
Hey HN! I've spent the past year full-time building Knowing, a tool for interacting with LLMs directly inside hierarchical structures instead of the usual prompt-response format. The idea started because I realized how much more intuitive it felt to build concept hierarchies continuously—no more endless copy-pasting or wondering how everything connects. The journey’s been a struggle. While I see huge potential in structuring AI interactions this way (writing books fast, planning projects, or organizing ideas), it’s been hard to pin down clear use cases in the market. I’m also working in near…
- AAAn addendum to the Agile Manifesto for the AI eraMar 2026 · github.com · ▲7
I'm a VP of Engineering with 20 years in the field. I've been thinking deeply on why AI is breaking every engineering practice, and it led me to the conclusion that the Agile Manifesto's values need updating. The core argument: AI made producing software cheap, but understanding it is still expensive. The Manifesto optimizes for the former. This addendum shifts the emphasis toward the latter. Four updated values, three refined principles, with reasoning for each. Happy to discuss and defend any of it.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
