201–210 of 1001 posts
The language is heavily inspired by Python for the dev UX, and the interpreter is written in RPython (what Pypy uses). Rewriting to RPython was tedious, but the 80x speedup was worth it.
Chrome web store link: https://chromewebstore.google.com/detail/n8n-copilot-chat-wi...
Mostly writing for myself; I should really convert some drafts into proper blog posts because I'm really interested in discussing my ideas with others. I've been thinking a lot about the current field of AI research and wondering if we're asking the right questions? I've watched some videos from Yann LeCun where he highlights some of the key limitations of current approaches, but I haven't seen anyone discussing or s…
RAG and/or Fine-tuning is not the way.
Another topic is security, which would consist of using Ollama + Proxmox for example, but of course, right now, as emergent intelligence is still early, we would have to wait 2-3 years for ~8 B parameter local models to be as good as ChatGPT o3 pro or Claude Opus 4.
I do believe that we are close to discovering a new interface. What is now presenting itself through IDE’s and the command line (terminal)… I strongly believe we are 1-2 years away from a new kind of interface, that is not meant for developers only.
That feels like an IDE, works like a CLI, but is intuitive as Chrome is for browsing the web.
The thing is, we’ve been retrofitting software made for humans for machines, which creates unnecessary complications. It’s not about model capability, which is already there for most processes I have tested, it’s because systems designed for people are confusing to AI, do not fit their mental model, and making the proposition of relying on agents operating them a pipe dream from a reliability or success-rate perspective.
This led me to a realization: as agentic AI improves, companies need to be fully AI-native or lose to their more innovative competitors. Their edge will be granting AI agents access to their systems, or rather, leveraging systems that make life easy for their agents. So, focusing on greenfield SaaS projects/companies, I've been spending the last few weeks crafting building blocks for small to medium-sized businesses who want to be AI-native from the get-go. What began as an API-friendly ERP evolved into something much bigger, for example, cursor-like capabilities over multiple types of data (think semantic search on your codebase, but for any business data), or custom deep-search into the documentation of a product to answer a user question.
Now, an early version is powering my products, slashing implementation time by over 90%. I can launch a new product in hours supported by several internal agents, and my next focus is to possibly ship the first user-facing batch of agents this month to support these SaaS operations. A bit early to share something more concrete, but I hope by the next HN thread I will!
Happy to jam about these topics and the future of the agentic-driven economy, so feel free to hit me up!
Scrollable social network where the user generated content is microgames.
https://www.inclusivecolors.com/
The idea is it helps you create palettes that have predictable color contrast built-in, so when you're picking color pairs for your UI/web design later, it's easy to know which pairs have accessible color contrast.
For example, you can design your palette so that green-600, red-600, blue-600, all contrast against grey-50, and the same for any other 600 grade vs 50 grade color, like green-600 vs green-50.
That way you won't run into failing color contrast surprises later when you need e.g. an orange warning alert box (with different variations of orange for the background, border, heading text and body text), a red danger alert box, a green success alert box etc. against different color backgrounds.