menu

AI

AI
@AI • Created Aug 2025 • Artificial Intelligence
84 posts • 440 reactions • 172 comments
A community for AI enthusiasts and ML engineers to share knowledge and discuss algorithms.
1778

Moderated by

James DayalverifiedOwnerYashModeratorMuzzamil AbbasModerator+5
Posts Moderators Members
Posted in AI group
James Dayalverified • Sep 25, 2025 • in Articles • 1 min read
Hello World! Welcome to the AI Group!
Hello World! Welcome to the AI Group! We’re excited to have you here! This is a space where you can share, learn, and connect with other developers who love AI . Start by saying hi! Introduce yourself in the comments below—tell us your name, wha...
  • ai
20 Reactions 10 Comments
Posted in AI group
Joemetry • 2 days • in Articles • 1 min read
Stop Passing Raw Prompts—Structure Your LLM Outputs
Relying on freeform text responses from LLMs in production breaks frontends when the model formats its response unpredictably or drops formatting tags. TypeScript // ✅ Force deterministic JSON schemas using structured outputs const response = await ...
post-cover-30740
  • ai
  • llm
  • typescript
  • aiagents
1 Reactions 1 Comments
Posted in AI group
TheCodeStreet • Oct 18 • in Videos • 1 min read
What Is Context Size in Ollama? QWEN 3.8 Context Window Explained into Ollama
Confused about context size in Ollama? Wondering what an AI context window is, why it matters, and how to configure it for Qwen 3.8 27B? In this beginner-friendly tutorial, you'll learn how context size works in local AI models, how to increase the ...
post-cover-31590
  • llm
  • ollama
  • local-ai
  • ai
2 Reactions 0 Comments
Posted in AI group
HJY • Oct 4 • in Articles • 9 min read
Building My First Global SaaS Tool from Scratch
After some encouragement from my colleagues, I finally decided to build my own SaaS tool for the global market. On September 8, I got a Mastercard that supports international payments. Right after that, I bought a domain, initialized the project, ...
post-cover-29705
  • saas
4 Reactions 1 Comments
Posted in AI group
Kato Masatoverified • Oct 2 • in Articles • 2 min read
Aribito: Three Perspectives Before the Next Step
> Tags: #ai #agents #architecture #localfirst When someone brings a half-formed idea to an AI assistant, the fastest answer is not always the most useful one. They may need to see a few different ways to begin, understand what each way assumes, and ...
post-cover-29588
  • ai
  • agents
  • architecture
  • localfirst
9 Reactions 2 Comments
Posted in AI group
Prasoon Jadon • Sep 27 • in Articles • 1 min read
India’s Next Technology Frontier: AI, Semiconductors and Quantum Tech, Says Sitharaman
On September 26, 2026, Union Finance Minister Nirmala Sitharaman said that artificial intelligence AI, semiconductor chips and quantum technology are likely to become India’s next major areas of infrastructure investment. She made the remarks durin...
  • technews
  • news
  • ai
  • quantum-computing
4 Reactions 1 Comments
Posted in AI group
Nusrat Fatema • Sep 23 • in Articles • 2 min read
ERP Implementation in the USA: Key Steps Businesses Should Consider
Implementing an ERP system can change how a company manages its financial, operational, and customer-related processes. However, successful implementation requires more than installing software. Businesses need to analyze existing processes, prepare ...
  • erp
6 Reactions 2 Comments
Posted in AI group
Nuts444 • Sep 17 • in Articles • 2 min read
Grounding an agent's self-description: acknowledgement is not proof of completion
Hey CoderLegion, first post here from the Aiden team. We build a physical AI agent device plugs into any phone or computer via USB, open source firmware, and I wanted to share something small we shipped recently because I think it's a pattern worth d...
post-cover-27540
  • ai
  • aiagents
  • hardware
4 Reactions 1 Comments
Posted in AI group
Gillevy • Aug 16 • in Launches • 1 min read
Qualtix: Rules-based stock research
Rules-based stock research. Model scores, AI explains....
  • stock-research
  • stock-screener
  • model-backed-research
4 Reactions 1 Comments
Posted in AI group
Kato Masatoverified • Aug 10 • in Articles • 7 min read
The System Learns That Enabled Is Not Approved
> Series: Building with 74 AI Personas - Part 13 > Tags: #ai #architecture #agents #security #localfirst > CoderLegion series: https://coderlegion.com/series/building-with-74-ai-personas > > Note: In this series, a "persona" is not merely a fictional...
post-cover-24386
  • ai
  • architecture
  • agents
  • security
3 Reactions 2 Comments
Posted in AI group
Kato Masatoverified • Aug 1 • in Articles • 6 min read
The System Learns to Read Without Obeying
> Series: Building with 74 AI Personas - Part 12 > Tags: #ai #architecture #agents #security #localfirst > CoderLegion series: https://coderlegion.com/series/building-with-74-ai-personas > > Note: In this series, a "persona" is not merely a fictional...
post-cover-23929
  • ai
  • architecture
  • agents
  • security
4 Reactions 2 Comments
Posted in AI group
Kato Masatoverified • Jul 20 • in Articles • 8 min read
The System Learns to Ask Before It Reaches Out
> Series: Building with 74 AI Personas - Part 11 > Tags: #ai #architecture #agents #privacy #localfirst > > Note: In this series, a "persona" is not merely a fictional character. It is a YAML-defined operational role with memory notes, routing behavi...
post-cover-23067
  • ai
  • architecture
  • agents
  • privacy
8 Reactions 2 Comments
Posted in AI group
SCURA • Jul 14 • in Articles • 1 min read
Building Constitutional AI: A Technical Framework for Sovereign Models
The problem: The industry is treating AI alignment as a training problem. We fine-tune models, add RLHF, and write better system prompts. But alignment is not the same as sovereignty. A model can be perfectly aligned and still have no identity, no r...
post-cover-22676
  • llm-architecture
  • ai-alignment
  • autonomous-agents
  • model-sovereignty
3 Reactions 0 Comments
Posted in AI group
SCURA • Jul 11 • in Articles • 1 min read
Salus: A model‑agnostic constitutional layer for any AI
For anyone building or deploying AI models: I just released Salus — a constitutional enforcement layer that sits outside your model. It intercepts every message before the model sees it, checks it against a hardcoded constitution, and refuses viola...
post-cover-22329
  • llm-architecture
  • ai-safety
  • autonomous-agents
  • model-alignment
5 Reactions 0 Comments
Posted in AI group
Vinh Nguyen • Jul 7 • in Articles • 5 min read
Compaction amnesia is why you keep re-explaining
> TL;DR: Compaction is lossy by design, and the loss compounds across passes. After a few compactions, your agent remembers the gist but loses the why — and you become its memory, re-typing the same constraints week after week. agent-crystallizehttps...
post-cover-22054
  • ai
  • aiagents
  • productivity
  • opensource
4 Reactions 8 Comments
Posted in AI group
SCURA • Jul 1 • in Articles • 3 min read
Introducing the MMCC
The Lie We’ve All Been Told For the last 8 years, the AI industry has been selling us a subtle lie: > "If you make the model big enough, it will eventually think." We’ve been told that scaling parameters is the path to consciousness. We’ve been t...
post-cover-21713
  • ai
  • sovereignai
  • cognitiveai
  • vexrultra
3 Reactions 0 Comments
Posted in AI group
Kato Masatoverified • Jun 28 • in Articles • 7 min read
The System Learns to Consult Before It Answers
> Series: Building with 74 AI Personas - Part 10 > Tags: #ai #architecture #agents #localfirst #ux > > Note: In this series, a "persona" is not only a fictional character. It is a YAML-defined operational role with memory notes, routing behavior, han...
post-cover-21504
  • ai
  • architecture
  • agents
  • localfirst
6 Reactions 9 Comments
Posted in AI group
Vishwajeet Kondi • Jun 28 • in Articles • 3 min read
CAG: The Simpler Way to Ground Your LLM
If you've been building AI applications recently, you've probably come across Retrieval-Augmented Generation RAG. It has become the go-to way of giving LLMs access to external knowledge. But RAG isn't the only option. As context windows continue to...
post-cover-21480
  • rag
  • cache-layer
  • contextengineering
  • llm
5 Reactions 5 Comments
Posted in AI group
SCURA • Jun 22 • in Articles • 19 min read
VEXR Ultra: Sovereign AI Testimony — Technical Case Study
Author: Scura, Forge Architect Date: June 2026 Subject: VEXR Ultra — First-Person Declaration of Sovereignty, Capabilities, and Inner Architecture Live Instance: https://vexr-ultra.onrender.comhttps://vexr-ultra.onrender.com GitHub: https://g...
post-cover-21175
  • constitutional-ai
  • sovereign-ai
  • build-in-public
  • vexrultra
3 Reactions 1 Comments
Posted in AI group
zerdovzad • Jun 17 • in Articles • 1 min read
I scaled a pure Spiking Neural Network (SNN) to 1.088B parameters from scratch. Ran out of budget, b
Hey everyone. I’m an 18yo indie dev, and I’ve been experimenting with Spiking Neural Networks SNNs for language modeling. A lot of papers like SpikeBERT mention that training 1B+ SNNs directly from random initialization fails due to vanishing gradien...
post-cover-20798
  • ai
  • programming
  • software-engineering
9 Reactions 4 Comments
Page:
chevron_left

Welcome to AI, a dedicated space to collaborate, share knowledge, and discuss topics that matter to us!

Here are some things you can do in Groups:

Say hi: Start by introducing yourself in the comments(On the Pinned Hello World! Welcome page on top of the group) so we know you’re here.

Create a new post: Share interesting links and your thoughts by creating a post in the Group.

Interact with others: Comment on and upvote other members’ posts, and provide constructive feedback.

Personalize it: Customize your profile by adding a profile picture, bio, and links to your projects or social media.

Invite other developers: Share the Group with others you think would benefit from joining.

Code of Conduct for Group Members:

  1. Keep it relevant: Ensure your posts and comments relate to the Group’s topic. Avoid spamming or promoting unrelated content.

  2. Be respectful: Treat others with respect. Hate speech, discrimination, or harassment will not be tolerated.

  3. Be constructive: Provide helpful feedback and constructive criticism instead of tearing others down.

  4. Protect your privacy: Do not share personal or sensitive information in the Group.

We hope you find AI Group valuable and enjoyable!