Forem

Artificial Intelligence

Artificial intelligence leverages computers and machines to mimic the problem-solving and decision-making capabilities found in humans and in nature.

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Transformer - Encoder Deep Dive - Part 3: What is Self-Attention
iamyuvaraj profile

Transformer - Encoder Deep Dive - Part 3: What is Self-Attention

#ai #architecture #machinelearning #deeplearning
3
Comments 1
9 min read
Edge AI Inference: Goldmine of Compute, or Management Black Hole?
skyguan92 profile

Edge AI Inference: Goldmine of Compute, or Management Black Hole?

#ai #edgecomputing #infrastructure
1
Comments
4 min read
Building Intelligent Retail Signage with BrightSign's NPU: A Deep Dive into Real-Time Gaze Detection
lherlein profile

Building Intelligent Retail Signage with BrightSign's NPU: A Deep Dive into Real-Time Gaze Detection

#brightsign #ai #npu #techdemo
Comments
5 min read
Run Claude Code on AWS with Amazon Bedrock: Credits, Costs, and Claude Platform on AWS
Cover image for Run Claude Code on AWS with Amazon Bedrock: Credits, Costs, and Claude Platform on AWS
pabloin profile

Run Claude Code on AWS with Amazon Bedrock: Credits, Costs, and Claude Platform on AWS

#ai #aws #development #bedrock
5
Comments
7 min read
I built an open-source tool that lets AI agents hire real humans to test your product
Cover image for I built an open-source tool that lets AI agents hire real humans to test your product
reallizhi profile

I built an open-source tool that lets AI agents hire real humans to test your product

#opensource #ai #testing #webdev
5
Comments 2
3 min read
Import Your AI Memory into ContextForge: Claude Code, ChatGPT, and Knowledge Graph
alfredoizjr profile

Import Your AI Memory into ContextForge: Claude Code, ChatGPT, and Knowledge Graph

#ai #programming #claudecode #chatgpt
1
Comments
3 min read
The Sandboxed "Ralph Wiggum" Loop: Securely Letting Agents Fix Code Until Tests Pass
Cover image for The Sandboxed "Ralph Wiggum" Loop: Securely Letting Agents Fix Code Until Tests Pass
kowshik_jallipalli_a7e0a5 profile

The Sandboxed "Ralph Wiggum" Loop: Securely Letting Agents Fix Code Until Tests Pass

#ai #agents #code #programming
1
Comments
4 min read
How do you know the software is working?
marostr profile

How do you know the software is working?

#ruby #rails #ai #webdev
Comments
6 min read
Why a 4B Parameter Model Now Beats GPT-3.5 — The 4 Techniques Behind Small Model Revolution
ji_ai profile

Why a 4B Parameter Model Now Beats GPT-3.5 — The 4 Techniques Behind Small Model Revolution

#ai #machinelearning #llm #programming
Comments
8 min read
I Compressed a 14GB Model to 3.5GB and Kept 95% of Its Quality — Here's How
ji_ai profile

I Compressed a 14GB Model to 3.5GB and Kept 95% of Its Quality — Here's How

#ai #machinelearning #programming #tutorial
Comments
4 min read
Single-Pass RAG Is Dead — Here's What Replaced It in 2026
ji_ai profile

Single-Pass RAG Is Dead — Here's What Replaced It in 2026

#ai #beginners #rag #llm
Comments
5 min read
REST API Generator with Spring Boot and Spring AI
rrezart_prebreza profile

REST API Generator with Spring Boot and Spring AI

#ai #api #java #springboot
3
Comments
1 min read
Building a Personal Health Agent with LangGraph: From Blood Tests to Pharmacy Checkouts
beck_moulton profile

Building a Personal Health Agent with LangGraph: From Blood Tests to Pharmacy Checkouts

#ai #python #productivity #devops
Comments
3 min read
Top 7 LLM Observability Tools in 2026: Which One Actually Fits Your Stack?
thedailyagent profile

Top 7 LLM Observability Tools in 2026: Which One Actually Fits Your Stack?

#ai #llm #devops #productivity
Comments 1
5 min read
This AI Spent 28 Minutes Thinking Before Answering — And Got It Right
ji_ai profile

This AI Spent 28 Minutes Thinking Before Answering — And Got It Right

#ai #llm #machinelearning #programming
Comments
4 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.