Forem

# llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
ChatGPT Thought 'Suspicious' but Wrote 'Unlikely'
odakin profile

ChatGPT Thought 'Suspicious' but Wrote 'Unlikely'

#ai #chatgpt #llm #prompt
1
Comments
4 min read
TCI Toolkit: Real-time stability metric + live dashboard for persistent LLM agents
Cover image for TCI Toolkit: Real-time stability metric + live dashboard for persistent LLM agents
nilegreen profile

TCI Toolkit: Real-time stability metric + live dashboard for persistent LLM agents

#ai #opensource #llm #agents
Comments
1 min read
Skill to make you slow, but to go fast
kination profile

Skill to make you slow, but to go fast

#llm #skill #development
Comments
3 min read
Deepseek v4 Flash, Gemma/Qwen KV Cache Quantization & 384K Context
soytuber profile
soy

Deepseek v4 Flash, Gemma/Qwen KV Cache Quantization & 384K Context

#ai #llm #selfhosted
Comments 1
3 min read
An Empty AI Response Corrupted Chat History
jurijtokarski profile

An Empty AI Response Corrupted Chat History

#ai #gemini #javascript #llm
1
Comments
4 min read
Context Engineering for Developers: A Practical Guide (2026)
Cover image for Context Engineering for Developers: A Practical Guide (2026)
amitba profile

Context Engineering for Developers: A Practical Guide (2026)

#ai #developers #llm #devex
1
Comments 2
16 min read
The MCP Discovery Problem: Why 7,500+ Servers Is Both a Victory and a Warning
Cover image for The MCP Discovery Problem: Why 7,500+ Servers Is Both a Victory and a Warning
codemalasartes profile

The MCP Discovery Problem: Why 7,500+ Servers Is Both a Victory and a Warning

#ai #llm #mcp #tooling
Comments 7
3 min read
Why Your LLM Probably Has a PII Problem (And How to Fix It)
Cover image for Why Your LLM Probably Has a PII Problem (And How to Fix It)
coridev profile

Why Your LLM Probably Has a PII Problem (And How to Fix It)

#ai #webdev #llm #infosec
2
Comments 2
4 min read
How Do You Know Your AI Is Actually Good? A Guide to LLM Evaluation
Cover image for How Do You Know Your AI Is Actually Good? A Guide to LLM Evaluation
obila34 profile

How Do You Know Your AI Is Actually Good? A Guide to LLM Evaluation

#ai #llm #testing #tutorial
Comments
8 min read
Ten CLAUDE.md rules for Claude Code - four edit-time, six runtime
reneza profile

Ten CLAUDE.md rules for Claude Code - four edit-time, six runtime

#ai #llm #productivity #tutorial
7
Comments 1
3 min read
Oh My Opencode Specialised Agents Deep Dive and Model Guide
rosgluk profile
Rost

Oh My Opencode Specialised Agents Deep Dive and Model Guide

#selfhosting #llm #ai #aicoding
Comments
15 min read
Kimi K3 Is Coming — Here's How to Prep Your Code Today
Cover image for Kimi K3 Is Coming — Here's How to Prep Your Code Today
tokenmixai profile

Kimi K3 Is Coming — Here's How to Prep Your Code Today

#ai #llm #python #opensource
5
Comments 1
6 min read
Building AI Agents in 2026: Templates, Evaluation, and Production Lessons
extebarrri profile

Building AI Agents in 2026: Templates, Evaluation, and Production Lessons

#ai #agents #llm #javascript
Comments
2 min read
A $0.25 model beat a $3 model -- with better context
Cover image for A $0.25 model beat a $3 model -- with better context
kenimo49 profile

A $0.25 model beat a $3 model -- with better context

#ai #llm #rag #contextengineering
Comments
7 min read
How Do You Know Your AI Is Actually Good? A Guide to LLM Evaluation
Cover image for How Do You Know Your AI Is Actually Good? A Guide to LLM Evaluation
obila34 profile

How Do You Know Your AI Is Actually Good? A Guide to LLM Evaluation

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