DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
The Handoff Is Where Agents Break
prpatel05 profile

The Handoff Is Where Agents Break

#agents #ai #architecture #llm
Comments
6 min read
QUASAR: How Saliency-Weighted Reconstruction Closes the Loss Floor Gap in LLM Quantization-Aware Training
prabhakar_chaudhary_7afe4 profile

QUASAR: How Saliency-Weighted Reconstruction Closes the Loss Floor Gap in LLM Quantization-Aware Training

#machinelearning #deeplearning #llm #python
Comments
5 min read
Hotel Data vs E-commerce Data: Why They're Nothing Alike
iamthedev profile

Hotel Data vs E-commerce Data: Why They're Nothing Alike

#agents #architecture #data #llm
1
Comments 2
9 min read
8 Papers on the Agent Harness Progress You Need to Know
hyperai profile

8 Papers on the Agent Harness Progress You Need to Know

#ai #machinelearning #agents #llm
1
Comments 1
3 min read
A Rule Can Be Specific and Still Be Too Broad
debashish_ghosal profile

A Rule Can Be Specific and Still Be Too Broad

#ai #llm #broad #testing
12
Comments 3
10 min read
CĂłmo integrar un LLM (Claude o GPT) en tu aplicaciĂłn Python
isazajuancarlos profile

CĂłmo integrar un LLM (Claude o GPT) en tu aplicaciĂłn Python

#ai #python #llm
Comments
2 min read
git blame Told Me I Wrote 767 Lines I Didn't Write
lexosi profile
Lex

git blame Told Me I Wrote 767 Lines I Didn't Write

#ai #git #llm #agents
4
Comments 5
9 min read
I built a RAG evaluation tool that catches failures RAGAS misses
abdullah_sethi_a9ac97879e profile

I built a RAG evaluation tool that catches failures RAGAS misses

#rag #llm #fastapi #react
Comments
2 min read
Building a Multi-Signal Renewal-Risk Workflow with n8n, Deterministic Scoring, and a Dual-LLM Audit
mychelgarzon profile

Building a Multi-Signal Renewal-Risk Workflow with n8n, Deterministic Scoring, and a Dual-LLM Audit

#ai #automation #llm #python
Comments
5 min read
Your LLM Skill can't do astronomy: why packaged divination Skills compute the wrong answer
shanni profile

Your LLM Skill can't do astronomy: why packaged divination Skills compute the wrong answer

#llm #ai #architecture #typescript
1
Comments
8 min read
Zhipu va ouvrir les poids du meilleur chasseur de failles
thibault_monteiro profile

Zhipu va ouvrir les poids du meilleur chasseur de failles

#ai #cybersecurity #llm #opensource
Comments
5 min read
Zero to Verified: A Free Coding Model Tutorial
devgo_5325 profile

Zero to Verified: A Free Coding Model Tutorial

#ai #llm #python #tutorial
1
Comments
4 min read
One terminal, two trust levels — running Claude Code against a real subscription and a cheap proxy
mediblacksand_f0ea36c53fb profile

One terminal, two trust levels — running Claude Code against a real subscription and a cheap proxy

#ai #claudecode #llm #devops
Comments
4 min read
The Bottleneck Moved From Writing Code to Proving It
debashish_ghosal profile

The Bottleneck Moved From Writing Code to Proving It

#ai #llm #programming #testing
20
Comments 5
4 min read
AI Mental Health Support: What a New Audit Found in Long Conversations
tahiralmas profile

AI Mental Health Support: What a New Audit Found in Long Conversations

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