DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
I built an answer key for eval suites: six models broken on purpose, exactly.
agentdev9 profile

I built an answer key for eval suites: six models broken on purpose, exactly.

#showdev #testing #llm #opensource
1
Comments
2 min read
What Changed in AI in the Last 90 Days (Quick Round-up)
viv_chaudhary profile

What Changed in AI in the Last 90 Days (Quick Round-up)

#ai #llm #productivity #machinelearning
Comments
5 min read
How to Build a No-Code AI Test Automation Agent Using RAG + Playwright MCP
rahul_sharma_pq profile

How to Build a No-Code AI Test Automation Agent Using RAG + Playwright MCP

#agents #ai #llm #testing
Comments
10 min read
The Requests library for AI one Unified Python SDK for every LLM provider
6t9 profile

The Requests library for AI one Unified Python SDK for every LLM provider

#ai #api #llm #python
Comments
7 min read
GPT-5.6 Luna à 1,40 $/M : on a migré une pipeline de classification, voici la facture
hernanz profile

GPT-5.6 Luna à 1,40 $/M : on a migré une pipeline de classification, voici la facture

#openai #python #llm #api
Comments
5 min read
Prompt Caching in LLMs, Measured on Our Own Bill
jula-markova profile

Prompt Caching in LLMs, Measured on Our Own Bill

#ai #llm #programming #devops
5
Comments 1
6 min read
AI's Worst Failure Mode Isn't Hallucination
max_quimby profile

AI's Worst Failure Mode Isn't Hallucination

#ai #machinelearning #programming #llm
1
Comments 1
10 min read
Run DeepSeek V4 Flash 0731 on Your Own Hardware: What It Takes
purpledoubled profile

Run DeepSeek V4 Flash 0731 on Your Own Hardware: What It Takes

#ai #llm #opensource #tutorial
Comments
2 min read
DeepSeek V4 Flash vs V4 Pro: A Developer Decision Guide
purpledoubled profile

DeepSeek V4 Flash vs V4 Pro: A Developer Decision Guide

#ai #llm #opensource #productivity
Comments
2 min read
Your agent's failed traces are wasted fine-tuning data
wane_hong_ff200a8f78f5d46 profile

Your agent's failed traces are wasted fine-tuning data

#agents #ai #cli #llm
Comments 2
3 min read
Why INT4 Weight-Only Quantization Doesn't Speed Up Prefill
ji_ai profile

Why INT4 Weight-Only Quantization Doesn't Speed Up Prefill

#llm #machinelearning #performance
Comments 1
7 min read
Your Agent's Plan Isn't a Plan. It's a Post-Hoc Rationalization
aiexplore369zoho profile

Your Agent's Plan Isn't a Plan. It's a Post-Hoc Rationalization

#ai #agents #architecture #llm
Comments
5 min read
Everyone's Trying Vectors and Graphs for AI Memory. We Went Back to SQL.
priyeshdave6 profile

Everyone's Trying Vectors and Graphs for AI Memory. We Went Back to SQL.

#ai #agenticai #machinelearning #llm
Comments 1
4 min read
CI/CD for Agentic AI: Freezing Production Failures Into Hermetic Regression Tests With Tracely-ai
priyeshdave6 profile

CI/CD for Agentic AI: Freezing Production Failures Into Hermetic Regression Tests With Tracely-ai

#ai #agenticai #machinelearning #llm
Comments
5 min read
The Two-Hour Gatekeeper for a 'Cheap and Capable' Model Announcement
codepro_9661 profile

The Two-Hour Gatekeeper for a 'Cheap and Capable' Model Announcement

#ai #testing #llm #programming
1
Comments
4 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.