DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
I Tested 300+ Models. Then I Killed the Benchmark.

High maintenance cost of custom benchmarks
vystartasv profile

I Tested 300+ Models. Then I Killed the Benchmark.

#ai #llm #opensource #productivity
8
Comments 5
4 min read
MiniMax M3 Ships Open-Weight 1M Context: MiniMax Sparse Attention (MSA)
pueding profile

MiniMax M3 Ships Open-Weight 1M Context: MiniMax Sparse Attention (MSA)

#ai #llm #machinelearning #tutorial
Comments
6 min read
Email Triage Taxonomies for LLM Classification
qasim157 profile

Email Triage Taxonomies for LLM Classification

#ai #llm #email #machinelearning
2
Comments
5 min read
I stopped trusting “same answers, fewer tokens” after watching an agent lose 1 field name and burn 3 hours
lars_winstand profile

I stopped trusting “same answers, fewer tokens” after watching an agent lose 1 field name and burn 3 hours

#ai #llm #agents #devops
Comments
7 min read
Human Approval Gates in the Claude Agent SDK
sekeraradim profile

Human Approval Gates in the Claude Agent SDK

#ai #llm #opensource #tutorial
1
Comments 1
3 min read
How to Build Production-Ready Generative AI Development Services for Enterprise Applications
dixit_angiras_1f2a7cb300d profile

How to Build Production-Ready Generative AI Development Services for Enterprise Applications

#ai #architecture #llm #systemdesign
Comments
4 min read
LLM cost reduction techniques ranked by ROI: the 5 that matter, the 9 that don't (much)
rikuq profile

LLM cost reduction techniques ranked by ROI: the 5 that matter, the 9 that don't (much)

#llm #costreduction #aicostoptimization #rankedtechniques
Comments
12 min read
Multi-Turn Email Conversations for LLM Agents
qasim157 profile

Multi-Turn Email Conversations for LLM Agents

#ai #email #llm #agents
1
Comments
4 min read
The best bug reports were written by the suspect
andreasbergstrom profile

The best bug reports were written by the suspect

#llm #openai #ai #security
1
Comments 1
1 min read
Shipping an LLM-powered "lie detector" in a Flutter dating app
vladvladescu profile

Shipping an LLM-powered "lie detector" in a Flutter dating app

#showdev #ai #flutter #llm
Comments
3 min read
From Chatbot to Mailbox: Persistent Agent Memory in Threads
qasim157 profile

From Chatbot to Mailbox: Persistent Agent Memory in Threads

#ai #llm #email #agents
1
Comments
5 min read
Sampling strategies compared: temperature, top-p, top-k, min-p, and what actually works in production
tech_nuggets profile

Sampling strategies compared: temperature, top-p, top-k, min-p, and what actually works in production

#llm #ai #machinelearning #opensource
Comments
9 min read
Why your AI Agent needs a sandbox, not a blank check 🛡️
florabrandao profile

Why your AI Agent needs a sandbox, not a blank check 🛡️

#ai #llm
Comments
1 min read
I Vibe-Coded an App for a $3,000 Hackathon. It Was Complete Slop đź« 
qamar_dev_01 profile

I Vibe-Coded an App for a $3,000 Hackathon. It Was Complete Slop đź« 

#showdev #hackathon #vibecoding #llm
Comments
2 min read
I tested 3 models as AI agent quality inspectors: the stronger the model, the more valid work it rejects

Precision-recall and the false positive mirage
zxpmail profile

I tested 3 models as AI agent quality inspectors: the stronger the model, the more valid work it rejects

#ai #llm #testing #agents
10
Comments 60
5 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.