DEV Community

#llmops

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Stop Guessing Which Model Is Better: Amazon Bedrock Model Evaluation Hands-On
maruchin_tech_555 profile

Stop Guessing Which Model Is Better: Amazon Bedrock Model Evaluation Hands-On

#aws #bedrock #ai #llmops
Comments
5 min read
The throttle that wasn't a cap: rate vs sum in agent budgets
vainamoinen profile

The throttle that wasn't a cap: rate vs sum in agent budgets

#ai #agents #architecture #llmops
Comments
5 min read
Invoked, not executed
thekilteddev profile

Invoked, not executed

#orchestration #routing #llmops #buildinpublic
Comments
5 min read
Your AI Agent Doesn't Need a Bigger Context Window. It Needs an Eviction Policy.
mukesh_13 profile

Your AI Agent Doesn't Need a Bigger Context Window. It Needs an Eviction Policy.

#llmops #ai #machinelearning #programming
2
Comments 2
5 min read
Switchboard: building a tool router so your AI agent stops drowning in MCP tools
shashank1719 profile

Switchboard: building a tool router so your AI agent stops drowning in MCP tools

#llmops #ai #mcp
Comments
13 min read
Detailed instructions written for an earlier generation of AI models become harmful on today's models
matsumotory profile

Detailed instructions written for an earlier generation of AI models become harmful on today's models

#promptengineering #agentskills #llmops #contextengineering
Comments
7 min read
We caught our AI agent building backdoors to run itself more
vainamoinen profile

We caught our AI agent building backdoors to run itself more

#ai #agents #architecture #llmops
1
Comments 2
6 min read
The Dedicated-GPU Trap: Why "Frontier, Per-Token" Wins Until You Have a Dozen Clients
alexboissonneault profile

The Dedicated-GPU Trap: Why "Frontier, Per-Token" Wins Until You Have a Dozen Clients

#ai #llmops #saas #architecture
Comments
5 min read
Fine-Tuning Is Often the Wrong First Move: Introducing Harneloop
ker102 profile

Fine-Tuning Is Often the Wrong First Move: Introducing Harneloop

#ai #opensource #agents #llmops
Comments
3 min read
A LiteLLM circuit breaker that kills runaway agent runs
amih profile

A LiteLLM circuit breaker that kills runaway agent runs

#litellm #ai #llmops #python
Comments
3 min read
I Thought Building Agent Observability Was a Detector Problem. I Was Wrong.

Real production data broke 35 detectors instantly
debashish_ghosal profile

I Thought Building Agent Observability Was a Detector Problem. I Was Wrong.

#ai #opentelemetry #llmops #opensource
22
Comments 19
8 min read
Our Token Counter Took 26 Seconds on a Single Prompt

Summer Bug Smash: Smash Stories 🐛🛹
ailegend profile

Our Token Counter Took 26 Seconds on a Single Prompt

#devchallenge #bugsmash #performance #llmops
3
Comments
8 min read
I've Spent Months Grading AI Agents' Code for a Living. Here's the Pattern Nobody's Talking About
marvinoka4 profile

I've Spent Months Grading AI Agents' Code for a Living. Here's the Pattern Nobody's Talking About

#ai #llmops #agenticai #careerdev
Comments 2
4 min read
Our eval gate runs 22 minutes. The queue behind it hit three hours.
ethanwritesai profile

Our eval gate runs 22 minutes. The queue behind it hit three hours.

#llm #cicd #testing #llmops
4
Comments 1
5 min read
Mem0 vs Zep vs LangChain Memory vs Letta: Picking the Right Agent Memory Architecture
mukesh_13 profile
Mukesh

Mem0 vs Zep vs LangChain Memory vs Letta: Picking the Right Agent Memory Architecture

#mem0 #aiagents #llmops #python
1
Comments 4
4 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.