close

DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Are AI Tools Actually Making Us Productive — or Just Giving Us Something New to Play With?

The courier problem of manual tab-hopping

Are AI Tools Actually Making Us Productive — or Just Giving Us Something New to Play With?

16
Comments 12
8 min read
We measured a week of inference. Routing by task difficulty cuts our cost per call roughly 48x — and flips which users are profitable.

We measured a week of inference. Routing by task difficulty cuts our cost per call roughly 48x — and flips which users are profitable.

Comments
5 min read
Your Agent Planned the Right Tools. It Still Crashed the Machine.

Your Agent Planned the Right Tools. It Still Crashed the Machine.

3
Comments 1
6 min read
Your Agent's Memory Is a Lie: A Durable, Queryable Memory Layer for Local LLM Agents

Your Agent's Memory Is a Lie: A Durable, Queryable Memory Layer for Local LLM Agents

Comments
7 min read
AgentCore Evaluations: How AWS Built a Framework-Agnostic Eval Layer Using OpenTelemetry as the Contract

AgentCore Evaluations: How AWS Built a Framework-Agnostic Eval Layer Using OpenTelemetry as the Contract

Comments
6 min read
Deploying DeepSeek R1 Reasoning LLM Using SGLang

Deploying DeepSeek R1 Reasoning LLM Using SGLang

Comments
2 min read
I told my agent not to work around a refusal. It obeyed forever.

I told my agent not to work around a refusal. It obeyed forever.

Comments
3 min read
Constraint Weakening in LLM Agent Workflows: Why \\\\\\\"Must\\\\\\\" Becomes \\\\\\\"Maybe\\\\\\\" Across Multi-Stage Pipelines

Constraint Weakening in LLM Agent Workflows: Why \\\\\\\"Must\\\\\\\" Becomes \\\\\\\"Maybe\\\\\\\" Across Multi-Stage Pipelines

Comments
6 min read
MCP Describe Injection: Audit Tool Descriptions Like Code

MCP Describe Injection: Audit Tool Descriptions Like Code

1
Comments
4 min read
50 minutes from issue to merged fix: when the readers find the boundary you shipped past

50 minutes from issue to merged fix: when the readers find the boundary you shipped past

5
Comments 1
5 min read
Installing LM Studio – A Graphical Application for Running LLMs

Installing LM Studio – A Graphical Application for Running LLMs

Comments
4 min read
I put my cost router on a neutral benchmark. It ranked near the bottom, and that's the interesting part

I put my cost router on a neutral benchmark. It ranked near the bottom, and that's the interesting part

Comments 2
5 min read
Your local RAG isn't slow — it re-reads every document on every question

Your local RAG isn't slow — it re-reads every document on every question

Comments
9 min read
Agentic AI Security: Sandboxing LLM Tool Calls in Production

Agentic AI Security: Sandboxing LLM Tool Calls in Production

Comments
5 min read
LLM evals are a parameter sweep — use a parameter sweep tool

LLM evals are a parameter sweep — use a parameter sweep tool

Comments
9 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.