DEV Community

Posts

Some latest posts are only visible for members. Sign in to see all latest.

Your LLM Judge Agrees With Itself. That Is Not an Eval.
Cover image for Your LLM Judge Agrees With Itself. That Is Not an Eval.

Your LLM Judge Agrees With Itself. That Is Not an Eval.

Comments
13 min read
Do You Really Need a Dedicated MQTT Broker for IoT?

Do You Really Need a Dedicated MQTT Broker for IoT?

Comments
4 min read
ToGO for Laravel developers: the artisan commands you know, in Go

ToGO for Laravel developers: the artisan commands you know, in Go

Comments
3 min read
Dimensionare un pallettizzatore dal lato del progettista: i tre numeri che non stanno nelle brochure

Dimensionare un pallettizzatore dal lato del progettista: i tre numeri che non stanno nelle brochure

Comments
2 min read
Landlock ABI checks decide which network restrictions a sandbox can enforce

Landlock ABI checks decide which network restrictions a sandbox can enforce

Comments
2 min read
Kwi vs Konsole: Should KDE Developers Switch Terminals?

Kwi vs Konsole: Should KDE Developers Switch Terminals?

Comments
7 min read
What Happens When Your AI Agent Fails Halfway Through a Ten-Step Task?

What Happens When Your AI Agent Fails Halfway Through a Ten-Step Task?

Comments
4 min read
Reviewing PRs in an Agentic Era

Reviewing PRs in an Agentic Era

Comments
4 min read
AI Wrote 162 Python Packages. Only One Worked. Here's What That Means for Open Source

AI Wrote 162 Python Packages. Only One Worked. Here's What That Means for Open Source

Comments
6 min read
One Repayment, Two Webhooks: Preventing Duplicate Loan Postings

One Repayment, Two Webhooks: Preventing Duplicate Loan Postings

Comments
3 min read
Myers, Patience, Histogram: Why Git Can Make an Agent's Moved Method Look Rewritten

Myers, Patience, Histogram: Why Git Can Make an Agent's Moved Method Look Rewritten

Comments
10 min read
We checked over 2,000 AI answers for 14 businesses. Four times out of five, the business wasn't named.

We checked over 2,000 AI answers for 14 businesses. Four times out of five, the business wasn't named.

Comments
3 min read
Stop Writing Unpaid Proposals: An 8-Question Client Intake SOP for Freelance Developers

Stop Writing Unpaid Proposals: An 8-Question Client Intake SOP for Freelance Developers

Comments
4 min read
Generating WhatsApp Templates With an LLM: Category Rules, Invented Facts and Checks in Code

Generating WhatsApp Templates With an LLM: Category Rules, Invented Facts and Checks in Code

1
Comments
11 min read
How Reliable Is the Wake-and-Catch-Up Mechanism, Actually? 4 Late Runs Out of 34, Counted.

How Reliable Is the Wake-and-Catch-Up Mechanism, Actually? 4 Late Runs Out of 34, Counted.

Comments
4 min read
Your LLM cost log says $0.00. The invoice says $1,320.

Your LLM cost log says $0.00. The invoice says $1,320.

Comments
4 min read
.ai vs .com for a Startup

.ai vs .com for a Startup

Comments
4 min read
Is AI dangerous, or just misunderstood?

Is AI dangerous, or just misunderstood?

Comments
2 min read
loading...