DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
The Promptfoo Acquisition Made Me Realize I Was Evaluating LLMs on Easy Mode

The Promptfoo Acquisition Made Me Realize I Was Evaluating LLMs on Easy Mode

Comments
2 min read
Removing AI Tells from Your Writing: A Skill That Turns One Flag into a Permanent Rule

Removing AI Tells from Your Writing: A Skill That Turns One Flag into a Permanent Rule

1
Comments
4 min read
Inference Efficiency Ratio: Measure Model Spend Before It Eats Your Margin

Inference Efficiency Ratio: Measure Model Spend Before It Eats Your Margin

1
Comments 1
10 min read
Look for Long Horizon Agents for frontier Labs, located in Mountain View (Remote)

Look for Long Horizon Agents for frontier Labs, located in Mountain View (Remote)

Comments
2 min read
I have been Vibecoding Evals (works better than I thought)

I have been Vibecoding Evals (works better than I thought)

Comments
3 min read
How Actually Your Functions Get Called By LLMs?

How Actually Your Functions Get Called By LLMs?

Comments 2
19 min read
XML Tagging in Prompts: The Secret to Getting Better Output from Claude and GPT

XML Tagging in Prompts: The Secret to Getting Better Output from Claude and GPT

Comments
3 min read
The J-Space: How I Learned To Read An LLM's Mind

The J-Space: How I Learned To Read An LLM's Mind

6
Comments
1 min read
What Is Semantic Segmentation?

What Is Semantic Segmentation?

Comments
1 min read
Monitor LLM Costs with Prometheus & Grafana (Without a Proxy)

Monitor LLM Costs with Prometheus & Grafana (Without a Proxy)

Comments
2 min read
Why We Are Not Building Another Foundation Model

Why We Are Not Building Another Foundation Model

Comments
5 min read
Low-Rank Adapters Turn Preference Tuning Into Shortcut Tuning

Low-Rank Adapters Turn Preference Tuning Into Shortcut Tuning

Comments
4 min read
You are the bottleneck

You are the bottleneck

Comments
6 min read
If you let an AI do the scoring, start by doubting the scores

If you let an AI do the scoring, start by doubting the scores

Comments
7 min read
OpenAI cut a model's price 80% and told nobody. It took me 23 days to notice — and I run a price tracker.

OpenAI cut a model's price 80% and told nobody. It took me 23 days to notice — and I run a price tracker.

Comments
6 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.