DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
How Open-Source LLMs Differ: Comparing 130+ Model Architectures

How Open-Source LLMs Differ: Comparing 130+ Model Architectures

5
7 min read
️🎞️ What is native multimodality?

️🎞️ What is native multimodality?

5
1 min read
Restricting MCP connectors to read-only access

Restricting MCP connectors to read-only access

1
2
10 min read
I gave AI agents an empty API response. They made up support tickets.

I gave AI agents an empty API response. They made up support tickets.

4 min read
What app code should assume about an LLM call

What app code should assume about an LLM call

1
6 min read
Your MCP Scanner Passed. Would Your Agent Still Follow a Poisoned Tool? A Canary Method for Testing AI Agents

Your MCP Scanner Passed. Would Your Agent Still Follow a Poisoned Tool? A Canary Method for Testing AI Agents

7 min read
Two Official Pages Disagree on When Claude Haiku 4.5 Retires

Two Official Pages Disagree on When Claude Haiku 4.5 Retires

1
4 min read
Prefill vs Decode: Why Splitting Them Wins

Prefill vs Decode: Why Splitting Them Wins

1
10 min read
Medindo um agente de treino: o que o few-shot fez (e não fez) com um modelo local e com o Gemini

Medindo um agente de treino: o que o few-shot fez (e não fez) com um modelo local e com o Gemini

4 min read
LLM benchmark stimulus audit: 33 of 80 pairs not clean

LLM benchmark stimulus audit: 33 of 80 pairs not clean

4 min read
Testing LLM Tool Calls With Pytest: Asserting the Right Tool, Arguments, and Order

Testing LLM Tool Calls With Pytest: Asserting the Right Tool, Arguments, and Order

10 min read
RLHF vs RLAIF: The Labeling Bill Behind Model Alignment

RLHF vs RLAIF: The Labeling Bill Behind Model Alignment

5 min read
An AI agent believes whatever its tools send back

An AI agent believes whatever its tools send back

2
3
6 min read
Ripple 65B Puts Open Coding Models to a More Practical Test

Ripple 65B Puts Open Coding Models to a More Practical Test

8 min read
One constant was costing my schema retriever 17 points

One constant was costing my schema retriever 17 points

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