DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Model DNA, Analyzed: Verifying 'From-Scratch' LLM Claims with Architecture, Tokenizer, and CKA (PyTorch)

Model DNA, Analyzed: Verifying 'From-Scratch' LLM Claims with Architecture, Tokenizer, and CKA (PyTorch)

Comments
6 min read
How to Verify a 'Trained-From-Scratch' LLM in 2026: A Provenance and Fingerprinting Guide

How to Verify a 'Trained-From-Scratch' LLM in 2026: A Provenance and Fingerprinting Guide

Comments
5 min read
Andrew Ng at Berkeley: AGI is a contract term, the jobocalypse is a myth, and bubble risk is in the wrong layer

Andrew Ng at Berkeley: AGI is a contract term, the jobocalypse is a myth, and bubble risk is in the wrong layer

Comments
2 min read
A reader read my benchmark better than I did

A reader read my benchmark better than I did

3
Comments 2
7 min read
Stop Infinite ReAct Loops: Deterministic Cycle Detection in Spring AI with Java 21 Record Patterns

Stop Infinite ReAct Loops: Deterministic Cycle Detection in Spring AI with Java 21 Record Patterns

Comments 1
2 min read
Ollama Has No API Authentication: How To Properly Gate Port 11434

Ollama Has No API Authentication: How To Properly Gate Port 11434

2
Comments 1
14 min read
Your embeddings forget exactly like a human brain does

Your embeddings forget exactly like a human brain does

1
Comments
4 min read
Your LLM App Is Wasting Money: What Happens When Users Close the Tab?

Your LLM App Is Wasting Money: What Happens When Users Close the Tab?

6
Comments 10
9 min read
What if the main coding-agent session was intentionally dumb?

What if the main coding-agent session was intentionally dumb?

Comments
1 min read
The Schema Was Valid. The Translation Was in Chinese

The Schema Was Valid. The Translation Was in Chinese

2
Comments 7
5 min read
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?

23
Comments 34
8 min read
Local LLMs in 2026: What Actually Runs Well on a Laptop Now

Local LLMs in 2026: What Actually Runs Well on a Laptop Now

Comments
3 min read
Default-to-Flagship Is Now a Cost Bug: Tiered Model Routing for Agentic Workloads

Default-to-Flagship Is Now a Cost Bug: Tiered Model Routing for Agentic Workloads

1
Comments 2
3 min read
12 Agentic Harness Patterns

12 Agentic Harness Patterns

2
Comments 3
6 min read
Sending Images to GPT-4o, Claude, and Gemini: The Base64 Payload Each One Wants

Sending Images to GPT-4o, Claude, and Gemini: The Base64 Payload Each One Wants

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