DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
llama-bench skipped FA on capable GPUs — b9437 corrects it

llama-bench skipped FA on capable GPUs — b9437 corrects it

Comments
7 min read
Nemotron 3 Ultra went live June 4. Here's the call that works.

Nemotron 3 Ultra went live June 4. Here's the call that works.

Comments
7 min read
The Citation Lied Without Lying: The Hard Limit of My Memory Gate

Publicly pre-registered failure predictions

The Citation Lied Without Lying: The Hard Limit of My Memory Gate

23
Comments 126
8 min read
I Ran Five Small Multimodal Models on a Jetson. The Fastest One Was Not the Best Baseline.

I Ran Five Small Multimodal Models on a Jetson. The Fastest One Was Not the Best Baseline.

Comments
3 min read
Building a Multi-Step AI Pipeline with Automatic Retry Logic

Building a Multi-Step AI Pipeline with Automatic Retry Logic

1
Comments
5 min read
Lately, I’ve been thinking about setting up my homelab again. I still…

Lately, I’ve been thinking about setting up my homelab again. I still…

Comments
1 min read
The AI Supply Chain Attack Surface Nobody's Actually Checking

The AI Supply Chain Attack Surface Nobody's Actually Checking

2
Comments
13 min read
The context your agents don't have

The context your agents don't have

Comments 1
1 min read
I Think I Just Found One of Python's Most Underrated AI Libraries

I Think I Just Found One of Python's Most Underrated AI Libraries

1
Comments
3 min read
An alternative to LLM quality gates: deterministic routing + sampling

Six experiments on LLM-judge failures

An alternative to LLM quality gates: deterministic routing + sampling

13
Comments 69
11 min read
Stop telling your RAG bot not to hallucinate. Make it impossible.

Stop telling your RAG bot not to hallucinate. Make it impossible.

1
Comments
4 min read
Two months building an investment bot. What it taught me about LLMs

Two months building an investment bot. What it taught me about LLMs

1
Comments
17 min read
Prompts Aren't Enough: Enforcing Hard Constraints on LLM Output

Prompts Aren't Enough: Enforcing Hard Constraints on LLM Output

1
Comments 1
4 min read
I put 6 LLM guardrail tools inline and measured what they cost me. Here is the latency-vs-recall tradeoff.

I put 6 LLM guardrail tools inline and measured what they cost me. Here is the latency-vs-recall tradeoff.

1
Comments
3 min read
Top 10 Prompt Engineering Concepts Every AI Developer Should Master in 2026 !🚀

Top 10 Prompt Engineering Concepts Every AI Developer Should Master in 2026 !🚀

1
Comments
1 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.