Llm Page 205 - DEV Community

Skip to content

DEV Community

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

Rob

May 11

Model Showdown Round 4: Opus vs Qwen — Writers, Not Coders

#ai #llm #benchmark #agents

10 min read

May 11

SubQ Model: Can Subquadratic Make Long-Context AI More Efficient?

#ai #architecture #longconext #llm

9 min read

Jun 14

LLM-as-Judge Is Three Decisions

#aiagents #evals #llm #observability

6 min read

Jun 14

We Built a Self-Hosted AI Platform That Runs 100% on Your Hardware — Introducing local-ai.run

#ai #llm #selfhosted #opensource

5 min read

Augustine Uzokwe

Jun 2

6 lessons on testing AI features

#ai #qa #testing #llm

8 min read

Gemma 4 Challenge: Write about Gemma 4 Submission

May 25

🔬 Direction 1 closure on JAMES — when the hypothesis fails but the data turns "7-tier monotonic natural-stop gradient"

#rag #gemma #gemmachallenge #llm

2 min read

Alan West

May 11

TokenSpeed and the Quiet Race to Make LLM Inference Boring

#llm #machinelearning #performance #devops

5 min read

soy

May 11

ExLlamaV3 Updates, Unsloth Qwen GGUFs & Phi3 Autonomous Bridge

#ai #llm #selfhosted

3 min read

May 11

Part 8 — Token-by-Token: Why AI Generates Text One Word at a Time (And Why It Costs 4x More)

#tokens #llm #costoptimization #aifundamentals

9 min read

zeromathai

May 12

How Large Language Models Work — From Transformers to Conversational AI

#ai #machinelearning #llm #deeplearning

4 min read

May 11

Three Layers of Tool Call Hardening for AI Agents

#ai #agents #llm #software

4 min read

Sebastian Chedal

May 11

Anthropic’s Multi-Agent Blueprint: What Production Constraints Add

#ai #agents #llm #machinelearning

13 min read

May 11

Strict-schema LLM outputs: what we learned shipping to a HIPAA environment

#llm #python #ai #webdev

8 min read

Martin Tuncaydin

May 11

Fine-Tuning Open-Source LLMs on Travel Domain Data: A Practitioner's Guide to LoRA Adapters

#llm #finetuning #traveltechnology #lora

7 min read

Kunal

Jun 14

Prompt Injection in 2026: Still OWASP's Number One LLM Vulnerability

#aisecurity #owasp #llm #promptinjection

13 min read

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