DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
The hard part of agent memory isn't remembering — it's forgetting
01_a125211d8c3da3fdcfd profile

The hard part of agent memory isn't remembering — it's forgetting

#ai #llm #agents #machinelearning
1
Comments
4 min read
The LLM Kept Saying “Fixed.” For Three Months, It Wasn’t.
ianlpaterson profile

The LLM Kept Saying “Fixed.” For Three Months, It Wasn’t.

#ai #llm #testing #programming
Comments
7 min read
Inference Arbitrage: How I Route 200+ Daily LLM Calls Across Five Models
ianlpaterson profile

Inference Arbitrage: How I Route 200+ Daily LLM Calls Across Five Models

#ai #llm #devops #python
Comments
10 min read
Three Months of Speed-Up Experiments on a 3090 Ti: Autoregressive DFlash MTP for Qwen3.6-27B
ianlpaterson profile

Three Months of Speed-Up Experiments on a 3090 Ti: Autoregressive DFlash MTP for Qwen3.6-27B

#ai #llm #gpu #performance
Comments
18 min read
Building llama.cpp from source on a Dell Precision T5820 with an RTX 3090 Ti (after seven power cycles)
ianlpaterson profile

Building llama.cpp from source on a Dell Precision T5820 with an RTX 3090 Ti (after seven power cycles)

#ai #llm #gpu #linux
Comments
16 min read
How I Track Claude, Codex, and Gemini Quotas from One Script
ianlpaterson profile

How I Track Claude, Codex, and Gemini Quotas from One Script

#ai #llm #productivity #bash
Comments
6 min read
Designing a Multi-Agent AI System for Content Analysis and Recommendations
nagashreebhat profile

Designing a Multi-Agent AI System for Content Analysis and Recommendations

#systemdesign #llm #backend #ai
Comments
7 min read
Claude Mythos vs Opus 4.8: 90x More Firefox Exploits — But Stay on Opus Anyway
tokenmixai profile

Claude Mythos vs Opus 4.8: 90x More Firefox Exploits — But Stay on Opus Anyway

#claude #ai #llm #security
5
Comments
6 min read
I Cut My LLM API Bill by 73% — Here's the Exact Optimization Playbook
kollittle profile

I Cut My LLM API Bill by 73% — Here's the Exact Optimization Playbook

#ai #llm #devops #costoptimization
Comments
5 min read
Why Your Reranker Isn't Helping Your RAG Pipeline (And How to Prove It)
siddharth_pandey_27 profile

Why Your Reranker Isn't Helping Your RAG Pipeline (And How to Prove It)

#rag #opensource #llm #typescript
1
Comments 4
4 min read
What Production ML Systems Taught Me About AI Hallucinations
mansisomayajula03 profile

What Production ML Systems Taught Me About AI Hallucinations

#ai #machinelearning #llm #softwareengineering
Comments
4 min read
AI Red-Teaming Techniques: A Practical Starting Point for Security Teams
cgivre profile

AI Red-Teaming Techniques: A Practical Starting Point for Security Teams

#ai #cybersecurity #llm #security
Comments 1
4 min read
Local Inference Boost: Qwen 3.6 Benchmarks, KV Cache Quantization, & Ollama UI
soytuber profile
soy

Local Inference Boost: Qwen 3.6 Benchmarks, KV Cache Quantization, & Ollama UI

#ai #llm #selfhosted
Comments
3 min read
Kimi K2.6 Beats Frontier Models in Coding Benchmarks
logiqode profile

Kimi K2.6 Beats Frontier Models in Coding Benchmarks

#llm #opensource #ai #programming
Comments
6 min read
From Burnout to Building: One Indie Dev's Story Behind Mozart
t1m4lc profile
Tim

From Burnout to Building: One Indie Dev's Story Behind Mozart

#ai #llm #coding #devs
Comments
5 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.