DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Defender flujos de agentes contra el OWASP LLM Top 10

Defender flujos de agentes contra el OWASP LLM Top 10

2
Comments 1
9 min read
Building a sub-millisecond LLM security proxy in Go — lessons from 62 adversarial vectors

Building a sub-millisecond LLM security proxy in Go — lessons from 62 adversarial vectors

7
Comments 9
7 min read
Observability told me exactly how much money my agents wasted. I wanted something that says no.

Observability told me exactly how much money my agents wasted. I wanted something that says no.

2
Comments 1
3 min read
AIchain: Connecting Steps into a Pipeline

AIchain: Connecting Steps into a Pipeline

2
Comments
5 min read
Vibe Coding Traps and Delusions

Vibe Coding Traps and Delusions

4
Comments
5 min read
Write your error states for a stranger three months from now, not for yourself today

Error states as incident reports for async work

Write your error states for a stranger three months from now, not for yourself today

4
Comments 12
4 min read
AI & Human Collaboration: Building audit.sh

AI & Human Collaboration: Building audit.sh

1
Comments
3 min read
KIMI + Agnes: A Real-World Test of Cross-Provider Agent Chain Correctover

KIMI + Agnes: A Real-World Test of Cross-Provider Agent Chain Correctover

Comments
3 min read
The hard part of agent memory isn't remembering — it's forgetting

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

1
Comments
4 min read
Building llama.cpp from source on a Dell Precision T5820 with an RTX 3090 Ti (after seven power cycles)

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

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

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

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

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

Comments
18 min read
Inference Arbitrage: How I Route 200+ Daily LLM Calls Across Five Models

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

Comments
10 min read
Designing a Multi-Agent AI System for Content Analysis and Recommendations

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

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

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

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