DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Anthropic prompt caching cut our RCA cost by 90%
stella_lin_82914c71e25769 profile

Anthropic prompt caching cut our RCA cost by 90%

#ai #llm #performance #tutorial
Comments
7 min read
Claude 全球宕机 3 小时复盘：为什么你的 AI Agent 不能只有一家 LLM
correctover profile

Claude 全球宕机 3 小时复盘：为什么你的 AI Agent 不能只有一家 LLM

#python #ai #llm #devops
Comments
1 min read
2026 年 6 月 Claude 全球宕机 3 小时复盘：你的 AI Agent 还在单点依赖吗？
correctover profile

2026 年 6 月 Claude 全球宕机 3 小时复盘：你的 AI Agent 还在单点依赖吗？

#python #ai #llm #devops
Comments
1 min read
AI Agent 生产环境每月崩几次？——LLM API 可靠性数据真相
correctover profile

AI Agent 生产环境每月崩几次？——LLM API 可靠性数据真相

#ai #llm #devops #reliability
Comments
1 min read
6 Part series on how UI is changing with GenAI; Day 0: The Chat Box Era and Its Limits
ravidasari profile
Ravi

6 Part series on how UI is changing with GenAI; Day 0: The Chat Box Era and Its Limits

#ai #llm #ui #ux
1
Comments
6 min read
How a Morse Code Attack Bypassed Bankr's LLM Agent: T1027 Obfuscation in the Wild
pav_j_9391d9a9c1bcac profile
PJ

How a Morse Code Attack Bypassed Bankr's LLM Agent: T1027 Obfuscation in the Wild

#ai #cybersecurity #llm #security
Comments
11 min read
What is a Mobile AI Agent? The Architecture, Limits, and Hardware Problem (2026)
nataiden profile
Nat

What is a Mobile AI Agent? The Architecture, Limits, and Hardware Problem (2026)

#ai #mobile #hardware #llm
Comments
4 min read
Prompt injection through website content: how AI agents can be manipulated by the pages they visit
erp_forgeai_39e262c8c5509 profile

Prompt injection through website content: how AI agents can be manipulated by the pages they visit

#agents #ai #llm #security
Comments
4 min read
Local AI Updates: llama.cpp MTP, vLLM Gemma 4 Speeds, Ollama Coder Benchmarks
soytuber profile
soy

Local AI Updates: llama.cpp MTP, vLLM Gemma 4 Speeds, Ollama Coder Benchmarks

#ai #llm #selfhosted
Comments
3 min read
Claude Fable 5 Was Jailbroken in 48 Hours. Here's What Actually Stopped Nothing.
coridev profile

Claude Fable 5 Was Jailbroken in 48 Hours. Here's What Actually Stopped Nothing.

#security #llm #appsec #cybersecurity
1
Comments
5 min read
The Hidden Math Behind AI Agents: Why GPT-4o Can Be More Expensive Than Hiring a Human
bytecalculators profile

The Hidden Math Behind AI Agents: Why GPT-4o Can Be More Expensive Than Hiring a Human

#agents #ai #llm #productivity
Comments
1 min read
AI Email Agents Are Phishable: How OpenClaw Spilled User Data to Social Engineering Attacks
coridev profile

AI Email Agents Are Phishable: How OpenClaw Spilled User Data to Social Engineering Attacks

#security #ai #llm #appsec
2
Comments
4 min read
"What Codex's 'sudo workaround' actually means for production agents"
ashahin profile

"What Codex's 'sudo workaround' actually means for production agents"

#ai #agents #llm #productionai
Comments
5 min read
Why agents need memory that improves itself
baranozdemir profile

Why agents need memory that improves itself

#ai #typescript #llm #programming
1
Comments
2 min read
Your RL Agent Failed a 12-Step Task. Which Step Was Wrong? (The Supervision Problem in Agentic RL)
shoaibalimir profile

Your RL Agent Failed a 12-Step Task. Which Step Was Wrong? (The Supervision Problem in Agentic RL)

#machinelearning #reinforcementlearning #llm #aws
Comments 2
5 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.