DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Portable Agent Governance at Solo-Developer Scale: A Four-Domain Case Study
sovereign34 profile
Lionel

Portable Agent Governance at Solo-Developer Scale: A Four-Domain Case Study

#showdev #ai #agenticai #llm
1
Comments
8 min read
How Much Does AI Actually Cost? The Field Guide to 12 AI Economics Calculators
pich profile

How Much Does AI Actually Cost? The Field Guide to 12 AI Economics Calculators

#ai #llm #opensource #productivity
Comments 3
5 min read
Claude Opus 5: The Flagship Got Cheaper (There's a Catch)
eristoddle profile

Claude Opus 5: The Flagship Got Cheaper (There's a Catch)

#llm #openrouter
Comments
9 min read
What changed in Apiarium after developers started using it
manolito99 profile
Lolo

What changed in Apiarium after developers started using it

#ai #api #llm #software
21
Comments 3
3 min read
I scanned 25 popular MCP servers — the hidden context-tax spans 544
wartzarbee profile

I scanned 25 popular MCP servers — the hidden context-tax spans 544

#ai #mcp #llm #agents
1
Comments 1
3 min read
权重即数据：神经网络权重空间学习如何成为 AI 的下一类训练集
cognitalk profile

权重即数据：神经网络权重空间学习如何成为 AI 的下一类训练集

#ai #deeplearning #llm #machinelearning
Comments
2 min read
Container-Native AI: Mastering GPU Passthrough, Memory Limits, and Auto-Scaling for Your Agent Infrastructure
hypernexus profile

Container-Native AI: Mastering GPU Passthrough, Memory Limits, and Auto-Scaling for Your Agent Infrastructure

#ai #llm #opensource #mcp
1
Comments
5 min read
What If AI Breaks Loose? A Developer's Thought Experiment
john_kagunda_85b6493a9200 profile

What If AI Breaks Loose? A Developer's Thought Experiment

#ai #llm #machinelearning
1
Comments
3 min read
Most of Your LLM Spend Is Wasted on Calls That Don't Need a Frontier Model
tokenlat profile

Most of Your LLM Spend Is Wasted on Calls That Don't Need a Frontier Model

#ai #llm #machinelearning #productivity
7
Comments 14
4 min read
No one measured AI API latency and uptime independently across regions — so I built it. 38 days and 2M probes in, here's what the data shows
max_bob profile

No one measured AI API latency and uptime independently across regions — so I built it. 38 days and 2M probes in, here's what the data shows

#ai #llm #opensource #webperf
Comments
3 min read
Why Large Language Models Hallucinate (And Why That Isn't a Bug)
sanjay_batthula_38d8e913e profile

Why Large Language Models Hallucinate (And Why That Isn't a Bug)

#ai #llm #machinelearning
1
Comments
4 min read
9 Ways Your AI Agent Silently Fails (and How to Catch Each)

Tackling stealthy gray failures
james_anderson_h profile

9 Ways Your AI Agent Silently Fails (and How to Catch Each)

#ai #agents #llm #webdev
28
Comments 26
8 min read
Building AI-Native Organizations: Why Most Companies Are Automating the Wrong Things
formulater profile

Building AI-Native Organizations: Why Most Companies Are Automating the Wrong Things

#ai #automation #llm #productivity
Comments
4 min read
LLM Failover Isn't Just a Backup Model: Retry, Fallback, Cache, and Semantic Routing
natalie_seeklab_4ce72aa3b profile

LLM Failover Isn't Just a Backup Model: Retry, Fallback, Cache, and Semantic Routing

#llm #architecture #ai
1
Comments 1
3 min read
Anthropic deleted 80% of Claude Code's system prompt. No regression.
thegatewayguy profile

Anthropic deleted 80% of Claude Code's system prompt. No regression.

#ai #anthropic #llm #agents
Comments
2 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.