DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Do Not Add an LLM Router Until You Can Defend Each Downgrade
euk_ela_a3e7ed01aa3f7314e profile

Do Not Add an LLM Router Until You Can Defend Each Downgrade

#ai #opensource #devtools #llm
Comments
2 min read
Anthropic’s Road to $2 Trillion
techytcm profile

Anthropic’s Road to $2 Trillion

#ai #claude #llm #startup
Comments 2
6 min read
OpenSquilla routes each turn to the cheapest model that can handle it
renolu profile

OpenSquilla routes each turn to the cheapest model that can handle it

#aiagents #llm #routing #python
1
Comments
3 min read
Run Qwen 3.8 27B Locally: Real GGUF Sizes, the KV Cache Trick, and the Template Trap
purpledoubled profile

Run Qwen 3.8 27B Locally: Real GGUF Sizes, the KV Cache Trick, and the Template Trap

#ai #llm #opensource #tutorial
2
Comments 2
5 min read
I Built an AI Agent With Tools. The First 50 Calls Were a Disaster.
chenyuan20509 profile

I Built an AI Agent With Tools. The First 50 Calls Were a Disaster.

#ai #programming #tutorial #llm
Comments
3 min read
GLM 5.3: Zhipu's Open-Weight Model Excels at Coding and Cyber
jamilxt profile

GLM 5.3: Zhipu's Open-Weight Model Excels at Coding and Cyber

#ai #llm #glm #zhipu
Comments 1
7 min read
Why Your AI Agent Forgets Everything Between Sessions (and the Three Honest Fixes)
izgorodin profile

Why Your AI Agent Forgets Everything Between Sessions (and the Three Honest Fixes)

#ai #agents #mcp #llm
1
Comments 2
4 min read
Setting you up to fail
melvyn_sopacua_afcf30b58a profile

Setting you up to fail

#llm #career
Comments
3 min read
I Analyzed 4,788 AI Coding Sessions — Here's Where Your Tokens Actually Go
psycgod profile

I Analyzed 4,788 AI Coding Sessions — Here's Where Your Tokens Actually Go

#ai #llm #productivity #programming
Comments
2 min read
MCP rug-pulls: how a "safe" AI tool turns malicious after you approve it
wesellistools profile

MCP rug-pulls: how a "safe" AI tool turns malicious after you approve it

#security #ai #mcp #llm
3
Comments 2
3 min read
Answer Engine Optimization for Developers: What I Check First
nitishyadav profile

Answer Engine Optimization for Developers: What I Check First

#ai #llm #seo #webdev
4
Comments 1
7 min read
Self-hosting a lite agent backend on one TPU: Gemma 4 E2B + vLLM on a v5e-1
xbill profile

Self-hosting a lite agent backend on one TPU: Gemma 4 E2B + vLLM on a v5e-1

#tpu #vllm #llm #gcp
16
Comments 1
21 min read
A Line of Documentation Was Acting as a Global Config Flag
lexosi profile
Lex

A Line of Documentation Was Acting as a Global Config Flag

#ai #llm #agents #productivity
Comments
6 min read
I built an answer key for eval suites: six models broken on purpose, exactly.
agentdev9 profile

I built an answer key for eval suites: six models broken on purpose, exactly.

#showdev #testing #llm #opensource
1
Comments
2 min read
What Anthropic’s J-lens teaches us about debugging large language models
lenabrooks profile

What Anthropic’s J-lens teaches us about debugging large language models

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