DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
GLM 5.2 Has a 1M Token Context Window. Here's What That Does to Your API Bill.

GLM 5.2 Has a 1M Token Context Window. Here's What That Does to Your API Bill.

Comments
4 min read
Your Training Set Is Quietly Eating Itself: A Field Guide to Model Collapse in 2026

Your Training Set Is Quietly Eating Itself: A Field Guide to Model Collapse in 2026

Comments
6 min read
Context Warp Drive: deterministic folding for long-running LLM agents

Context Warp Drive: deterministic folding for long-running LLM agents

Comments 1
1 min read
Coding Agents Play Favorites With Your Dependencies

Coding Agents Play Favorites With Your Dependencies

Comments
3 min read
Stop Serving Raw Cosine Scores: Explainable RAG Confidence Scoring at Query Time

Stop Serving Raw Cosine Scores: Explainable RAG Confidence Scoring at Query Time

Comments 1
6 min read
Deploy AI agents in 5 lines of code.

Deploy AI agents in 5 lines of code.

Comments
3 min read
Reactive is Dead: Build Low-Latency Voice Agents with OpenAI Realtime and JDK WebSockets

Reactive is Dead: Build Low-Latency Voice Agents with OpenAI Realtime and JDK WebSockets

1
Comments
2 min read
# We Keep Teaching AI to Retrieve Information. What If We Taught It to Understand It Instead?

# We Keep Teaching AI to Retrieve Information. What If We Taught It to Understand It Instead?

7
Comments
1 min read
Google A2A Protocol in 2026: Adoption, Hype, and Reality

Google A2A Protocol in 2026: Adoption, Hype, and Reality

Comments
17 min read
RAG for codebases is hard. Trusting the answer is harder.

RAG for codebases is hard. Trusting the answer is harder.

Comments 1
4 min read
Graceful Degradation Strategies for LLM Rate Limits

Graceful Degradation Strategies for LLM Rate Limits

Comments
3 min read
# What Happens When You Try to Build a Lawyer for Someone Who Can't Afford One?

# What Happens When You Try to Build a Lawyer for Someone Who Can't Afford One?

3
Comments
10 min read
Why did one day of AI cost more than a month of servers?

Why did one day of AI cost more than a month of servers?

Comments
5 min read
I accidentally built a production LLM router by running it for 3 months on my own projects

I accidentally built a production LLM router by running it for 3 months on my own projects

Comments
2 min read
How I cut my LLM API bill by ~60% (5 levers that actually work)

How I cut my LLM API bill by ~60% (5 levers that actually work)

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