DEV Community

#llms

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
How to stop an LLM from inventing numbers: evidence containment and numeral tracing

How to stop an LLM from inventing numbers: evidence containment and numeral tracing

Comments
3 min read
How AI Agents Adapt When Plans Break: Lessons from the Minecraft Experiment

How AI Agents Adapt When Plans Break: Lessons from the Minecraft Experiment

Comments
9 min read
Streaming LLM output through a Next.js proxy: why you only get stream_end

Streaming LLM output through a Next.js proxy: why you only get stream_end

Comments
3 min read
How I got my first pull request merged into LiteLLM

How I got my first pull request merged into LiteLLM

Comments
3 min read
Why LLM cost dashboards lie when two deployments share a model name

Why LLM cost dashboards lie when two deployments share a model name

Comments
3 min read
Stop paying for tokens nobody reads: cancel the LLM call when the client disconnects in Node.js

Stop paying for tokens nobody reads: cancel the LLM call when the client disconnects in Node.js

Comments
3 min read
Is your LLM judge any good? Measuring agreement with humans using Cohen's kappa

Is your LLM judge any good? Measuring agreement with humans using Cohen's kappa

Comments
4 min read
Limiting concurrency in Python asyncio with a semaphore and per-task timeouts, in the right order

Limiting concurrency in Python asyncio with a semaphore and per-task timeouts, in the right order

Comments
4 min read
Parsing a streamed LLM response in Node.js: Server-Sent Events, split chunks and the CRLF bug

Parsing a streamed LLM response in Node.js: Server-Sent Events, split chunks and the CRLF bug

Comments
5 min read
Semantic caching for LLM apps: when reusing an answer is safe, and when it's a bug

Semantic caching for LLM apps: when reusing an answer is safe, and when it's a bug

Comments
4 min read
Limiting concurrent async calls in Node.js without a library: a 15-line promise pool

Limiting concurrent async calls in Node.js without a library: a 15-line promise pool

Comments
3 min read
Canary tokens for LLM apps: detecting system prompt leaks and injected exfiltration

Canary tokens for LLM apps: detecting system prompt leaks and injected exfiltration

Comments
4 min read
Rate limiting LLM API calls in Node.js: a token bucket for requests and tokens per minute

Rate limiting LLM API calls in Node.js: a token bucket for requests and tokens per minute

Comments
4 min read
What is the Model Context Protocol (MCP)? Tools, resources, transports and auth, explained by someone who built a server

What is the Model Context Protocol (MCP)? Tools, resources, transports and auth, explained by someone who built a server

Comments
4 min read
Why you can't average p95 latencies, and how to combine percentiles correctly

Why you can't average p95 latencies, and how to combine percentiles correctly

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