Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
llms
Follow
Hide
Posts
Left menu
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
How to stop an LLM from inventing numbers: evidence containment and numeral tracing
Ali Ahmed
Ali Ahmed
Ali Ahmed
Follow
Nov 20
How to stop an LLM from inventing numbers: evidence containment and numeral tracing
#
aiengineering
#
llms
#
hallucinations
#
evaluation
Comments
Add Comment
3 min read
Moderation
How AI Agents Adapt When Plans Break: Lessons from the Minecraft Experiment
Maya Richardson
Maya Richardson
Maya Richardson
Follow
Nov 20
How AI Agents Adapt When Plans Break: Lessons from the Minecraft Experiment
#
ai
#
agents
#
llms
#
testing
Comments
Add Comment
9 min read
Moderation
Streaming LLM output through a Next.js proxy: why you only get stream_end
Ali Ahmed
Ali Ahmed
Ali Ahmed
Follow
Nov 20
Streaming LLM output through a Next.js proxy: why you only get stream_end
#
nextjs
#
streaming
#
llms
#
webdev
Comments
Add Comment
3 min read
Moderation
How I got my first pull request merged into LiteLLM
Ali Ahmed
Ali Ahmed
Ali Ahmed
Follow
Nov 20
How I got my first pull request merged into LiteLLM
#
opensource
#
aiengineering
#
llms
Comments
Add Comment
3 min read
Moderation
Why LLM cost dashboards lie when two deployments share a model name
Ali Ahmed
Ali Ahmed
Ali Ahmed
Follow
Nov 20
Why LLM cost dashboards lie when two deployments share a model name
#
aiengineering
#
llms
#
opensource
#
finops
Comments
Add Comment
3 min read
Moderation
Stop paying for tokens nobody reads: cancel the LLM call when the client disconnects in Node.js
Ali Ahmed
Ali Ahmed
Ali Ahmed
Follow
Nov 20
Stop paying for tokens nobody reads: cancel the LLM call when the client disconnects in Node.js
#
llms
#
node
#
streaming
#
cost
Comments
Add Comment
3 min read
Moderation
Is your LLM judge any good? Measuring agreement with humans using Cohen's kappa
Ali Ahmed
Ali Ahmed
Ali Ahmed
Follow
Nov 20
Is your LLM judge any good? Measuring agreement with humans using Cohen's kappa
#
llms
#
evaluation
#
aiengineering
#
python
Comments
Add Comment
4 min read
Moderation
Limiting concurrency in Python asyncio with a semaphore and per-task timeouts, in the right order
Ali Ahmed
Ali Ahmed
Ali Ahmed
Follow
Nov 20
Limiting concurrency in Python asyncio with a semaphore and per-task timeouts, in the right order
#
python
#
llms
#
aiengineering
#
performance
Comments
Add Comment
4 min read
Moderation
Parsing a streamed LLM response in Node.js: Server-Sent Events, split chunks and the CRLF bug
Ali Ahmed
Ali Ahmed
Ali Ahmed
Follow
Nov 19
Parsing a streamed LLM response in Node.js: Server-Sent Events, split chunks and the CRLF bug
#
llms
#
node
#
streaming
#
aiengineering
Comments
Add Comment
5 min read
Moderation
Semantic caching for LLM apps: when reusing an answer is safe, and when it's a bug
Ali Ahmed
Ali Ahmed
Ali Ahmed
Follow
Nov 19
Semantic caching for LLM apps: when reusing an answer is safe, and when it's a bug
#
llms
#
aiengineering
#
python
#
rag
Comments
Add Comment
4 min read
Moderation
Limiting concurrent async calls in Node.js without a library: a 15-line promise pool
Ali Ahmed
Ali Ahmed
Ali Ahmed
Follow
Nov 19
Limiting concurrent async calls in Node.js without a library: a 15-line promise pool
#
node
#
javascript
#
performance
#
llms
Comments
Add Comment
3 min read
Moderation
Canary tokens for LLM apps: detecting system prompt leaks and injected exfiltration
Ali Ahmed
Ali Ahmed
Ali Ahmed
Follow
Nov 19
Canary tokens for LLM apps: detecting system prompt leaks and injected exfiltration
#
security
#
llms
#
aiagents
#
python
Comments
Add Comment
4 min read
Moderation
Rate limiting LLM API calls in Node.js: a token bucket for requests and tokens per minute
Ali Ahmed
Ali Ahmed
Ali Ahmed
Follow
Nov 19
Rate limiting LLM API calls in Node.js: a token bucket for requests and tokens per minute
#
llms
#
node
#
aiengineering
#
reliability
Comments
Add Comment
4 min read
Moderation
What is the Model Context Protocol (MCP)? Tools, resources, transports and auth, explained by someone who built a server
Ali Ahmed
Ali Ahmed
Ali Ahmed
Follow
Nov 18
What is the Model Context Protocol (MCP)? Tools, resources, transports and auth, explained by someone who built a server
#
mcp
#
aiagents
#
llms
#
aiengineering
Comments
Add Comment
4 min read
Moderation
Why you can't average p95 latencies, and how to combine percentiles correctly
Ali Ahmed
Ali Ahmed
Ali Ahmed
Follow
Nov 18
Why you can't average p95 latencies, and how to combine percentiles correctly
#
monitoring
#
sre
#
typescript
#
llms
Comments
Add Comment
3 min read
Moderation
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
We're a place where coders share, stay up-to-date and grow their careers.
Log in
Create account