Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
llm
Follow
Hide
Posts
Left menu
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
Why Your AI Coding Agent Should Never See Your .env
z-150
z-150
z-150
Follow
Aug 21
Why Your AI Coding Agent Should Never See Your .env
#
security
#
ai
#
llm
#
devops
Comments
Add Comment
2 min read
The Day a Support Ticket Overrode My System Prompt
Taylor Wang
Taylor Wang
Taylor Wang
Follow
Aug 21
The Day a Support Ticket Overrode My System Prompt
#
security
#
llm
#
ai
#
python
1
 reaction
Comments
Add Comment
5 min read
7 Lessons from Building Agentic AI in Production
Haider Farooq
Haider Farooq
Haider Farooq
Follow
Aug 21
7 Lessons from Building Agentic AI in Production
#
ai
#
llm
#
agents
#
programming
Comments
Add Comment
2 min read
The Eval Passed and Production Still Broke: A Token-Counting Retrospective
Riley Lin
Riley Lin
Riley Lin
Follow
Aug 21
The Eval Passed and Production Still Broke: A Token-Counting Retrospective
#
ai
#
debugging
#
llm
#
serverless
Comments
Add Comment
4 min read
Free Model Tokens Are a Measurement Budget, Not a Demo Fund
Riley Xu
Riley Xu
Riley Xu
Follow
Aug 21
Free Model Tokens Are a Measurement Budget, Not a Demo Fund
#
ai
#
llm
#
testing
#
python
Comments
Add Comment
6 min read
The Free-Tier Trap: A Framework for Choosing Model Access
Quinn Li
Quinn Li
Quinn Li
Follow
Aug 21
The Free-Tier Trap: A Framework for Choosing Model Access
#
ai
#
llm
#
opensource
#
devops
Comments
Add Comment
5 min read
Free AI Servers Fail Quietly: A Reproducible Test for MonkeyCode's Free Tier
Morgan Ma
Morgan Ma
Morgan Ma
Follow
Aug 21
Free AI Servers Fail Quietly: A Reproducible Test for MonkeyCode's Free Tier
#
ai
#
llm
#
testing
#
opensource
Comments
Add Comment
5 min read
A Free-Tier LLM Gateway: Routing, Caching, and Failover in About 200 Lines
Emery Li
Emery Li
Emery Li
Follow
Aug 21
A Free-Tier LLM Gateway: Routing, Caching, and Failover in About 200 Lines
#
llm
#
python
#
api
#
opensource
1
 reaction
Comments
Add Comment
5 min read
Are We Sending Too Much Data to LLMs? Agentic Production Support (APS)
Dev Hajare
Dev Hajare
Dev Hajare
Follow
Aug 21
Are We Sending Too Much Data to LLMs? Agentic Production Support (APS)
#
architecture
#
llm
#
privacy
#
security
Comments
Add Comment
2 min read
I Built My Own AI Assistant in My Evenings — Free, No Signup, No Credit Card
exadokoai
exadokoai
exadokoai
Follow
Aug 21
I Built My Own AI Assistant in My Evenings — Free, No Signup, No Credit Card
#
ai
#
programming
#
cod
#
llm
Comments
Add Comment
3 min read
The Same Prompt Twice Is Double Quota: A Verifiable Cache for Free Model Endpoints
Dakota Huang
Dakota Huang
Dakota Huang
Follow
Aug 21
The Same Prompt Twice Is Double Quota: A Verifiable Cache for Free Model Endpoints
#
ai
#
llm
#
tutorial
#
node
Comments
Add Comment
7 min read
Why Open-Weight Models Are Closing the Gap with Closed Models
manil
manil
manil
Follow
Aug 21
Why Open-Weight Models Are Closing the Gap with Closed Models
#
ai
#
llm
#
machinelearning
#
opensource
Comments
Add Comment
2 min read
Benchmark scores are marketing now
Aamer Mihaysi
Aamer Mihaysi
Aamer Mihaysi
Follow
Aug 25
Benchmark scores are marketing now
#
ai
#
llm
#
agents
1
 reaction
Comments
Add Comment
4 min read
Trend: On-Device Small Language Models Are Replacing Cloud Calls
manil
manil
manil
Follow
Aug 21
Trend: On-Device Small Language Models Are Replacing Cloud Calls
#
ai
#
cloud
#
llm
#
performance
Comments
Add Comment
1 min read
Trend: On-Device Small Language Models Are Replacing Cloud Calls
manil
manil
manil
Follow
Aug 21
Trend: On-Device Small Language Models Are Replacing Cloud Calls
#
ai
#
llm
#
performance
#
privacy
Comments
Add Comment
2 min read
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