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
I Kept Retrying a Local Model Into the Right Shape. Turns Out I Didn't Have To Retry At All.
Naitik Kapatel
Naitik Kapatel
Naitik Kapatel
Follow
Aug 7
I Kept Retrying a Local Model Into the Right Shape. Turns Out I Didn't Have To Retry At All.
#
llm
#
node
#
typescript
#
gbnf
3
 reactions
Comments
1
 comment
4 min read
MLOps / LLMOps — CI/CD Pipelines for Continuous Quality Assurance
Hiroki Kameyama
Hiroki Kameyama
Hiroki Kameyama
Follow
Jul 4
MLOps / LLMOps — CI/CD Pipelines for Continuous Quality Assurance
#
ai
#
mlops
#
llm
#
python
Comments
Add Comment
7 min read
Multi-Agent — Implementing the Orchestrator Worker Pattern
Hiroki Kameyama
Hiroki Kameyama
Hiroki Kameyama
Follow
Jul 4
Multi-Agent — Implementing the Orchestrator Worker Pattern
#
ai
#
mlops
#
llm
#
python
Comments
Add Comment
9 min read
Security — Guardrails and Prompt Injection Defense for Production RAG
Hiroki Kameyama
Hiroki Kameyama
Hiroki Kameyama
Follow
Jul 4
Security — Guardrails and Prompt Injection Defense for Production RAG
#
ai
#
mlops
#
llm
#
python
Comments
Add Comment
7 min read
2.Self-Hosted AI: n8n + Ollama, local AI workflows on your Mac
Lorena Dávila Ermus
Lorena Dávila Ermus
Lorena Dávila Ermus
Follow
Aug 8
2.Self-Hosted AI: n8n + Ollama, local AI workflows on your Mac
#
ai
#
automation
#
docker
#
llm
Comments
Add Comment
4 min read
What Building Anamnesis Taught Me About Giving AI a Memory
Naazim Hussain
Naazim Hussain
Naazim Hussain
Follow
Jul 4
What Building Anamnesis Taught Me About Giving AI a Memory
#
ai
#
architecture
#
llm
#
rag
Comments
Add Comment
5 min read
Scaling LLMs: Why Deterministic Hashing Isn't Enough
Suraj Panda
Suraj Panda
Suraj Panda
Follow
Jul 4
Scaling LLMs: Why Deterministic Hashing Isn't Enough
#
ai
#
architecture
#
llm
#
systemdesign
Comments
Add Comment
4 min read
Every dashboard was green while my agent made things up. Here is how I debugged it.
Kartik N V J K
Kartik N V J K
Kartik N V J K
Follow
Aug 7
Every dashboard was green while my agent made things up. Here is how I debugged it.
#
ai
#
agents
#
debugging
#
llm
12
 reactions
Comments
2
 comments
4 min read
I rewrote the same detector three times in one day. Each fix introduced a new way of being wrong.
VisibilityAtlas
VisibilityAtlas
VisibilityAtlas
Follow
Aug 6
I rewrote the same detector three times in one day. Each fix introduced a new way of being wrong.
#
llm
#
testing
#
debugging
#
ai
2
 reactions
Comments
8
 comments
5 min read
Your reasoning model isn't dumb. Your parser is throwing away its best answers.
Rickesh T N
Rickesh T N
Rickesh T N
Follow
Aug 7
Your reasoning model isn't dumb. Your parser is throwing away its best answers.
#
machinelearning
#
llm
#
evaluation
#
ai
1
 reaction
Comments
4
 comments
4 min read
One compaction, four actions, one block: compaction safety is a property of the pair
Alexey Spinov
Alexey Spinov
Alexey Spinov
Follow
Jul 18
One compaction, four actions, one block: compaction safety is a property of the pair
#
ai
#
agents
#
python
#
llm
2
 reactions
Comments
Add Comment
14 min read
What 3 Days at Stanford's AI Security Conference Taught Me About Building Agents Safely
Yogi
Yogi
Yogi
Follow
Aug 7
What 3 Days at Stanford's AI Security Conference Taught Me About Building Agents Safely
#
agents
#
mlsecurity
#
aisecurity
#
llm
5
 reactions
Comments
3
 comments
9 min read
Observability — Tracing RAG and Agents with Langfuse v4
Hiroki Kameyama
Hiroki Kameyama
Hiroki Kameyama
Follow
Jul 4
Observability — Tracing RAG and Agents with Langfuse v4
#
ai
#
mlops
#
llm
#
python
Comments
Add Comment
6 min read
Evals — Automatically Measuring RAG Answer Quality
Hiroki Kameyama
Hiroki Kameyama
Hiroki Kameyama
Follow
Jul 4
Evals — Automatically Measuring RAG Answer Quality
#
ai
#
mlops
#
llm
#
python
Comments
Add Comment
5 min read
Taking RAG to Production — Evals, Observability, Security, and Beyond (Introduction)
Hiroki Kameyama
Hiroki Kameyama
Hiroki Kameyama
Follow
Jul 4
Taking RAG to Production — Evals, Observability, Security, and Beyond (Introduction)
#
ai
#
mlops
#
llm
#
python
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