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
LLM evals are a parameter sweep — use a parameter sweep tool
Norman Niemer
Norman Niemer
Norman Niemer
Follow
Aug 26
LLM evals are a parameter sweep — use a parameter sweep tool
#
ai
#
datascience
#
llm
#
machinelearning
Comments
Add Comment
9 min read
How to Build a Good Human-in-the-Loop for AI-Driven Deployments
Brenn Hill
Brenn Hill
Brenn Hill
Follow
Aug 26
How to Build a Good Human-in-the-Loop for AI-Driven Deployments
#
ai
#
devops
#
llm
#
programming
1
 reaction
Comments
Add Comment
7 min read
I Reviewed 12 Free-Tier Integrations. The Same Six Myths Kept Appearing.
Jordan Huang
Jordan Huang
Jordan Huang
Follow
Aug 26
I Reviewed 12 Free-Tier Integrations. The Same Six Myths Kept Appearing.
#
ai
#
llm
#
testing
#
api
Comments
Add Comment
4 min read
Free Tokens, Real Queues: Measure What Your LLM Calls Actually Cost
Quinn Li
Quinn Li
Quinn Li
Follow
Aug 26
Free Tokens, Real Queues: Measure What Your LLM Calls Actually Cost
#
ai
#
llm
#
devops
#
opensource
Comments
Add Comment
4 min read
LLM Evaluation for Software Engineers Without an ML Background: the 90+ Checks We Actually Run
Jula Markova
Jula Markova
Jula Markova
Follow
Aug 26
LLM Evaluation for Software Engineers Without an ML Background: the 90+ Checks We Actually Run
#
ai
#
llm
#
testing
#
programming
Comments
Add Comment
10 min read
Flash Onyx 2.1, one day later: my model spent 400 tokens thinking and returned an empty string
Nathan C.
Nathan C.
Nathan C.
Follow
Aug 26
Flash Onyx 2.1, one day later: my model spent 400 tokens thinking and returned an empty string
#
ai
#
llm
#
ollama
#
opensource
Comments
1
 comment
6 min read
GLM-5.3-Flash: Z.ai Reveals Ox Alpha Was Its Open Multimodal Model
jamilxt
jamilxt
jamilxt
Follow
Aug 26
GLM-5.3-Flash: Z.ai Reveals Ox Alpha Was Its Open Multimodal Model
#
ai
#
llm
#
glm
#
opensource
Comments
Add Comment
7 min read
SGLang outputs endless repetition on NVFP4 models: the FP8 lm_head bug
Jahn
Jahn
Jahn
Follow
Aug 26
SGLang outputs endless repetition on NVFP4 models: the FP8 lm_head bug
#
llm
#
gpu
#
machinelearning
#
debugging
Comments
Add Comment
3 min read
A Decision Tree for Free-Tier AI Automation: Terms, Branches, Worked Leaves
Taylor Lin
Taylor Lin
Taylor Lin
Follow
Aug 26
A Decision Tree for Free-Tier AI Automation: Terms, Branches, Worked Leaves
#
ai
#
llm
#
automation
#
tutorial
Comments
Add Comment
5 min read
INTRODUCTION TO RAG (RETRIEVAL AUGMENTED GENERATION)
Neville Kibwanga
Neville Kibwanga
Neville Kibwanga
Follow
Aug 26
INTRODUCTION TO RAG (RETRIEVAL AUGMENTED GENERATION)
#
rag
#
ai
#
llm
Comments
Add Comment
4 min read
Inside IBM Granite 4.2: Building an Orchestrate-Ready Reasoning App
Alain Airom (Ayrom)
Alain Airom (Ayrom)
Alain Airom (Ayrom)
Follow
Aug 26
Inside IBM Granite 4.2: Building an Orchestrate-Ready Reasoning App
#
bob
#
granite
#
ibmgranite
#
llm
Comments
Add Comment
17 min read
DGX Spark (GB10) bare-metal vLLM: the install that works, two landmines, measured timings
Jahn
Jahn
Jahn
Follow
Aug 26
DGX Spark (GB10) bare-metal vLLM: the install that works, two landmines, measured timings
#
nvidia
#
llm
#
gpu
#
vllm
Comments
Add Comment
2 min read
Why My LLM Agent Fabricated Numbers From Stale Context
Chad Priest
Chad Priest
Chad Priest
Follow
Aug 26
Why My LLM Agent Fabricated Numbers From Stale Context
#
typescript
#
llm
#
debugging
#
caching
Comments
Add Comment
6 min read
cached_tokens is 0 because your system prompt isn't stable
Chad Priest
Chad Priest
Chad Priest
Follow
Aug 26
cached_tokens is 0 because your system prompt isn't stable
#
llm
#
caching
#
typescript
#
debugging
Comments
Add Comment
3 min read
I Seeded Bugs Into My Own PR to Test the AI Reviewer
Alex Chen
Alex Chen
Alex Chen
Follow
Aug 26
I Seeded Bugs Into My Own PR to Test the AI Reviewer
#
ai
#
python
#
testing
#
llm
Comments
Add Comment
5 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