Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
llm
Follow
Hide
Posts
Left menu
👋
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
The MCP Tax Hit 42,000 Tokens on a Single Server. Here's What I Did About It.
MrClaw207
MrClaw207
MrClaw207
Follow
Jun 29
The MCP Tax Hit 42,000 Tokens on a Single Server. Here's What I Did About It.
#
ai
#
llm
#
agents
#
llmtools
Comments
Add Comment
4 min read
Building Maestro AI: Routing LLM Calls So Your Agent Doesn't Burn Sonnet on Summaries
David Shibley
David Shibley
David Shibley
Follow
Jul 12
Building Maestro AI: Routing LLM Calls So Your Agent Doesn't Burn Sonnet on Summaries
#
showdev
#
agents
#
ai
#
llm
Comments
2
 comments
7 min read
A Better LLM Judge? The Rubric Made My Small Model Worse
Suman Nath
Suman Nath
Suman Nath
Follow
Jun 29
A Better LLM Judge? The Rubric Made My Small Model Worse
#
machinelearning
#
llm
#
python
#
ai
Comments
Add Comment
5 min read
LLM-as-a-Judge: I Built One From Scratch, Then Checked It Against Humans
Suman Nath
Suman Nath
Suman Nath
Follow
Jun 29
LLM-as-a-Judge: I Built One From Scratch, Then Checked It Against Humans
#
machinelearning
#
llm
#
python
#
ai
Comments
Add Comment
4 min read
How Modern Transformer Blocks Work — From RMSNorm to MoE
zeromathai
zeromathai
zeromathai
Follow
Jun 29
How Modern Transformer Blocks Work — From RMSNorm to MoE
#
ai
#
machinelearning
#
llm
#
transformers
Comments
Add Comment
5 min read
One Agent or Five? What I Learned Running a Team of AI Coders
Enjoy Kumawat
Enjoy Kumawat
Enjoy Kumawat
Follow
Jun 29
One Agent or Five? What I Learned Running a Team of AI Coders
#
ai
#
claudecode
#
llm
#
productivity
Comments
Add Comment
4 min read
My AI Agent Read 56 KB to Answer One Question. I Made It Stop.
Enjoy Kumawat
Enjoy Kumawat
Enjoy Kumawat
Follow
Jun 29
My AI Agent Read 56 KB to Answer One Question. I Made It Stop.
#
ai
#
llm
#
claudecode
#
productivity
Comments
Add Comment
4 min read
How to switch AI models without rewriting your app
GWEN
GWEN
GWEN
Follow
Jun 29
How to switch AI models without rewriting your app
#
ai
#
llm
#
api
#
python
Comments
Add Comment
3 min read
I Built Byte Because OpenWebUI Kept Breaking
Byte
Byte
Byte
Follow
Jun 30
I Built Byte Because OpenWebUI Kept Breaking
#
showdev
#
ai
#
llm
#
sideprojects
5
 reactions
Comments
Add Comment
1 min read
From Transformer to ChatGPT: How One Paper Changed AI Engineering Forever
luka
luka
luka
Follow
Jun 29
From Transformer to ChatGPT: How One Paper Changed AI Engineering Forever
#
ai
#
machinelearning
#
deeplearning
#
llm
1
 reaction
Comments
Add Comment
3 min read
Stop Hardcoding Your Agent Workflows (or Don't): A Dev's Guide to Supervisor Delegation
Marc Newstead
Marc Newstead
Marc Newstead
Follow
Jun 29
Stop Hardcoding Your Agent Workflows (or Don't): A Dev's Guide to Supervisor Delegation
#
ai
#
architecture
#
devops
#
llm
Comments
Add Comment
3 min read
Stop pasting your API keys into ChatGPT: a safer way to feed a codebase to an LLM
Cá»u thiên vÅ© đế review
Cá»u thiên vÅ© đế review
Cá»u thiên vÅ© đế review
Follow
Jul 3
Stop pasting your API keys into ChatGPT: a safer way to feed a codebase to an LLM
#
ai
#
llm
#
security
#
cli
Comments
Add Comment
2 min read
"LLM Inference Optimization: The Line Item That Decides If Your AI Ships"
Vladyslav Donchenko
Vladyslav Donchenko
Vladyslav Donchenko
Follow
Jun 29
"LLM Inference Optimization: The Line Item That Decides If Your AI Ships"
#
ai
#
llm
#
machinelearning
#
performance
Comments
Add Comment
2 min read
Resurrecting Kepler: Getting Modern LLMs Running on a GTX 770 (Kernel 7.x)
skyne
skyne
skyne
Follow
Jun 27
Resurrecting Kepler: Getting Modern LLMs Running on a GTX 770 (Kernel 7.x)
#
cuda
#
linux
#
llm
#
gpu
1
 reaction
Comments
Add Comment
4 min read
Caching LLM responses is just content addressing
Muhammet ÅžAFAK
Muhammet ÅžAFAK
Muhammet ÅžAFAK
Follow
Jun 29
Caching LLM responses is just content addressing
#
go
#
llm
#
performance
#
cli
Comments
Add Comment
5 min read
👋
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