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
I Measured What My Curated MCP Tool Output Is Actually Saving
Enjoy Kumawat
Enjoy Kumawat
Enjoy Kumawat
Follow
Aug 10
I Measured What My Curated MCP Tool Output Is Actually Saving
#
mcp
#
llm
#
python
#
ai
3
reactions
Comments
1
comment
4 min read
怎麼用一套開源系統,把 LLM 逼近世界模型(實驗技術篇)
力智栩
力智栩
力智栩
Follow
Aug 10
怎麼用一套開源系統,把 LLM 逼近世界模型(實驗技術篇)
#
ai
#
llm
#
opensource
#
worldmodel
Comments
Add Comment
3 min read
EchoLeak: zero-click data theft from an AI assistant
Brenn Hill
Brenn Hill
Brenn Hill
Follow
Jul 7
EchoLeak: zero-click data theft from an AI assistant
#
security
#
ai
#
llm
#
infosec
1
reaction
Comments
Add Comment
3 min read
LLM Policy as Code: Version-Controlled Governance for Model and Agent Access
DVARA
DVARA
DVARA
Follow
Jul 7
LLM Policy as Code: Version-Controlled Governance for Model and Agent Access
#
ai
#
security
#
llm
#
governance
Comments
Add Comment
4 min read
How I Cut 30% LLM Costs: RAG Context Pruning Cost Reduction
Umair Bilal
Umair Bilal
Umair Bilal
Follow
Jul 7
How I Cut 30% LLM Costs: RAG Context Pruning Cost Reduction
#
aiagents
#
llm
#
rag
#
costoptimization
Comments
Add Comment
10 min read
How to Build a Streaming Chatbot API in Python with FastAPI and SSE
Ayi NEDJIMI
Ayi NEDJIMI
Ayi NEDJIMI
Follow
Jul 7
How to Build a Streaming Chatbot API in Python with FastAPI and SSE
#
python
#
ai
#
llm
#
tutorial
1
reaction
Comments
Add Comment
4 min read
Taming LLM Tail Latency: Dynamic Request Hedging with Java's JEP 480 Structured Concurrency
Machine coding Master
Machine coding Master
Machine coding Master
Follow
Jul 7
Taming LLM Tail Latency: Dynamic Request Hedging with Java's JEP 480 Structured Concurrency
#
java
#
concurrency
#
systemdesign
#
llm
Comments
Add Comment
2 min read
Karpathy: Agent Performance Gap Is in the Harness, Not the Model
WDSEGA
WDSEGA
WDSEGA
Follow
Jul 7
Karpathy: Agent Performance Gap Is in the Harness, Not the Model
#
karpathy
#
agents
#
harness
#
llm
Comments
1
comment
2 min read
I Wrote the Same Tool-Calling Loop Three Times, Once Per Provider, Before I Stopped
Yatin Davra
Yatin Davra
Yatin Davra
Follow
Aug 10
I Wrote the Same Tool-Calling Loop Three Times, Once Per Provider, Before I Stopped
#
ai
#
javascript
#
llm
#
node
Comments
Add Comment
5 min read
A New Open-Weight Model Just Dropped? Run This 30-Minute Eval Before You Rewrite Your Pipeline
Riley Lin
Riley Lin
Riley Lin
Follow
Aug 10
A New Open-Weight Model Just Dropped? Run This 30-Minute Eval Before You Rewrite Your Pipeline
#
ai
#
opensource
#
llm
#
programming
Comments
Add Comment
4 min read
Self-Hosting Your First LLM: What the Tutorials Skip About GPU Memory
Libme
Libme
Libme
Follow
Aug 10
Self-Hosting Your First LLM: What the Tutorials Skip About GPU Memory
#
llm
#
ai
#
machinelearning
#
devops
Comments
2
comments
5 min read
Your AI API fallback is hiding your real bill
Edward Li
Edward Li
Edward Li
Follow
Jul 7
Your AI API fallback is hiding your real bill
#
ai
#
api
#
llm
#
devops
Comments
Add Comment
3 min read
我讓一個 AI 拿 2000 塊台幣去股市,目標 30 天翻倍,這是第 0 天
力智栩
力智栩
力智栩
Follow
Aug 10
我讓一個 AI 拿 2000 塊台幣去股市,目標 30 天翻倍,這是第 0 天
#
ai
#
llm
#
trading
#
experiment
2
reactions
Comments
Add Comment
3 min read
Question AI software development
John
John
John
Follow
Jul 7
Question AI software development
#
help
#
llm
#
beginners
#
ai
Comments
Add Comment
1 min read
Running a 122B Parameter Model and Agent Locally on AMD MI300X GPU — What I Learned
Yogi
Yogi
Yogi
Follow
Aug 10
Running a 122B Parameter Model and Agent Locally on AMD MI300X GPU — What I Learned
#
gpu
#
llm
#
agents
#
roc
1
reaction
Comments
Add Comment
7 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