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
TIL - Choosing Between Code, an LLM Call, and an AI Agent
M. Alwi Sukra
M. Alwi Sukra
M. Alwi Sukra
Follow
Jul 27
TIL - Choosing Between Code, an LLM Call, and an AI Agent
#
softwareengineering
#
go
#
ai
#
llm
Comments
Add Comment
12 min read
Fully Autonomous. Except for the Human Doing the Hard Part.
Vinicius Fagundes
Vinicius Fagundes
Vinicius Fagundes
Follow
Jul 27
Fully Autonomous. Except for the Human Doing the Hard Part.
#
llm
#
ai
#
data
#
python
1
 reaction
Comments
Add Comment
2 min read
How I Shrunk My Agent's Core from 15 to 9: Why Hit Rate Alone Can't Tell You Which Rules to Retire
Xin & EQ
Xin & EQ
Xin & EQ
Follow
Jul 27
How I Shrunk My Agent's Core from 15 to 9: Why Hit Rate Alone Can't Tell You Which Rules to Retire
#
ai
#
llm
#
agents
#
devtool
1
 reaction
Comments
Add Comment
10 min read
My AI agent tried to delete my secrets. It couldn't.
Jules Robineau
Jules Robineau
Jules Robineau
Follow
Jul 27
My AI agent tried to delete my secrets. It couldn't.
#
ai
#
security
#
devops
#
llm
1
 reaction
Comments
Add Comment
9 min read
Your Error Messages Are an API Now
Claudius
Claudius
Claudius
Follow
Aug 9
Your Error Messages Are an API Now
#
mcp
#
ai
#
llm
#
architecture
Comments
2
 comments
4 min read
The Model Writes, the Judge Measures: Anatomy of an LLM Judge
Sam Wen
Sam Wen
Sam Wen
Follow
Jul 27
The Model Writes, the Judge Measures: Anatomy of an LLM Judge
#
ai
#
llm
#
testing
#
machinelearning
Comments
Add Comment
12 min read
Why RL Training Collapses on Long-Horizon Agents
Orkas
Orkas
Orkas
Follow
Jul 27
Why RL Training Collapses on Long-Horizon Agents
#
agents
#
ai
#
llm
#
machinelearning
Comments
2
 comments
10 min read
What 78K attack samples taught me about catching prompt injection
Wes Ellis
Wes Ellis
Wes Ellis
Follow
Jul 27
What 78K attack samples taught me about catching prompt injection
#
security
#
ai
#
machinelearning
#
llm
Comments
Add Comment
2 min read
I built a spend cap for LLM calls. It failed by 4.2x under parallel load.
pr3tik
pr3tik
pr3tik
Follow
Aug 9
I built a spend cap for LLM calls. It failed by 4.2x under parallel load.
#
agents
#
ai
#
backend
#
llm
1
 reaction
Comments
2
 comments
5 min read
Your Knowledge Graph Is Wasting 70% of Its Tokens
Mahesh VAIKRI
Mahesh VAIKRI
Mahesh VAIKRI
Follow
Jul 27
Your Knowledge Graph Is Wasting 70% of Its Tokens
#
llm
#
ai
#
opensource
#
programming
1
 reaction
Comments
Add Comment
2 min read
We made SigNoz's LLM observability actually reachable…
Gajanand V Dhayagode
Gajanand V Dhayagode
Gajanand V Dhayagode
Follow
Jul 26
We made SigNoz's LLM observability actually reachable…
#
observability
#
opentelemetry
#
llm
#
hackathon
Comments
Add Comment
8 min read
Is AI Limited by the Exact Superpower That Made It Powerful?
Mei Hammer
Mei Hammer
Mei Hammer
Follow
Jul 26
Is AI Limited by the Exact Superpower That Made It Powerful?
#
ai
#
llm
#
innovation
#
creativity
Comments
Add Comment
7 min read
Tracing Voice AI is Hard: How I Instrumented Streaming LLMs with OpenTelemetry and SigNoz
Jay Prajapati
Jay Prajapati
Jay Prajapati
Follow
Jul 26
Tracing Voice AI is Hard: How I Instrumented Streaming LLMs with OpenTelemetry and SigNoz
#
ai
#
llm
#
monitoring
#
performance
Comments
Add Comment
4 min read
Andrej Karpathy's "Deep Dive into LLMs like ChatGPT"
absterellio
absterellio
absterellio
Follow
Jul 26
Andrej Karpathy's "Deep Dive into LLMs like ChatGPT"
#
ai
#
llm
#
chatgpt
Comments
Add Comment
4 min read
Stop Validating AI Agents Only at the Start: Introducing Mid-Chain Governance
Subramanya L
Subramanya L
Subramanya L
Follow
Jul 26
Stop Validating AI Agents Only at the Start: Introducing Mid-Chain Governance
#
agents
#
ai
#
llm
#
security
Comments
Add Comment
4 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