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
OK, DEGRADED, ABSTAINED, FAILED: Designing a Typed Outcome Model for LLM Calls
David Shibley
David Shibley
David Shibley
Follow
Jul 8
OK, DEGRADED, ABSTAINED, FAILED: Designing a Typed Outcome Model for LLM Calls
#
typescript
#
ai
#
softwareengineering
#
llm
1
 reaction
Comments
2
 comments
9 min read
3 Open-Source Repos That Each Kill a Different AI Bill(token, infra, creative)
Shilpa Mitra
Shilpa Mitra
Shilpa Mitra
Follow
Jun 25
3 Open-Source Repos That Each Kill a Different AI Bill(token, infra, creative)
#
ai
#
opensource
#
productivity
#
llm
Comments
Add Comment
4 min read
The Feynman Technique Prompt: How to Make AI Explain Anything in 4 Layers of Depth
Yao Xiao
Yao Xiao
Yao Xiao
Follow
Jun 25
The Feynman Technique Prompt: How to Make AI Explain Anything in 4 Layers of Depth
#
promptengineering
#
ailearning
#
llm
#
ai
Comments
Add Comment
13 min read
Qwen3 vs DeepSeek R1: Which Open-Source Reasoning Model Should You Use in 2026?
NaveenKumar Namachivayam ⚡
NaveenKumar Namachivayam ⚡
NaveenKumar Namachivayam ⚡
Follow
Jun 25
Qwen3 vs DeepSeek R1: Which Open-Source Reasoning Model Should You Use in 2026?
#
ai
#
opensource
#
llm
Comments
Add Comment
8 min read
I built an RL-native memory engine for LLM agents (every memory decision becomes a training signal)
Aditi Chatterji
Aditi Chatterji
Aditi Chatterji
Follow
Jun 25
I built an RL-native memory engine for LLM agents (every memory decision becomes a training signal)
#
ai
#
llm
#
python
#
opensource
Comments
Add Comment
2 min read
Your Multi-Agent Pipeline Isn't Slow Because of the Model
Wessam Ibrahim
Wessam Ibrahim
Wessam Ibrahim
Follow
Jul 18
Your Multi-Agent Pipeline Isn't Slow Because of the Model
#
ai
#
productivity
#
llm
#
claude
5
 reactions
Comments
Add Comment
3 min read
The AI judge that called a half-finished audit 'exhaustive'
Luc B. Perussault-Diallo
Luc B. Perussault-Diallo
Luc B. Perussault-Diallo
Follow
Jun 30
The AI judge that called a half-finished audit 'exhaustive'
#
ai
#
llm
#
testing
#
tooling
Comments
Add Comment
6 min read
MLOps for LLM: A Case Study on Dresscode
Saad Alkentar
Saad Alkentar
Saad Alkentar
Follow
Jun 25
MLOps for LLM: A Case Study on Dresscode
#
mlops
#
llm
#
gemma
#
ai
Comments
Add Comment
21 min read
LLMs Can't Reliably Do Date Math — And Now There's Data
Maverick Y
Maverick Y
Maverick Y
Follow
Jul 29
LLMs Can't Reliably Do Date Math — And Now There's Data
#
ai
#
testing
#
llm
#
opensource
Comments
Add Comment
6 min read
Why KV Cache Matters — How MQA, GQA, and MLA Make LLM Inference Faster
zeromathai
zeromathai
zeromathai
Follow
Jun 25
Why KV Cache Matters — How MQA, GQA, and MLA Make LLM Inference Faster
#
ai
#
machinelearning
#
llm
#
transformers
Comments
Add Comment
5 min read
Write returned success. The file was never there.
Vlad
Vlad
Vlad
Follow
Jun 25
Write returned success. The file was never there.
#
ai
#
agents
#
llm
#
rag
Comments
Add Comment
2 min read
The 50% Context Tax: Why Your AI Agent's Million-Token Window Is Burning Money
MrClaw207
MrClaw207
MrClaw207
Follow
Jun 25
The 50% Context Tax: Why Your AI Agent's Million-Token Window Is Burning Money
#
ai
#
llm
#
agents
#
llmtools
Comments
Add Comment
4 min read
smolagents replays its whole memory every step: the O(n ) token bill nobody mentions
wartzar-bee
wartzar-bee
wartzar-bee
Follow
Jul 29
smolagents replays its whole memory every step: the O(n ) token bill nobody mentions
#
llm
#
aiagents
#
python
#
opensource
2
 reactions
Comments
3
 comments
6 min read
A local model opened 41 of our pull requests in five weeks. The model is the least interesting part.
Christopher Maher
Christopher Maher
Christopher Maher
Follow
Jun 25
A local model opened 41 of our pull requests in five weeks. The model is the least interesting part.
#
ai
#
kubernetes
#
opensource
#
llm
Comments
Add Comment
10 min read
Your First LLM API on Kubernetes: From Model to Curl Request
Pawan Kumar
Pawan Kumar
Pawan Kumar
Follow
Jun 25
Your First LLM API on Kubernetes: From Model to Curl Request
#
kubernetes
#
llm
#
ai
#
devops
Comments
Add Comment
10 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