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
300+ languages doesn't mean what you think: three tiers of code understanding
Na'aman Hirschfeld (Goldziher)
Na'aman Hirschfeld (Goldziher)
Na'aman Hirschfeld (Goldziher)
Follow
Aug 8
300+ languages doesn't mean what you think: three tiers of code understanding
#
ai
#
llm
#
programming
#
software
Comments
Add Comment
7 min read
Keeping the LLM out of the verdict
quemtrouxe
quemtrouxe
quemtrouxe
Follow
Aug 9
Keeping the LLM out of the verdict
#
ai
#
architecture
#
llm
#
python
Comments
1
 comment
5 min read
Understanding Tokens: How AI Models Process Text and Why It Matters for Cost, Context, and Agentic AI
Adolfo Pedernera
Adolfo Pedernera
Adolfo Pedernera
Follow
Aug 8
Understanding Tokens: How AI Models Process Text and Why It Matters for Cost, Context, and Agentic AI
#
guide
#
llm
#
ai
#
beginners
Comments
Add Comment
10 min read
I built an async wrapper for OpenAI/Anthropic SDKs because I didn't want a proxy in my request path
Mandar Shinde
Mandar Shinde
Mandar Shinde
Follow
Aug 8
I built an async wrapper for OpenAI/Anthropic SDKs because I didn't want a proxy in my request path
#
showdev
#
python
#
ai
#
llm
Comments
Add Comment
2 min read
I created a tool to inspect full python codebases
Santiago Martinez
Santiago Martinez
Santiago Martinez
Follow
Aug 8
I created a tool to inspect full python codebases
#
llm
#
python
#
ai
#
code
Comments
Add Comment
1 min read
"How to Tell If an LLM Was Really Trained From Scratch: A Reproducible Fingerprinting Method"
ai maya
ai maya
ai maya
Follow
Aug 8
"How to Tell If an LLM Was Really Trained From Scratch: A Reproducible Fingerprinting Method"
#
ai
#
llm
#
machinelearning
#
opensource
Comments
Add Comment
7 min read
🤖 AI Context Engineering (Part 4): AI Agents - From Tool Calling to Multi-Step Workflows
Fazal Mansuri
Fazal Mansuri
Fazal Mansuri
Follow
Aug 8
🤖 AI Context Engineering (Part 4): AI Agents - From Tool Calling to Multi-Step Workflows
#
ai
#
llm
#
agents
#
softwareengineering
1
 reaction
Comments
Add Comment
9 min read
I tested if system prompts actually matter, here's what I found
Taha Shashtari
Taha Shashtari
Taha Shashtari
Follow
Aug 8
I tested if system prompts actually matter, here's what I found
#
ai
#
webdev
#
javascript
#
llm
Comments
Add Comment
2 min read
Claude Code Keeps Forgetting My Projects - Here's the Skill I Built to Make It Remember /project-registry
Scott Sun
Scott Sun
Scott Sun
Follow
Aug 8
Claude Code Keeps Forgetting My Projects - Here's the Skill I Built to Make It Remember /project-registry
#
ai
#
claude
#
llm
#
productivity
Comments
Add Comment
3 min read
Integrating AgentRouter with Tauric Research TradingAgents
Arpan Dhara
Arpan Dhara
Arpan Dhara
Follow
Aug 8
Integrating AgentRouter with Tauric Research TradingAgents
#
agents
#
ai
#
llm
#
tutorial
Comments
Add Comment
4 min read
Your multi-agent system isn't hitting prompt cache. Your system prompt is the reason.
Rickesh T N
Rickesh T N
Rickesh T N
Follow
Aug 11
Your multi-agent system isn't hitting prompt cache. Your system prompt is the reason.
#
llm
#
ai
#
architecture
#
performance
3
 reactions
Comments
4
 comments
4 min read
One Prompt Template, Three Engines That Disagree
Faisal Mehmood
Faisal Mehmood
Faisal Mehmood
Follow
Aug 8
One Prompt Template, Three Engines That Disagree
#
opensource
#
llm
#
cncf
#
apicurioregistry
Comments
Add Comment
6 min read
1. Self-Hosted AI: the LLM concepts you need to run models effectively
Lorena Dávila Ermus
Lorena Dávila Ermus
Lorena Dávila Ermus
Follow
Aug 8
1. Self-Hosted AI: the LLM concepts you need to run models effectively
#
ai
#
llm
Comments
Add Comment
9 min read
Designing an End-to-End RAG Architecture from Scratch
Valery Odinga
Valery Odinga
Valery Odinga
Follow
Aug 11
Designing an End-to-End RAG Architecture from Scratch
#
ai
#
architecture
#
llm
#
rag
11
 reactions
Comments
2
 comments
8 min read
DeepSeek's Flash outpaced its own flagship. The upgrade was post-training, not parameters.
Andrew Kew
Andrew Kew
Andrew Kew
Follow
Aug 9
DeepSeek's Flash outpaced its own flagship. The upgrade was post-training, not parameters.
#
discuss
#
ai
#
llm
#
machinelearning
1
 reaction
Comments
Add Comment
2 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