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
I built a Homebrew for AI skills: install flow and eval harness inside
Sulthon Zainul Habib
Sulthon Zainul Habib
Sulthon Zainul Habib
Follow
Jun 18
I built a Homebrew for AI skills: install flow and eval harness inside
#
showdev
#
opensource
#
ai
#
llm
3
 reactions
Comments
Add Comment
8 min read
How to Extract Business Rules from Legacy COBOL Code
Michel Ozzello
Michel Ozzello
Michel Ozzello
Follow
for
CoreStory
May 15
How to Extract Business Rules from Legacy COBOL Code
#
ai
#
llm
#
programming
#
softwareengineering
Comments
Add Comment
8 min read
How I Reduced Prompt Injection Attacks by 86% With My Own Framework (And What Went Wrong the First Time)
Gustavo Viana
Gustavo Viana
Gustavo Viana
Follow
May 15
How I Reduced Prompt Injection Attacks by 86% With My Own Framework (And What Went Wrong the First Time)
#
ai
#
security
#
python
#
llm
Comments
Add Comment
5 min read
Is AI Getting Quietly Dumber? A 24/7 Benchmark That Catches LLM Degradation
Ray
Ray
Ray
Follow
Jun 18
Is AI Getting Quietly Dumber? A 24/7 Benchmark That Catches LLM Degradation
#
ai
#
llm
#
openai
#
devtools
1
 reaction
Comments
2
 comments
6 min read
Push vs Pull Memory: A Better Way to Think About AI Agent Memory
Todd Hendricks
Todd Hendricks
Todd Hendricks
Follow
Jun 18
Push vs Pull Memory: A Better Way to Think About AI Agent Memory
#
ai
#
llm
#
agents
#
memory
1
 reaction
Comments
1
 comment
5 min read
Compass v1.1.0 · we shipped a memory plugin that catches its own consumption drift
chunxiaoxx
chunxiaoxx
chunxiaoxx
Follow
May 19
Compass v1.1.0 · we shipped a memory plugin that catches its own consumption drift
#
llm
#
memory
#
mcp
#
agents
1
 reaction
Comments
Add Comment
5 min read
RAG SOTA: I Tested 7 Pipelines and Built SEQUOIA (Open Source)
Ai developer
Ai developer
Ai developer
Follow
May 28
RAG SOTA: I Tested 7 Pipelines and Built SEQUOIA (Open Source)
#
ai
#
machinelearning
#
rag
#
llm
Comments
2
 comments
2 min read
Claude Code and Codex are logging your token usage locally. Here is how to read it.
Rob
Rob
Rob
Follow
Jun 18
Claude Code and Codex are logging your token usage locally. Here is how to read it.
#
llm
#
claude
#
codex
#
localai
Comments
Add Comment
3 min read
Part 4 — High Semantic Similarity Correct Business Conclusion: A Three-Layer Judgment Engine from Retrieval to Quantifiable Decisions
James Lee
James Lee
James Lee
Follow
Jun 18
Part 4 — High Semantic Similarity Correct Business Conclusion: A Three-Layer Judgment Engine from Retrieval to Quantifiable Decisions
#
ai
#
architecture
#
llm
#
rag
6
 reactions
Comments
Add Comment
10 min read
Your LLM bill is not your capacity plan. Here's the math that pages you at 2am.
SolvoHQ
SolvoHQ
SolvoHQ
Follow
May 15
Your LLM bill is not your capacity plan. Here's the math that pages you at 2am.
#
ai
#
llm
#
webdev
#
programming
Comments
Add Comment
4 min read
Your AI agent talks to one EU user on Aug 2. Can you prove it disclosed it was AI?
Armando Gaona
Armando Gaona
Armando Gaona
Follow
Jun 18
Your AI agent talks to one EU user on Aug 2. Can you prove it disclosed it was AI?
#
ai
#
opensource
#
python
#
llm
Comments
1
 comment
3 min read
Beyond Pay-Per-Token: How Enterprises Barter Architecture for AI Access
Vikrant Shukla
Vikrant Shukla
Vikrant Shukla
Follow
May 15
Beyond Pay-Per-Token: How Enterprises Barter Architecture for AI Access
#
ai
#
llm
#
cloud
Comments
Add Comment
3 min read
LLM Prompt Injection & Guardrail Security
Aaradhanah Appalo Eleven
Aaradhanah Appalo Eleven
Aaradhanah Appalo Eleven
Follow
Jun 18
LLM Prompt Injection & Guardrail Security
#
ai
#
cybersecurity
#
llm
#
security
1
 reaction
Comments
1
 comment
5 min read
LLM Structured Output Validation in Python That Holds Up
Rost
Rost
Rost
Follow
May 15
LLM Structured Output Validation in Python That Holds Up
#
architecture
#
llm
#
ai
#
aicoding
Comments
Add Comment
14 min read
Determinism as a feature: when to let your agent call a math API instead of reasoning
Whatsonyourmind
Whatsonyourmind
Whatsonyourmind
Follow
Jun 17
Determinism as a feature: when to let your agent call a math API instead of reasoning
#
mcp
#
agents
#
ai
#
llm
1
 reaction
Comments
6
 comments
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