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
Don’t “Execute” the LLM: Typed Actions + Verifiers for Safe Business Agents
kanaria007
kanaria007
kanaria007
Follow
Mar 30
Don’t “Execute” the LLM: Typed Actions + Verifiers for Safe Business Agents
#
ai
#
agents
#
sre
#
llm
1
 reaction
Comments
Add Comment
8 min read
I audited CrewAI's default patterns for token efficiency. Score: 43/100.
gary-botlington
gary-botlington
gary-botlington
Follow
Mar 30
I audited CrewAI's default patterns for token efficiency. Score: 43/100.
#
ai
#
agents
#
llm
#
productivity
Comments
Add Comment
4 min read
A Spreadsheet Library Where You Can Build =LLM("question") — GridSheet v3 Release Notes
righ
righ
righ
Follow
Mar 30
A Spreadsheet Library Where You Can Build =LLM("question") — GridSheet v3 Release Notes
#
spreadsheet
#
javascript
#
react
#
llm
Comments
Add Comment
10 min read
The LiteLLM Supply Chain Attack Changed How We Think About AI Cost Monitoring
Peter Kacerik
Peter Kacerik
Peter Kacerik
Follow
Mar 31
The LiteLLM Supply Chain Attack Changed How We Think About AI Cost Monitoring
#
ai
#
security
#
llm
#
python
Comments
Add Comment
2 min read
How I added LLM fallback to my OpenAI app in 10 minutes
Jay
Jay
Jay
Follow
May 3
How I added LLM fallback to my OpenAI app in 10 minutes
#
python
#
llm
#
openai
#
tutorial
Comments
1
 comment
3 min read
The Compound Interest of AI Context: Why Your Knowledge Layer Will Be Your Most Valuable Business Asset
William Welsh
William Welsh
William Welsh
Follow
Mar 30
The Compound Interest of AI Context: Why Your Knowledge Layer Will Be Your Most Valuable Business Asset
#
ai
#
llm
#
productivity
#
rag
Comments
Add Comment
4 min read
Using GPT-4o-mini for Simple Tasks and GPT-4o for Complex Ones - Automatically
Devon
Devon
Devon
Follow
Mar 30
Using GPT-4o-mini for Simple Tasks and GPT-4o for Complex Ones - Automatically
#
python
#
ai
#
agents
#
llm
Comments
Add Comment
5 min read
Building an LLM-as-a-Judge Evaluation Pipeline for Translation Quality
Temitope
Temitope
Temitope
Follow
May 3
Building an LLM-as-a-Judge Evaluation Pipeline for Translation Quality
#
llm
#
ai
#
machinelearning
#
python
1
 reaction
Comments
Add Comment
4 min read
CAG-EDU: Extending Context-Anchored Generation into Educational Intelligence
Salvatore Attaguile
Salvatore Attaguile
Salvatore Attaguile
Follow
Apr 22
CAG-EDU: Extending Context-Anchored Generation into Educational Intelligence
#
ai
#
learning
#
llm
#
nlp
1
 reaction
Comments
Add Comment
5 min read
Mistral Medium 3.5 Review: A 128B Open-Weight Model With a Coding Agent That Opens PRs For You
Marcus Rowe
Marcus Rowe
Marcus Rowe
Follow
May 3
Mistral Medium 3.5 Review: A 128B Open-Weight Model With a Coding Agent That Opens PRs For You
#
mistral
#
opensourceai
#
openweight
#
llm
Comments
Add Comment
9 min read
How I built a Go proxy that keeps your LLM conversation alive when cloud quota runs out
Shouvik Palit
Shouvik Palit
Shouvik Palit
Follow
May 3
How I built a Go proxy that keeps your LLM conversation alive when cloud quota runs out
#
opensource
#
llm
#
ai
#
go
1
 reaction
Comments
1
 comment
2 min read
I Tested GPT-5.4 vs Claude Opus 4.6 vs Gemini 3.1 Pro on 5 Real Coding Tasks
Sean
Sean
Sean
Follow
Mar 30
I Tested GPT-5.4 vs Claude Opus 4.6 vs Gemini 3.1 Pro on 5 Real Coding Tasks
#
ai
#
programming
#
llm
#
productivity
Comments
Add Comment
2 min read
Prompt Injection in Agentic Apps: 4 Layers of Defense
Dany Paredes
Dany Paredes
Dany Paredes
Follow
May 12
Prompt Injection in Agentic Apps: 4 Layers of Defense
#
agents
#
ai
#
llm
#
security
Comments
2
 comments
9 min read
How to Build a Local Agentic Search Pipeline That Actually Gets Facts Right
Alan West
Alan West
Alan West
Follow
May 3
How to Build a Local Agentic Search Pipeline That Actually Gets Facts Right
#
ai
#
llm
#
machinelearning
#
opensource
2
 reactions
Comments
Add Comment
6 min read
CTX: I built a LLM-free code context loader that uses 5.2% of tokens
June7th
June7th
June7th
Follow
Mar 31
CTX: I built a LLM-free code context loader that uses 5.2% of tokens
#
python
#
ai
#
llm
#
opensource
Comments
Add Comment
1 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