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
Score Coding Models With a 60-Line Harness Before You Spend a Cent
Riley Zhang
Riley Zhang
Riley Zhang
Follow
Aug 5
Score Coding Models With a 60-Line Harness Before You Spend a Cent
#
ai
#
llm
#
python
#
tutorial
Comments
Add Comment
5 min read
My Tool-Calling Loop Worked Fine, Until Compliance Wanted a Second Model to Check It
deep patel
deep patel
deep patel
Follow
Aug 5
My Tool-Calling Loop Worked Fine, Until Compliance Wanted a Second Model to Check It
#
llm
#
node
#
typescript
#
agents
2
 reactions
Comments
1
 comment
4 min read
What I learned trying to benchmark local LLMs honestly
David G
David G
David G
Follow
Aug 9
What I learned trying to benchmark local LLMs honestly
#
llm
#
python
#
opensource
#
ai
Comments
2
 comments
4 min read
The night an uncapped prompt turned into a bill
Wren Calloway
Wren Calloway
Wren Calloway
Follow
Aug 5
The night an uncapped prompt turned into a bill
#
ai
#
architecture
#
llm
#
softwareengineering
Comments
Add Comment
1 min read
Can a Cheap Model Beat a Frontier Model? Rebuilding Recursive Language Models with Codex
Rickesh T N
Rickesh T N
Rickesh T N
Follow
Aug 9
Can a Cheap Model Beat a Frontier Model? Rebuilding Recursive Language Models with Codex
#
ai
#
llm
#
agents
#
machinelearning
2
 reactions
Comments
Add Comment
6 min read
RAG vs MAG: Two Paths to Smarter AI Memory
Saumya Ranjan Mohapatra
Saumya Ranjan Mohapatra
Saumya Ranjan Mohapatra
Follow
Aug 5
RAG vs MAG: Two Paths to Smarter AI Memory
#
ai
#
machinelearning
#
rag
#
llm
Comments
Add Comment
3 min read
llmperf Is Archived: Alternatives for LLM Benchmarking
Wayne
Wayne
Wayne
Follow
Aug 5
llmperf Is Archived: Alternatives for LLM Benchmarking
#
rust
#
benchmarking
#
llm
Comments
Add Comment
3 min read
LLM Narrative Engines, Part 6: Runtime Loop and Branching
yuelinghuashu
yuelinghuashu
yuelinghuashu
Follow
Aug 5
LLM Narrative Engines, Part 6: Runtime Loop and Branching
#
go
#
llm
#
engineering
Comments
Add Comment
10 min read
Measuring LLM Prefix Caching: The Cache Hit Rate Metric
Wayne
Wayne
Wayne
Follow
Aug 5
Measuring LLM Prefix Caching: The Cache Hit Rate Metric
#
llm
#
benchmarking
#
performance
Comments
Add Comment
6 min read
Beyond Size: The Three Pillars of Test-Time Scaling in Large Language Models
Prabhakar Chaudhary
Prabhakar Chaudhary
Prabhakar Chaudhary
Follow
Aug 5
Beyond Size: The Three Pillars of Test-Time Scaling in Large Language Models
#
ai
#
machinelearning
#
deeplearning
#
llm
Comments
Add Comment
5 min read
Beyond RAG: Building an AI Coding Agent with Planning, Tool Execution, and ReAct Reasoning
Sri Deevi
Sri Deevi
Sri Deevi
Follow
Aug 5
Beyond RAG: Building an AI Coding Agent with Planning, Tool Execution, and ReAct Reasoning
#
agents
#
ai
#
coding
#
llm
Comments
Add Comment
3 min read
LLMs on Consumer Hardware — Part 1: The Stack and First Benchmarks
Sven Welack
Sven Welack
Sven Welack
Follow
Aug 5
LLMs on Consumer Hardware — Part 1: The Stack and First Benchmarks
#
localllama
#
ai
#
llm
#
homelab
Comments
Add Comment
3 min read
PassiveDx: The Body's API
Seyed Alireza Alhosseini
Seyed Alireza Alhosseini
Seyed Alireza Alhosseini
Follow
Aug 5
PassiveDx: The Body's API
#
ai
#
llm
#
softwaredevelopment
#
computerscience
1
 reaction
Comments
Add Comment
8 min read
Stop Guessing: A Repeatable Harness for Comparing Free LLM Endpoints on Your Actual Tasks
Emery Li
Emery Li
Emery Li
Follow
Aug 5
Stop Guessing: A Repeatable Harness for Comparing Free LLM Endpoints on Your Actual Tasks
#
ai
#
llm
#
python
#
testing
1
 reaction
Comments
Add Comment
4 min read
Vector RAG can't fix long-context state tracking (33 runs, zero variance)
he fangsheng
he fangsheng
he fangsheng
Follow
Aug 5
Vector RAG can't fix long-context state tracking (33 runs, zero variance)
#
ai
#
llm
#
rag
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