Skip to content

Forem

# llm

👋 Sign in for the ability to sort posts by relevant, latest, or top.

Cover image for I added a local eval loop to my personal AI assistant — here's what 800 scored interactions taught me

Apr 14

I added a local eval loop to my personal AI assistant — here's what 800 scored interactions taught me

#ai #llm #promptengineering #sideprojects

1 min read

Cover image for Indeed Data API: Extract Structured JSON in 2026

AlterLab

May 7

Indeed Data API: Extract Structured JSON in 2026

#dataextraction #llm #python #datapipelines

8 min read

김이더

Apr 14

To Teach AI How to Remember, First Teach It How to Forget 2/2

#ai #llm #memorybank #math

9 min read

Michael Tuszynski

Apr 14

38% of AI Answers Are Wrong — And It's Your Prompt's Fault

#ai #promptengineering #llm #machinelearning

3 min read

Rost

Apr 14

Anthropic Closes Claude Loophole for Agent Tools

#cloud #hosting #selfhosting #llm

4 min read

Apr 15

Spec-Driven Development Based on DSPI: Design-Specify-Plan-Implement

#dspi #ai #llm #coding

9 min read

Ultra Dune

Apr 14

EVAL #010: The AI Coding Agent Wars — 10 Agents, 4 Architectures, 1 Winner (For Now)

#ai #machinelearning #llm #mlops

12 min read

Cover image for Claude Haiku 4.5 Outperformed Sonnet 4.6 on PR Writing - Context Was the Difference

Apr 14

Claude Haiku 4.5 Outperformed Sonnet 4.6 on PR Writing - Context Was the Difference

#ai #llm #devtools #productivity

5 min read

Apr 14

CARE Loop: A Human-Centered Framework for Local LLM Development

#ai #llm #rag #softwaredevelopment

5 min read

Cover image for Your AI agent does not need a bigger context window

Apr 14

Your AI agent does not need a bigger context window

#python #ai #llm #opensource

5 min read

Janu

Apr 14

Building a Voice-Controlled AI Agent

#agents #llm #nlp #python

1 min read

Cover image for Compare harnesses not models: Blitzy vs GPT-5.4 on SWE-Bench Pro

Apr 14

Compare harnesses not models: Blitzy vs GPT-5.4 on SWE-Bench Pro

#ai #llm #openai #harnessengineering

7 min read

Ishaan-Chaturved1

Apr 14

Building a Voice-Controlled AI Agent using AssemblyAI and Groq

#agents #ai #llm #python

1 min read

Venkata Manideep Patibandla

Apr 15

I Ran 163 Benchmarks Across 10 LLMs So You Don't Have To. Here's What I Found

#ai #llm #performance #tooling

6 min read

Cover image for What Actually Happens When Claude Says "Compacting Our Conversation"

Apr 13

What Actually Happens When Claude Says "Compacting Our Conversation"

#ai #llm #machinelearning

5 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.