Skip to content

Forem

# llm

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

Apr 29

Prompt Caching Works. Your Prompt Assembly Code Does Not.

#ai #llm #rag #machinelearning

4 min read

Edy Silva

Apr 29

Opus 4.7 vs GLM 5.1: is mixing models worth it?

#llm #ai #opus #glm

13 min read

kiwi_tech

Apr 29

Upgrading Kiwi-chan’s Brain: Pushing a 30GB "Frankenstein" GPU Rig to the Limit with Qwen 3.6-35B-A3B

#agents #ai #llm #rag

4 min read

soy

Apr 29

Mistral Medium 3.5 GGUF, FlashQLA Boost for Qwen, & Ollama Playground

#ai #llm #selfhosted

3 min read

Cover image for When the Reranker Hurts: Recall@5 Cases Where Two-Stage Retrieval Loses to One

Apr 29

When the Reranker Hurts: Recall@5 Cases Where Two-Stage Retrieval Loses to One

#ai #rag #llm #benchmark

7 min read

Cover image for Why Strict JSON Mode Doesn't Stop Hallucinated Tool Calls

Apr 29

Why Strict JSON Mode Doesn't Stop Hallucinated Tool Calls

#ai #llm #agents #python

7 min read

Cover image for Every LLM Eval Library Has the Same Bug: Stochastic Judges Used as Deterministic Oracles

Apr 29

Every LLM Eval Library Has the Same Bug: Stochastic Judges Used as Deterministic Oracles

#ai #testing #llm #observability

7 min read

Anikalp Jaiswal

Apr 29

Local AI Accessibility, JetBrains’ 2026 IDE Plans, and Agentic Architecture Pitfalls

#ai #technology #machinelearning #llm

2 min read

Pascal van Kooten

Apr 29

Announcing Cliche

#showdev #llm #opensource #python

3 min read

Cover image for Anthropic Prompt Caching Saves 90% — Here's the One Caveat Nobody Mentions

Apr 29

Anthropic Prompt Caching Saves 90% — Here's the One Caveat Nobody Mentions

#anthropic #llm #python #performance

7 min read

Cover image for Why I Built an AI That Tries to Destroy Your Legal Argument

Apr 29

Why I Built an AI That Tries to Destroy Your Legal Argument

#ai #agents #llm

11 min read

Cover image for Building an AI Agent That Owns Post-Call Execution: Architecture Decisions

SpurIQ Engineering

Apr 29

Building an AI Agent That Owns Post-Call Execution: Architecture Decisions

#ai #architecture #llm #revenue

6 min read

Cover image for Tokenizer Quirks: Claude, GPT, and Gemini Don't Count the Same Text the Same Way

Apr 29

Tokenizer Quirks: Claude, GPT, and Gemini Don't Count the Same Text the Same Way

#ai #llm #python #tokenization

6 min read

Cover image for The Hidden Tax of Structured Output: How Much Extra You Pay for JSON Mode

Apr 29

The Hidden Tax of Structured Output: How Much Extra You Pay for JSON Mode

#llm #openai #anthropic #python

7 min read

Cover image for When 'Take a Deep Breath' Stopped Working: Prompt Tricks With an Expiry Date

Apr 29

When 'Take a Deep Breath' Stopped Working: Prompt Tricks With an Expiry Date

#ai #llm #promptengineering #machinelearning

7 min read

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