Llm Page 209

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

Cover image for Reducing LLM Cost and Latency Using Semantic Caching

Kuldeep Paul

Mar 9

Reducing LLM Cost and Latency Using Semantic Caching

#ai #llm #performance #tutorial

5 min read

Cover image for I caught Claude Sonnet 4 inventing facts about a fake tool

Ken Imoto

Apr 11

I caught Claude Sonnet 4 inventing facts about a fake tool

#ai #llm #claude #contextengineering

9 min read

DavidAI311

Mar 8

Claude Designed Its Own Rule System — A Public Experiment

#discuss #ai #llm #productivity

4 min read

André N. Darcie

Mar 8

Qwen3.5 rodando localmente: super rápido e com ótima qualidade

#ai #llm #opensource #performance

2 min read

Ultra Dune

Mar 12

The Great LLM Inference Engine Showdown: vLLM vs TGI vs TensorRT-LLM vs SGLang vs llama.cpp vs Ollama

#ai #machinelearning #llm #mlops

10 min read

Venkata Manideep Patibandla

Apr 11

I Built a Benchmark That Proves Most LLM Agents Are Statistically Blind And Why That Costs Companies Real Money

#llm #ai #machinelearning #agile

3 min read

Behavioral science over ignored rule lists

Li-Hsuan Lung

Apr 8

How We Use Gherkin, Envelopes, and Schemas to Shape Agent Behavior

#agents #ai #llm #promptengineering

7 min read

InstaTunnel

Mar 8

The Evolution of Developer Tunnels: Bridging Local AI Experiments to the Cloud

#ai #llm #mcp #networking

9 min read

Cover image for Running AI in the Browser with Gemma 4 (No API, No Server)

System Rationale

Apr 11

Running AI in the Browser with Gemma 4 (No API, No Server)

#ai #javascript #llm #webdev

2 min read

Daniil Ratnikau

Apr 11

JGuardrails: Production-Ready Safety Rails for Java LLM Applications

#ai #programming #java #llm

14 min read

Cover image for I built a constitution for AI agents — budgets, permissions, and audits enforced before execution

Justin Yuan

Mar 8

I built a constitution for AI agents — budgets, permissions, and audits enforced before execution

#showdev #agents #ai #llm

2 min read

Cover image for I turned OpenAI Symphony into a one-command local workflow for any repo

Ntty

Mar 12

I turned OpenAI Symphony into a one-command local workflow for any repo

#llm #code #linear #openai

1 min read

Tom Lee

Mar 31

The Model Isn't the Bottleneck — Your Prompt Structure Is

#contextengineering #soulspec #llm #prompting

3 min read

Nathan Sportsman

Mar 12

When Proxies Become the Attack Vectors in Web Architectures

#ai #cybersecurity #llm

5 min read

Grontis Kostis

Mar 9

From Chatting to Reading: Teaching Pebbles to See My Code

#showdev #ai #api #llm

5 min read

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

Forem

# llm

Reducing LLM Cost and Latency Using Semantic Caching

I caught Claude Sonnet 4 inventing facts about a fake tool

Claude Designed Its Own Rule System — A Public Experiment

Qwen3.5 rodando localmente: super rápido e com ótima qualidade

The Great LLM Inference Engine Showdown: vLLM vs TGI vs TensorRT-LLM vs SGLang vs llama.cpp vs Ollama

I Built a Benchmark That Proves Most LLM Agents Are Statistically Blind And Why That Costs Companies Real Money

How We Use Gherkin, Envelopes, and Schemas to Shape Agent Behavior

The Evolution of Developer Tunnels: Bridging Local AI Experiments to the Cloud

Running AI in the Browser with Gemma 4 (No API, No Server)

JGuardrails: Production-Ready Safety Rails for Java LLM Applications

I built a constitution for AI agents — budgets, permissions, and audits enforced before execution

I turned OpenAI Symphony into a one-command local workflow for any repo

The Model Isn't the Bottleneck — Your Prompt Structure Is

When Proxies Become the Attack Vectors in Web Architectures

From Chatting to Reading: Teaching Pebbles to See My Code