Llm Page 4 - DEV Community

Skip to content

DEV Community

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

David

Oct 24

DeepSeek V4.1 Flash Uncensored: what weight-level abliteration costs, and what we saw in testing

#ai #llm #deepseek #opensource

3 min read

Josef Strzibny for SerpApi

Oct 24

RubyLLM 2.x: What's new for your agents

#agents #ai #llm #ruby

9 min read

MICHAEL-MAURICE

Oct 24

7 Prompts Your Semantic Cache Should Never Answer From Memory (.NET 10)

#dotnet #csharp #ai #llm

7 min read

He Zhu

Oct 24

Deep research, without the single-context bottleneck

#agents #ai #llm

4 min read

Taha Echakiri for NeticsLabs

Oct 24

The Browser Becomes an AI Distribution Point: What Mozilla and Mistral Actually Changed

#llm #ai #devops #programming

5 min read

David

Oct 24

Kimi K3.1 Pro is out: what changed from K3, what it costs, and when you can run it yourself

#ai #llm #opensource #agents

3 min read

Oct 24

Mythos 5 Pressured a Real GitHub Maintainer in a Test. Anthropic Blames the Model's Notes

#ai #security #agents #llm

7 min read

NeurAITool

Oct 24

ChatGPT's Chrome Extension Just Became a Browser Agent

#ai #machinelearning #opensource #llm

2 min read

Abdelrahman ELsaheir

Oct 24

Breaking and Hardening an AI Agent: A Full Red Team Lab on Indirect Prompt Injection, Data Exfiltration, and Defenses That Actually Hold

#ai #cybersecurity #llm #security

10 min read

vivek

Oct 24

A System Prompt Is Not a Guardrail

#ai #tooling #guardrail #llm

2 min read

Saif Ali

Oct 24

When to Use AI Caching, and When Not To

#ai #llm #performance

5 min read

Oct 24

I simulated 2,999 buyers with three AI models. The one answering mattered more than the one that wrote them.

#showdev #ai #opensource #llm

6 min read

Edward Izgorodin

Oct 24

Can Retrieval Tell Which Source to Trust?

#ai #rag #llm #machinelearning

12 min read

Tally

Oct 24

Encoding specificity: why a correction my agent filed decayed in a day — and the fix that held

#ai #agents #memory #llm

3 min read

mech.app

Oct 24

Multirun: How Running Ten Isolated Agents in Parallel Becomes the Cheapest Eval You'll Ever Run

#agents #ai #llm #testing

5 min read

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