DEV Community

#llm

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Gemini 3.8 Flash vs 3.7 Flash : Nouveautés et faut-il mettre à jour ?

Gemini 3.8 Flash vs 3.7 Flash : Nouveautés et faut-il mettre à jour ?

1
Comments
11 min read
Comparing INT4 and NVFP4 Palettes on Real Gradient Tensors

Comparing INT4 and NVFP4 Palettes on Real Gradient Tensors

1
Comments 2
7 min read
Labeling unsafe text without a moderation endpoint: chat completions and a JSON schema

Labeling unsafe text without a moderation endpoint: chat completions and a JSON schema

Comments
8 min read
5 Practical RAG Challenges and How to Mitigate Them

5 Practical RAG Challenges and How to Mitigate Them

5
Comments
5 min read
Gemini 3.8 Flash vs Claude Fable 5.1 vs GPT-5.6 Sol: which API should developers use?

Gemini 3.8 Flash vs Claude Fable 5.1 vs GPT-5.6 Sol: which API should developers use?

1
Comments
12 min read
CTXLENS - like du for tokens

CTXLENS - like du for tokens

Comments
2 min read
Self-Hosting an LLM: The Essentials, and When It's Worth It

Self-Hosting an LLM: The Essentials, and When It's Worth It

Comments
3 min read
9 RAG Techniques That Actually Improve Retrieval Quality

9 RAG Techniques That Actually Improve Retrieval Quality

5
Comments 2
12 min read
My Agent Found Real Improvements. The Statistics Still Killed the Promotion.

My Agent Found Real Improvements. The Statistics Still Killed the Promotion.

11
Comments 3
6 min read
I built a browser-based AI news briefing tool.

I built a browser-based AI news briefing tool.

Comments 1
1 min read
How to add PII redaction and audit logs to LiteLLM without the Enterprise license

How to add PII redaction and audit logs to LiteLLM without the Enterprise license

1
Comments 3
3 min read
Beyond the Chatbot: Building Production AI Systems on AWS

Beyond the Chatbot: Building Production AI Systems on AWS

1
Comments 1
4 min read
What I Learned Evaluating LLMs Across Four Languages

What I Learned Evaluating LLMs Across Four Languages

Comments
4 min read
Run your AI subscription 24 hours a day — use the quota you already pay for

Run your AI subscription 24 hours a day — use the quota you already pay for

2
Comments
9 min read
Automating LLM Answer Evaluation with a Small Python Scoring Script

Automating LLM Answer Evaluation with a Small Python Scoring Script

Comments
3 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.