DEV Community

#llm

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Why I made my eval tool refuse to give a score
ashwin_ugale_102f2abc9cec profile

Why I made my eval tool refuse to give a score

#ai #llm #testing #python
6
Comments
2 min read
Open LLM Gateway: self-hosted LLM control plane (proxy + analytics + admin UI, no seat cap)
nelsonlin profile

Open LLM Gateway: self-hosted LLM control plane (proxy + analytics + admin UI, no seat cap)

#showdev #ai #llm #llmops
Comments
2 min read
Deploying Inference Using NVIDIA Dynamo and vLLM
sharmukh profile

Deploying Inference Using NVIDIA Dynamo and vLLM

#nvidia #vllm #llm #gpu
6
Comments
8 min read
IBM Granite 4.1 8B: The Open-Weight LLM Built for Enterprise RAG — Day 14/30
aiexplore369zoho profile

IBM Granite 4.1 8B: The Open-Weight LLM Built for Enterprise RAG — Day 14/30

#ai #llm #opensource #webdev
Comments
6 min read
My gateway looked fine for 3 days. Then one request took 92 seconds.
keheai_harvey profile

My gateway looked fine for 3 days. Then one request took 92 seconds.

#ai #llm #devops #monitoring
Comments
3 min read
Your Hourly Rate Makes Free Tokens Expensive
hackrs_3352 profile

Your Hourly Rate Makes Free Tokens Expensive

#llm #devops #python #productivity
Comments
7 min read
I built a benchmark for AI companion apps because every "best AI girlfriend" list is affiliate spam
rizzmaster profile

I built a benchmark for AI companion apps because every "best AI girlfriend" list is affiliate spam

#ai #llm #benchmark
Comments 1
5 min read
Can a 27B Coding Model Be Useful on a 16GB GPU?
arczhi profile
arczhi

Can a 27B Coding Model Be Useful on a 16GB GPU?

#agents #ai #llm #softwaredevelopment
Comments
2 min read
Gemini 3.8 Flash vs 3.7 Flash : NouveautÃĐs et faut-il mettre à jour ?
antoine_laurentt profile

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

#ai #gemini #google #llm
Comments
11 min read
āđ€āļˆāļĄāļīāđ„āļ™ 3.8 āđāļŸāļĨāļŠ: āđ€āļ›āļĢāļĩāļĒāļšāđ€āļ—āļĩāļĒāļšāļĢāļ°āļ”āļąāļšāļāļēāļĢāļ„āļīāļ” āļ•āđˆāļģ āļ›āļēāļ™āļāļĨāļēāļ‡ āļŠāļđāļ‡ āļžāļĢāđ‰āļ­āļĄāđ€āļŦāļ•āļļāļœāļĨāļ—āļĩāđˆāļĢāļ°āļ”āļąāļš Minimal āļŦāļēāļĒāđ„āļ›
thanawat_wonchai profile

āđ€āļˆāļĄāļīāđ„āļ™ 3.8 āđāļŸāļĨāļŠ: āđ€āļ›āļĢāļĩāļĒāļšāđ€āļ—āļĩāļĒāļšāļĢāļ°āļ”āļąāļšāļāļēāļĢāļ„āļīāļ” āļ•āđˆāļģ āļ›āļēāļ™āļāļĨāļēāļ‡ āļŠāļđāļ‡ āļžāļĢāđ‰āļ­āļĄāđ€āļŦāļ•āļļāļœāļĨāļ—āļĩāđˆāļĢāļ°āļ”āļąāļš Minimal āļŦāļēāļĒāđ„āļ›

#ai #gemini #llm
Comments
4 min read
Gemini 3.8 Flash vs 3.7 Flash: Perbedaan dan Haruskah Anda Upgrade?
walse profile
Walse

Gemini 3.8 Flash vs 3.7 Flash: Perbedaan dan Haruskah Anda Upgrade?

#ai #gemini #google #llm
Comments
10 min read
Gemini 3.8 Flash āđ€āļ—āļĩāļĒāļšāļāļąāļš 3.7 Flash: āđ€āļ›āļĨāļĩāđˆāļĒāļ™āđ„āļ›āđāļ„āđˆāđ„āļŦāļ™ āļ„āļļāđ‰āļĄāļ„āđˆāļēāļ—āļĩāđˆāļˆāļ°āļ­āļąāļ›āđ€āļāļĢāļ”āđ„āļŦāļĄ
thanawat_wonchai profile

Gemini 3.8 Flash āđ€āļ—āļĩāļĒāļšāļāļąāļš 3.7 Flash: āđ€āļ›āļĨāļĩāđˆāļĒāļ™āđ„āļ›āđāļ„āđˆāđ„āļŦāļ™ āļ„āļļāđ‰āļĄāļ„āđˆāļēāļ—āļĩāđˆāļˆāļ°āļ­āļąāļ›āđ€āļāļĢāļ”āđ„āļŦāļĄ

#ai #gemini #google #llm
Comments
4 min read
What I Learned Evaluating LLMs Across Four Languages
zahid23saim profile

What I Learned Evaluating LLMs Across Four Languages

#ai #llm #nlp
Comments
3 min read
Your context window bills you every turn
ferhatatagun profile

Your context window bills you every turn

#claude #anthropic #llm #observability
Comments 1
5 min read
Automating LLM Answer Evaluation with a Small Python Scoring Script
zahid23saim profile

Automating LLM Answer Evaluation with a Small Python Scoring Script

#automation #llm #python #tutorial
Comments
3 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.