Llm Page 66 - DEV Community

Skip to content

DEV Community

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

Truong Pham | Moon The Train

Oct 2

QuantDinger's Jev trade filter: fail-open, never backtested

#ai #llm #trading #python

5 min read

Tatiana Radchenko 🇩🇰

Sep 30

My drift board learned to say "I don't know". Here is what it still cannot say.

#llm #observability #opensource #mlops

9 min read

Rcids

Sep 30

I built a Claude Code plugin around a model that only answers yes/no. What worked, what failed, what I measured

#agents #ai #claude #llm

6 min read

Sep 30

Why AI Providers Shouldn’t Grade Their Own Bills

#ai #llm #productivity

7 min read

Nokka

Oct 1

OpenAI เปิดตัว GPT-6.1 Sol ถูกกว่า Astra 5 เท่า พร้อมฉีก Astra ทิ้งกลางงาน DevDay

#thai #ai #openai #llm

2 min read

Sep 30

I built a QEMU sandbox to test if a 4B model (Gemma) can act as an autonomous Linux sysadmin — here are the results (2/3 pass rate)

#ai #agents #automation #llm

2 min read

Giuseppe Sirigu

Oct 1

I ran six coding agents on seven local models, 30 times each

#llm #ai #opensource #selfhosted

5 min read

Sep 30

IKAREM: a zero-dependency Python ASGI framework with built-in MCP tools (looking for people to break it)

#backend #llm #mcp #python

2 min read

Kaggle Benchmarking Challenge Submission

Sep 30

When LLMs don't know a Greek word, they make one up

#kagglechallenge #ai #llm #nlp

5 min read

Sep 30

Running Our First 100 URLs — Real Metrics From VNML Agent Framework

#showdev #ai #llm #performance

2 min read

Sep 30

Uniform INT8 on Recurrent States Is a Default, Not a Decision

#ai #llm #agents

4 min read

Sep 30

# When does an AI agent actually earn its cost? I measured it on 100 questions

#agents #ai #llm #rag

5 min read

2SD Technologies Limited

Oct 5

We stopped trusting our model's citations, so we check them in code

#rag #llm #ai #security

3 min read

Sep 30

Every LLM framework rebuilt the same tool object

#typescript #ai #llm #mcp

8 min read

Oct 13

Your Agent's Prompt Is Not a Permission System: Lessons from Anthropic's Unintended-Actions Report

#ai #security #llm #agents

8 min read

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