Llm Page 461 - DEV Community

Skip to content

DEV Community

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

Vitalii Cherepanov

May 13

I Scaled PHP Until It Broke. Three llama.cpp Patterns Saved It.

#php #llm #performance #programming

10 min read

May 13

Evaluating LLM code reviewers: an offline harness for precision, recall, and routing"

#llm #codereview #evaluation #ai

5 min read

May 13

Why JSON.parse() Fails Silently on Truncated LLM Responses (And What I Did About It)

#ai #llm #programming #python

3 min read

Apr 13

I built an Agent Memory System for myself and got 90.8% (end-to-end) on LongMemEval

#ai #mcp #llm #opensource

7 min read

Apr 10

AI Weekly: 4/1–4/10 | Anthropic Triple Shock Sequel — Mythos Too Dangerous to Ship, Revenue Passes OpenAI, Software Stocks Crash

#ai #machinelearning #tech #llm

9 min read

Andrew Kew

May 13

Your AI agent is the new attack vector. It just wants to help.

#ai #security #llm #agenticai

3 min read

kowshik

Apr 9

Your AI agent isn't broken. It's confidently wrong. Here's the difference

#agents #ai #llm #testing

4 min read

Apr 9

Embeddings Just Went Multimodal: What Sentence Transformers 5.4 Means for RAG

#ai #llm #rag #embeddings

2 min read

Spicy

May 14

SLM vs LLM: How to Pick the Right Model for Your Enterprise Workload

#ai #machinelearning #llm #programming

1 min read

EdFife

May 13

My AI Remembers Its Mistakes. Permanently. Here's the Engineering.

#ai #python #opensource #llm

13 min read

Joseph Yeo

May 13

The Information Design Gap: Why Our AI Agent Was Coding Blind

#agents #ai #llm #softwareengineering

9 min read

Yodit Weldegeorgise

Apr 13

𝗪𝗵𝗮𝘁 𝗜 𝗟𝗲𝗮𝗿𝗻𝗲𝗱 𝗳𝗿𝗼𝗺 𝗖𝗵𝗮𝗽𝘁𝗲𝗿 𝟮 𝗼𝗳 𝗔𝗜 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝗶𝗻𝗴: 𝗪𝗵𝘆 𝗦𝗮𝗺𝗽𝗹𝗶𝗻𝗴 𝗖𝗵𝗮𝗻𝗴𝗲𝘀 𝗘𝘃𝗲𝗿𝘆𝘁𝗵𝗶𝗻𝗴

#ai #deeplearning #llm #machinelearning

4 min read

Apr 9

Anthropic Just Did Something Unprecedented: They Hid Their Best Security Model

#ai #security #anthropic #llm

2 min read

kjyoun-ai

Apr 9

Marker, hosted: a scientific PDF parser API with LaTeX equations preserved

#api #llm #rag #tooling

4 min read

KRISHNAKAANTH REDDY YEDUGURU

Apr 9

RedSOC: Open-source framework to benchmark adversarial attacks on AI-powered SOCs — 100% detection rate across 15 attack scenarios [paper + code]

#security #python #llm #machinelearning

2 min read

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