DEV Community

# llms

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
ChatGPT Voice Mode Runs on GPT-4o. That's the Problem.

ChatGPT Voice Mode Runs on GPT-4o. That's the Problem.

Comments
3 min read
MegaTrain: entrenar LLMs de 100B+ parámetros en una sola GPU (y por qué tuve que cerrar la laptop)

MegaTrain: entrenar LLMs de 100B+ parámetros en una sola GPU (y por qué tuve que cerrar la laptop)

Comments
9 min read
LLMs Generate Vulnerable C/C++ Code: Self-Review Fails to Mitigate Security Flaws

LLMs Generate Vulnerable C/C++ Code: Self-Review Fails to Mitigate Security Flaws

Comments
10 min read
Self-Improving Python Scripts with LLMs: My Journey

Self-Improving Python Scripts with LLMs: My Journey

Comments
3 min read
Balancing Theory and Practice: Addressing the Shift in Machine Learning Research Focus

Balancing Theory and Practice: Addressing the Shift in Machine Learning Research Focus

Comments
18 min read
Reduce LLM Hallucinations? Why 'Make-No-Mistakes' Fails

Reduce LLM Hallucinations? Why 'Make-No-Mistakes' Fails

Comments
7 min read
Mid-Career Developer Overcomes Go Plateau: Strategies to Deepen Expertise Beyond LLMs and Tackle Complex Projects

Mid-Career Developer Overcomes Go Plateau: Strategies to Deepen Expertise Beyond LLMs and Tackle Complex Projects

Comments
12 min read
Self-Improving Python Scripts with LLMs: My Journey

Self-Improving Python Scripts with LLMs: My Journey

Comments
3 min read
GLM-5 vs Claude Opus: Why Cheap Models Win for Agents

GLM-5 vs Claude Opus: Why Cheap Models Win for Agents

Comments
8 min read
Gemma 4 Native Thinking Is a Real Developer Shift

Gemma 4 Native Thinking Is a Real Developer Shift

Comments 1
8 min read
Local LLM Coding: $500 GPU Beats Claude: Not the Story

Local LLM Coding: $500 GPU Beats Claude: Not the Story

1
Comments
7 min read
LeCun's $1B EBM Bet: Limitation of LLMs in Formal Reasoning or High-Risk Experiment?

LeCun's $1B EBM Bet: Limitation of LLMs in Formal Reasoning or High-Risk Experiment?

Comments
21 min read
Persona Drift: Why LLMs Go Insane Under Repetition

Persona Drift: Why LLMs Go Insane Under Repetition

Comments
7 min read
I Migrated from OpenAI to Google Gemini and Saved $5K/Month (Here's Why)

I Migrated from OpenAI to Google Gemini and Saved $5K/Month (Here's Why)

Comments
4 min read
Systems Thinking in the Age of AI

Systems Thinking in the Age of AI

2
Comments
5 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.