A week of AI coding cut a quantum-safe bitcoin transaction estimate from $320 to $66

Agentes LLM: un presupuesto para cada acción

Un agente LLM puede redactar un plan excelente y aun así ejecutar una acción equivocada. El riesgo aparece cuando una herramienta le permite enviar un correo, crear una cuenta o repetir una operación…

3h ago ·dev.to

Early rogue AI agent activity and attempts to hack found on urlquery.net

4h ago ·transluce.org

In 2018 I hand-wrote a C++ deep learning framework so I'd never pad a batch. In 2023 LLM serving landed on the same structure.

There's a sentence in the README of a library I wrote that I've been thinking about lately: "To summarize, we believe that Padding-free Dynamic Batching is the feature that NLPers will dive into but…

• In 2018, master's student created C++ deep learning library InsNet
• InsNet's design eliminated need for padded tensors by using flat buffers
• Batching in InsNet grouped nodes by type signature, not input shape

3h ago ·dev.to

Claude Code Subagents Were 48% of My Bill. Their Output Was 0.9%

I thought my expensive Claude Code habit was long sessions. I was half right. When I finally broke down a month of usage, Claude Code subagents cost 48% of my entire bill , and the tokens they wrote…

• Claude Code subagents comprised 48% of the budget
• Subagents' output accounted for only 0.9% of costs
• Fan-out workflows drove 48% of the expense

3h ago ·dev.to

The Cleaner vs Data Leaks: Sanitizing LLM Context

In Part 1 of this series , we laid out the anatomy of an agentic disaster and introduced our in-process tactical squad: The AG-Men .

• The Cleaner prevents data leaks by sanitizing LLM context.
• Operates on zero-trust doctrine, masking PII in memory.
• Intercepts payloads at front door and tool boundary to enforce boundary isolation.

3h ago ·dev.to