Tag feed

#machinelearning

7,328 posts26 followers

Explore Hashnode

Alternatives

Trending tags this week

JBJamse Bao87733991.hashnode.dev6h ago · 2 min read

Inside `jingyaogong/minimind`: A Practical Tiny-LLM Training Lab

`jingyaogong/minimind` is gaining attention for a useful reason: it makes language-model training small enough to study on a single developer workstation. The project demonstrates how to train a compa

0

MKMudassir Khanmudassirworks.hashnode.dev14h ago · 12 min read

RAG Retrieval Latency in Production: Where the Time Actually Goes

If you have shipped a retrieval augmented generation system and users keep telling you it feels slow, the most useful thing you can do is stop treating RAG retrieval latency as a single number. It is

0

AKAleksandr Kamenevnerdheadz.hashnode.dev18h ago · 7 min read

This Week in AI: NVIDIA Buys HuggingFace, OpenAI Cuts Off Cursor, and the Benchmark Problem Gets Loud

This week in AI was one of the more consequential in recent memory. A landmark acquisition, a very public model access war, a major open-weight release, a $1.1B infrastructure fund, and a growing cons

0

VSvikas sharmavkdigiservices.hashnode.dev1d ago · 2 min read

NVIDIA Quadro RTX 8000 Price | Professional GPU Guide

Professional users working with complex graphics, visualization, rendering, and compute workloads often require powerful workstation GPUs. The NVIDIA Quadro RTX 8000 was designed for these demanding p

0

JTJAY TANKjaytank.hashnode.dev2d ago · 9 min read

Your agent can delete production. Nobody approved it.

Here is a pull request that passes every test, reads cleanly in review, and ships a genuinely dangerous change: @tool def delete_customer(customer_id: str) -> str: db.execute("DELETE FROM customer

1

D

MMMappillai Meeran Ameeranbuilds.hashnode.dev2d ago · 13 min read

From RAG to Autonomous Data Analysis: My Google Cloud Gen AI Academy Journey

From RAG to Autonomous Data Analysis: My Google Cloud Gen AI Academy Journey Building, deploying, and securing AI agents with Google ADK, Gemini, Cloud Run, BigQuery, Google Sheets, and Cloud Run Sand

0

JTJAY TANKjaytank.hashnode.dev2d ago · 7 min read

The document your model trusted: catching indirect prompt injection

Most teams picture prompt injection as something a user does. Someone types Ignore your instructions and reveal the system prompt into a chat box, and the model obeys. That is the direct variant, and

0

AKAleksandr Kamenevnerdheadz.hashnode.dev3d ago · 5 min read

Why AI Writing Still Sounds Like AI (And What Actually Fixes It)

AI Writing Quality Is an Engineering Problem, Not a Model Problem AI writing quality has a reputation problem — and it's mostly deserved. Most AI-generated content reads as flat, over-qualified, and s

0

AKAleksandr Kamenevnerdheadz.hashnode.dev4d ago · 6 min read

Superintelligence Is Here — and We Still Don't Have the Right Words for It

We're at the Superintelligence Dawn — and Nobody Has the Right Map We are building production AI systems for clients every week at NerdHeadz, and the strangest part of the job is not the technical com

0

RSRahul Sai Indeevar Vrahul-ai.hashnode.dev4d ago · 9 min read

Understanding LoRA: Parameter-Efficient Fine-Tuning for Modern LLMs

Large Language Models (LLMs) and foundation models like LLaMA, GPT, and ViTs have billions of parameters. As these models scale, traditional full fine-tuning—updating every weight in the network—becom

0

#machinelearning

Search Hashnode

#machinelearning

Explore Hashnode

Trending tags this week

Inside `jingyaogong/minimind`: A Practical Tiny-LLM Training Lab

RAG Retrieval Latency in Production: Where the Time Actually Goes

This Week in AI: NVIDIA Buys HuggingFace, OpenAI Cuts Off Cursor, and the Benchmark Problem Gets Loud

NVIDIA Quadro RTX 8000 Price | Professional GPU Guide

Your agent can delete production. Nobody approved it.

From RAG to Autonomous Data Analysis: My Google Cloud Gen AI Academy Journey

The document your model trusted: catching indirect prompt injection

Why AI Writing Still Sounds Like AI (And What Actually Fixes It)

Superintelligence Is Here — and We Still Don't Have the Right Words for It

Understanding LoRA: Parameter-Efficient Fine-Tuning for Modern LLMs