cd/entity/Alpaca· home› entities› Alpaca
grep -l @alpaca /news/*.json | wc -l → 24

Alpaca

mentions 24 type Organization page 1/2 feed RSS

// recent coverage 24 mentions

16:40
2026-10-01
gilesthomas.com
large-language-models

Why do OpenAI's GPT-2 weights beat mine? Part five: data quality

Independent LLM-from-scratch experiments found that OpenAI's GPT-2 small (124M parameters) consistently outperformed the author's 163M-parameter models on an instruction fine-tuning task adapted from …

14:00
2026-09-12
openalternative.co
ai-products

alphai-tui

Alphai-tui, an MIT-licensed terminal dashboard written in Rust, launched as an open source tool that combines live price data, candlestick charts, and AI-scored news in a single terminal process. The …

00:00
2026-09-08
mindstudio.ai
artificial-intelligence

How to Turn GPT-6 Astra Into a 24/7 Stock Trading Bot

A practical guide explains how to configure OpenAI's GPT-6 Astra with the Alpaca brokerage API and scheduled tasks to create a 24/7 automated stock trading bot. The setup uses a fixed daily schedule, …

00:00
2026-08-18
zonted.com
artificial-intelligence

I Shut Down My Autonomous Trading Crons

On August 18, 2026, the operator of an autonomous Alpaca paper-trading system removed all seven scheduler jobs that directly ran, monitored, reviewed, or published the trading apprentice, leaving 16 j…

18:13
2026-07-30
gilesthomas.com
large-language-models

Why do OpenAI's GPT-2 weights beat mine? Part two: the bugfix

A bug in the evaluation code for GPT-2 style models caused incorrect baseline numbers, but OpenAI's original weights still outperform the author's models on instruction-following tasks. The bug involv…

15:00
2026-07-29
gilesthomas.com
large-language-models

Why do OpenAI's GPT-2 weights beat mine?

OpenAI's original GPT-2 small and medium weights consistently outperform custom-trained models in instruction-following evaluations, despite some custom models achieving better test loss, according to…

13:24
2026-07-10
arxiv.org
large-language-models

DominoTree

Researchers introduced DominoTree, a training-free best-first draft tree method for speculative decoding that uses Domino's conditional correction to achieve up to 6.6x speedup over autoregressive dec…

page 1 / 2 next →
// co-occurs with top 8 entities
// topics top 6 topics