AllyshipContent Radar

Hands-on 278

Công cụ, thử nghiệm và hướng dẫn thực hành

Crawl live-1795090500000 · 19:15 19 thg 11, 2026 · Xuất bản 19:35 19 thg 11, 2026

133

Should you rely on public benchmark scores when choosing a model? @VikParuchuri argues "no" in this talk.

26.9

Hướng dẫn hamelhusain

Should you rely on public benchmark scores when choosing a model? @VikParuchuri argues "no" in this talk. To illustrate this, he shows specific problems found in popular OCR benchmarks: ParseBench: • A test expects 310 gigawatts of solar-panel capacity when the correct value is 303. Additionally, 73% of its chart tests ask for values that aren't printed on the chart. (4:51) • A test requires "Parish Priest:" to be bold even though those words aren't bold in the source document. (15:33) • The scorer fails to recognize heading tags placed on separate lines. (16:15) • dots.mocr ranks last among six models even though it beats the first-ranked model on content and tables. This is an example of how overall benchmark score can hide important differences in model capabilities. (14:48) olmOCR-bench: • A model correctly preserves a line break in a document and gets penalized for it. (10:30) • A test expects "Republican Party" when a document says "Republican party". Copying the capitalization correctly makes the model fail. (10:49) • A 700-line postprocessor that rewrites model output adds 1 to 2 points, more than many gaps between models. (12:12) OmniDocBench: • This benchmark uses edit distance, which penalizes a correct table written in HTML more heavily than a wrong number in Markdown. So the format matters more than the answer! (6:58) This is just the tip of the iceberg, the video contains more examples. Chapters: 0:00 Choosing a model when every vendor claims to be #1 1:54 How OCR benchmark scores improve without better OCR 5:30 Metric design and tests that reject correct answers 11:33 Postprocessing, saturation, and misleading model rankings 12:40 How to slice benchmarks by your task and check for bias 16:53 How to build fair tests with verified answers and consistent scoring 19:05 How to test OCR models on your own documents 24:10 Benchmark marketing, private evals, and how to choose a model Media

X · 3 thg 11, 2026

Nguyên văn nguồn
Chi tiết nguồn
134

this video is an absolute masterclass on how to sell grokbot to businesses for a lot of money.

26.7

Hướng dẫn nickvasilescu

this video is an absolute masterclass on how to sell grokbot to businesses for a lot of money. in this episode, we talk about: - how to exactly build a vertical customized grokbot for businesses - what is the stack - what is the building process - what is the offer - how do you get leads - and how do you sell them. we go through literally every tool and step-by-step process that you need in this entire video and it's all under one hour. highly, highly recommend if there's one video you watch from me, this is the one.

X · 3 thg 11, 2026

Nguyên văn nguồn
Chi tiết nguồn
135

Setting up Grok Bots for boring businesses/SMBs might be one of the best AI businesses right now

26.7

Hướng dẫn gregisenberg

Setting up Grok Bots for boring businesses/SMBs might be one of the best AI businesses right now Give every agent its own computer, email, phone #, then charge like you're hiring an employee for $12 an hour Here's the whole plan: the stack, the offer and how to get customers. Media

X · 3 thg 11, 2026

Nguyên văn nguồn
Chi tiết nguồn
137

We asked Mistral Large 4 to show what happens when you break a molecule. ⚛️

26.0

Hướng dẫn mistralai

We asked Mistral Large 4 to show what happens when you break a molecule. ⚛️ With a short prompt, it wrote a quantum chemistry SCF solver from scratch, validated its output, and built a 3D view around it. Le Chonk also understand chemistry enough to independently choose how to break the molecule and what orbitals to show, without further input. 🧵 Media

X · 2 thg 11, 2026

Nguyên văn nguồn
Chi tiết nguồn
133–138 / 179
Trang 23 / 30