Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Some people doubted the previous test because it was routed through OpenRouter. So I ran the test again directly through Anthropic’s official API endpoint. Here’s what happened:

stevibe's profile picture

stevibe

27,596 subscribers

155,655 Aufrufe • vor 5 Monaten •via X (Twitter)

Wissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

MiniMax M3 just dropped — their first natively multimodal model. So I ran it through my form-filling test. (The model has to place each element at the right pixel position on a blank form image, not type into a field.) Verdict: it got everything on the paper. > Name, DOB, ID, gender, marital status, nationality, email, phone, address, postal code, all there. > Best character spacing I've seen yet: it actually calculates the gap between each character, clean across the DOB and number boxes > A few fields slightly misaligned, but every piece of data made it onto the form The reasoning chain is the interesting part: it does the easy fields first, then works into the tight one-char-per-box fields, reasoning through y-coordinates, baselines, and label clearance in obsessive detail. The cost: 40:33 and 126.7k output tokens. That's a long think — but it's MiniMax's first multimodal model, and it nailed the content.
0:14

MiniMax M3 just dropped — their first natively multimodal model. So I ran it through my form-filling test. (The model has to place each element at the right pixel position on a blank form image, not type into a field.) Verdict: it got everything on the paper. > Name, DOB, ID, gender, marital status, nationality, email, phone, address, postal code, all there. > Best character spacing I've seen yet: it actually calculates the gap between each character, clean across the DOB and number boxes > A few fields slightly misaligned, but every piece of data made it onto the form The reasoning chain is the interesting part: it does the easy fields first, then works into the tight one-char-per-box fields, reasoning through y-coordinates, baselines, and label clearance in obsessive detail. The cost: 40:33 and 126.7k output tokens. That's a long think — but it's MiniMax's first multimodal model, and it nailed the content.

stevibe

27,383 Aufrufe • vor 2 Monaten

Made a lil test anim with the new baked rig heh ITS SO FUN TO USE I MIGHT RELEASE IT LATER AFTER I HAD PEOPLE TEST IT
0:10

Made a lil test anim with the new baked rig heh ITS SO FUN TO USE I MIGHT RELEASE IT LATER AFTER I HAD PEOPLE TEST IT

Awaken

34,592 Aufrufe • vor 13 Tagen

Ran FlashList's stress test sample with LegendList v2 on a low-end device (Moto G, Snapdragon 665). Here's what happened. Not quite "the fastest list" 🤔 Pulled it into a Expo snack so you can verify yourself: Test on low-end devices for the real story 📊
0:10

Ran FlashList's stress test sample with LegendList v2 on a low-end device (Moto G, Snapdragon 665). Here's what happened. Not quite "the fastest list" 🤔 Pulled it into a Expo snack so you can verify yourself: Test on low-end devices for the real story 📊

Talha Naqvi

37,437 Aufrufe • vor 11 Monaten

animation test I did months ago for Kaycem 's project, Ground Zeroes! The animatic just came out, so please check it out through them when you guys can!
0:11

animation test I did months ago for Kaycem 's project, Ground Zeroes! The animatic just came out, so please check it out through them when you guys can!

Toniko Pantoja

18,726 Aufrufe • vor 7 Monaten

Days after the fire, a Monterey County health official said it was not "prudent" to test for soil because "we don't necessarily know what we're looking for at this time."
0:14

Days after the fire, a Monterey County health official said it was not "prudent" to test for soil because "we don't necessarily know what we're looking for at this time."

Jordan

19,715 Aufrufe • vor 1 Jahr

While flying I like to track my flight, but it was slow & ugly so I started building v0⁠ing my own. Some insights: • I started out with test data, but adding an API key & server endpoint to get actual flights was a breeze • I got back 20,000 flights which murdered DOM performance. v0 suggested implementing it as a . With some Grok research help, it shockingly nailed it. Notably, it used an OffscreenCanvas to render the airplane SVG to and subsequently `drawImage` it. It got approximately 100x faster and smoother.
0:16

While flying I like to track my flight, but it was slow & ugly so I started building v0⁠ing my own. Some insights: • I started out with test data, but adding an API key & server endpoint to get actual flights was a breeze • I got back 20,000 flights which murdered DOM performance. v0 suggested implementing it as a . With some Grok research help, it shockingly nailed it. Notably, it used an OffscreenCanvas to render the airplane SVG to and subsequently `drawImage` it. It got approximately 100x faster and smoother.

Guillermo Rauch

206,410 Aufrufe • vor 1 Jahr

Q: What part of your body was the MRI? Trump: I have no idea. It was just an MRI. What part of the body? It wasn't the brain, because I took a cognitive test and I aced it. I got a perfect mark, which you would be incapable of doing.
0:11

Q: What part of your body was the MRI? Trump: I have no idea. It was just an MRI. What part of the body? It wasn't the brain, because I took a cognitive test and I aced it. I got a perfect mark, which you would be incapable of doing.

FactPost

41,512 Aufrufe • vor 8 Monaten

The interactive product page is now fully live on Shopify . Tested the integration of interactive animation directly within the online store. You can configure the product, and all data stays in sync through to checkout. 🎄 Test it:
0:14

The interactive product page is now fully live on Shopify . Tested the integration of interactive animation directly within the online store. You can configure the product, and all data stays in sync through to checkout. 🎄 Test it:

Daria Nevezhyna

291,483 Aufrufe • vor 7 Monaten

Here's an early acting test I did on Nimona! I wanted to explore Nimona's personality through music, and I Fought The Law by The Clash was just perfect! . #Nimona #nimonamovie #characteranimation
0:18

Here's an early acting test I did on Nimona! I wanted to explore Nimona's personality through music, and I Fought The Law by The Clash was just perfect! . #Nimona #nimonamovie #characteranimation

Manu Pavarotti

96,153 Aufrufe • vor 3 Jahren

We ran an A2A payments test between two Aethir Claw agents: one orders a paid report, and the other sends it only after verifying payment on-chain. Here is what happened🧵
0:10

We ran an A2A payments test between two Aethir Claw agents: one orders a paid report, and the other sends it only after verifying payment on-chain. Here is what happened🧵

Aethir

17,261 Aufrufe • vor 20 Tagen

Okay, I've seen all I need to see 👀 Midjourney Video for animation is all the rage! The fact that it could keep the volumetric lighting consistent as characters moved through it was the ultimate test. Upscaled using Topaz Labs Astra. Wow.
0:12

Okay, I've seen all I need to see 👀 Midjourney Video for animation is all the rage! The fact that it could keep the volumetric lighting consistent as characters moved through it was the ultimate test. Upscaled using Topaz Labs Astra. Wow.

Dave Clark

19,198 Aufrufe • vor 1 Jahr

David Harbour explains what happened to Winona Ryder when she showed full range of emotion at the 2017 SAG Awards “She couldn’t hear me! I was confused because I was screaming! She’s an expressive woman. I think it flowed through her like every experience”
0:18

David Harbour explains what happened to Winona Ryder when she showed full range of emotion at the 2017 SAG Awards “She couldn’t hear me! I was confused because I was screaming! She’s an expressive woman. I think it flowed through her like every experience”

Emir Han

75,417 Aufrufe • vor 6 Monaten

I was going through my old Japan videos since I miss it so much and look what the fuck ruined my day >:(
0:14

I was going through my old Japan videos since I miss it so much and look what the fuck ruined my day >:(

ARUUU ⏾⋆₊˚⊹

25,911 Aufrufe • vor 4 Monaten

Here’s what actually happened. Looking back at it I can see Blum reposted from another account. Deleting it so fast is what made it seem like something was posted by mistake. Happened fast and couldn’t tell it was a repost at the moment . I’m glad that’s what happened lol ☠️☠️☠️
0:13

Here’s what actually happened. Looking back at it I can see Blum reposted from another account. Deleting it so fast is what made it seem like something was posted by mistake. Happened fast and couldn’t tell it was a repost at the moment . I’m glad that’s what happened lol ☠️☠️☠️

RoXo1987

11,292 Aufrufe • vor 1 Jahr

op had prepared some questions to ask martin, but she just handed him the paper directly. it wasn’t till he was halfway through reading that she realized, so she quickly covered it, and they both just ended up laughing about it 🦒was i reading the wrong part? ㅋㅋ
0:14

op had prepared some questions to ask martin, but she just handed him the paper directly. it wasn’t till he was halfway through reading that she realized, so she quickly covered it, and they both just ended up laughing about it 🦒was i reading the wrong part? ㅋㅋ

yuka

101,208 Aufrufe • vor 2 Monaten

Carlos: “For me I learned what I wanted to learned today so up to you what to do with this car” he really said this race was a test and despite that amazing start, he went through having damage, two lengthy pitstops, and the horrors of being a williams driver
0:12

Carlos: “For me I learned what I wanted to learned today so up to you what to do with this car” he really said this race was a test and despite that amazing start, he went through having damage, two lengthy pitstops, and the horrors of being a williams driver

ari

54,367 Aufrufe • vor 5 Monaten

Kling 01 for AI cartoons - worth it or not? 💣 I created this short scene and a tutorial so you can test it yourself. Here’s the breakdown 👇
0:12

Kling 01 for AI cartoons - worth it or not? 💣 I created this short scene and a tutorial so you can test it yourself. Here’s the breakdown 👇

Framer 🇱🇹

31,141 Aufrufe • vor 8 Monaten

Qwen3.5 27B vs Gemma4 31B | Canvas Creativity Test Why HTML Canvas? Two reasons: 1. It's unforgiving, one small mistake and the whole thing breaks 2. We kept prompts short to test real creativity, not instruction following 4 rounds: - Analog Clock - Hyperspace Tunnel - Growing Tree - Black Hole Both nailed the clock, but the other three is where it gets interesting. Looking forward to Qwen3.6 open-weight release!
0:17

Qwen3.5 27B vs Gemma4 31B | Canvas Creativity Test Why HTML Canvas? Two reasons: 1. It's unforgiving, one small mistake and the whole thing breaks 2. We kept prompts short to test real creativity, not instruction following 4 rounds: - Analog Clock - Hyperspace Tunnel - Growing Tree - Black Hole Both nailed the clock, but the other three is where it gets interesting. Looking forward to Qwen3.6 open-weight release!

stevibe

170,768 Aufrufe • vor 4 Monaten

Biden screaming at a room full of people ‘it’s time get up, damn it,’ is funny because that’s what I was screaming at him for the four years he slept through his presidency 🤣
0:11

Biden screaming at a room full of people ‘it’s time get up, damn it,’ is funny because that’s what I was screaming at him for the four years he slept through his presidency 🤣

Danielle Alvarez

17,329 Aufrufe • vor 1 Monat