Flavio Adamo's banner

Flavio Adamo

@flavioAd • 10,187 subscribers

Human approval layer for Coding Agents • Building https://t.co/myy6vStpTu

Shorts

Looks like they didn’t test light mode…

Looks like they didn’t test light mode…

1,935,482 Aufrufe

Every time Google AI Studio makes an svg i’m like yeah ok this is insane This was literally one shot

Every time Google AI Studio makes an svg i’m like yeah ok this is insane This was literally one shot

461,687 Aufrufe

🚨 GPT-4.5 is impressive! 🚨 This is the most realistic result so far. "write a Python program that shows a ball bouncing inside a spinning hexagon. The ball should be affected by gravity and friction, and it must bounce off the rotating walls realistically"

🚨 GPT-4.5 is impressive! 🚨 This is the most realistic result so far. "write a Python program that shows a ball bouncing inside a spinning hexagon. The ball should be affected by gravity and friction, and it must bounce off the rotating walls realistically"

851,646 Aufrufe

After MORE THAN A YEAR, Meta finally released a model that passes the Hexagon Test and I’m not gonna lie this is weirdly emotional 🥹 sorry guys but history had to be documented!!

After MORE THAN A YEAR, Meta finally released a model that passes the Hexagon Test and I’m not gonna lie this is weirdly emotional 🥹 sorry guys but history had to be documented!!

169,982 Aufrufe

Say hello to my new pet

Say hello to my new pet

129,733 Aufrufe

Alright guys, hear me out I was skeptical about Llama 4 coding skills... until I started comparing it to other models, including the earlier version of GPT-4o This thing is free, open source, and honestly pretty close to GPT-4o (pre-update), wild if you think about it

Alright guys, hear me out I was skeptical about Llama 4 coding skills... until I started comparing it to other models, including the earlier version of GPT-4o This thing is free, open source, and honestly pretty close to GPT-4o (pre-update), wild if you think about it

378,298 Aufrufe

gpt-oss-20b passes the vibe check ✅ no way this is only a 20B model, it’s beating models 2–3x its size

gpt-oss-20b passes the vibe check ✅ no way this is only a 20B model, it’s beating models 2–3x its size

256,252 Aufrufe

Codex on VSCode > copilot (and the UI is so clean 🤌)

Codex on VSCode > copilot (and the UI is so clean 🤌)

207,069 Aufrufe

Thinking ON vs OFF is night and day 👀 2.5 Flash-Lite is probably the best budget model out there right now

Thinking ON vs OFF is night and day 👀 2.5 Flash-Lite is probably the best budget model out there right now

114,839 Aufrufe

Google just released Firebase Studio I tried generating an app, and it didn't go well...

Google just released Firebase Studio I tried generating an app, and it didn't go well...

62,086 Aufrufe

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

Apparently everyone loves the Minecraft benchmark, so I had to give it a try GPT-6 Astra Minecraft one-shot

Apparently everyone loves the Minecraft benchmark, so I had to give it a try GPT-6 Astra Minecraft one-shot

733,415 Aufrufe • vor 1 Tag

Grok 4 just passed the hexagon vibe check ✅ Impressed. It’s actually really good.

Grok 4 just passed the hexagon vibe check ✅ Impressed. It’s actually really good.

4,355,277 Aufrufe • vor 1 Jahr

Got a Fitbit Air and refused to pay another $10/month AI subscription. So I built OpenFit

Got a Fitbit Air and refused to pay another $10/month AI subscription. So I built OpenFit

572,672 Aufrufe • vor 2 Monaten

🚨 o3-mini crushed DeepSeek R1 🚨 "write a Python program that shows a ball bouncing inside a spinning hexagon. The ball should be affected by gravity and friction, and it must bounce off the rotating walls realistically"

🚨 o3-mini crushed DeepSeek R1 🚨 "write a Python program that shows a ball bouncing inside a spinning hexagon. The ball should be affected by gravity and friction, and it must bounce off the rotating walls realistically"

5,040,561 Aufrufe • vor 1 Jahr

I've tested them all... and I think the winner is obvious 👀 "write a Python program that shows a ball bouncing inside a spinning hexagon. The ball should be affected by gravity and friction, and it must bounce off the rotating walls realistically"

I've tested them all... and I think the winner is obvious 👀 "write a Python program that shows a ball bouncing inside a spinning hexagon. The ball should be affected by gravity and friction, and it must bounce off the rotating walls realistically"

966,115 Aufrufe • vor 1 Jahr

Wow, someone already made a whole movie using Veo 3

Wow, someone already made a whole movie using Veo 3

390,537 Aufrufe • vor 1 Jahr

o3 and o4-mini have absolutely NAILED the vibe check ✅ This is best result so far!

o3 and o4-mini have absolutely NAILED the vibe check ✅ This is best result so far!

310,089 Aufrufe • vor 1 Jahr

OpenAI just dropped 3 new models! I've tested them all against 4.5 with the exact same prompt

OpenAI just dropped 3 new models! I've tested them all against 4.5 with the exact same prompt

303,497 Aufrufe • vor 1 Jahr

🚨 GEMINI 3 is finally OUT! Built this fun game in literally 5 minutes and it’s way better at coding than I expected👀

🚨 GEMINI 3 is finally OUT! Built this fun game in literally 5 minutes and it’s way better at coding than I expected👀

181,735 Aufrufe • vor 9 Monaten

🚨 OpenAI just released o1-pro as a standalone model in the API 🚨 I made the hexagon prompt even harder so see if o1-pro can handle it ⬇️

🚨 OpenAI just released o1-pro as a standalone model in the API 🚨 I made the hexagon prompt even harder so see if o1-pro can handle it ⬇️

294,422 Aufrufe • vor 1 Jahr

Google just launched Gemini 2.5 Pro I tested it against o1-pro with the exact same prompt

Google just launched Gemini 2.5 Pro I tested it against o1-pro with the exact same prompt

288,802 Aufrufe • vor 1 Jahr

OpenAI released o3 and o4-mini! I've tested both against the top reasoning models using the exact same prompt

OpenAI released o3 and o4-mini! I've tested both against the top reasoning models using the exact same prompt

262,309 Aufrufe • vor 1 Jahr

🚨 GPT-5.2 is finally OUT! I’ve got early access and it’s a significant upgrade over 5.1 especially in visual understanding and reasoning. The benchmark jumps vs 5.1 speak for themselves: SWE-Bench Pro: 50.8% → 55.6% GPQA Diamond: 88.1% → 92.4% AIME 2025: 94.0% → 100% ARC-AGI-2: 17.6% → 52.9% It’s also surprisingly good with 3D/physics, so of course I had to throw a harder version of our favorite vibe test at it

🚨 GPT-5.2 is finally OUT! I’ve got early access and it’s a significant upgrade over 5.1 especially in visual understanding and reasoning. The benchmark jumps vs 5.1 speak for themselves: SWE-Bench Pro: 50.8% → 55.6% GPQA Diamond: 88.1% → 92.4% AIME 2025: 94.0% → 100% ARC-AGI-2: 17.6% → 52.9% It’s also surprisingly good with 3D/physics, so of course I had to throw a harder version of our favorite vibe test at it

138,391 Aufrufe • vor 8 Monaten

(OpenAI?) Horizon Beta just dropped 👀 My take: same model as Alpha, just different weights (20B / 120B). Lines up with the leaks

(OpenAI?) Horizon Beta just dropped 👀 My take: same model as Alpha, just different weights (20B / 120B). Lines up with the leaks

11,289 Aufrufe • vor 1 Jahr

Keine weiteren Inhalte verfügbar