Joined November 2014
165 Photos and videos
ramyun retweeted
Michael Schumacher got his 1st victory as a Ferrari driver in Barcelona in June 1996. Lewis Hamilton could get his 1st victory as a Ferrari driver in Barcelona in June 2026. This would be so poetic.
37
451
7,189
94,111
ramyun retweeted
Learning how to work with AI in the cloud is an important skill for devs these days. And in this 23 hour course, @andrewbrown teaches you all the fundamentals of Generative AI. You'll learn about LLMs, AI assistants, prompt engineering, development tools, RAG, and more. freecodecamp.org/news/learn-…
2
51
355
12,089
ramyun retweeted
Lewis 🗣️ "The team did a great job and the upgrades are working as intended, so a big thank you to everyone in Maranello. There’s still a race to run and it won’t be easy, but I’ll give everything." Ready to give it all in Barcelona 🇪🇸
19
144
2,223
50,235
ramyun retweeted
Still not over that lap from LH 👏
52
894
14,100
238,162
🚨| Lewis Hamilton: "This car is going to win races, I'm sure of it. I'm saying this based on the development program we're running and the intensity with which we're working. I'm certain that at some point we'll be able to fight for the win, and I hope it'll be as early as tomorrow, because we've never been this close to the target in qualifying." [photo by Andrea Catalini]
17
142
2,651
42,647
ramyun retweeted
GHOST CAR! 👻 It was mighty tight between Russell and Hamilton ⚔️ Lewis was so close to taking his first pole for Ferrari 🤏 #F1 #BarcelonaGP
274
2,109
27,322
3,360,305
ramyun retweeted
The 177th front row of his career AND Lewis' first for @ScuderiaFerrari 💪 #F1 #BarcelonaGP
140
2,075
30,331
356,804
ramyun retweeted
Ready for the fight, send good vibes
2,115
9,642
92,216
861,076
ramyun retweeted
🫶🏾
402
3,741
49,159
481,980
ramyun retweeted

7
11
63
29,841
Experimenting today with: - PM OS /frame-problems - /decisions for judgement hardening - all with Fable 5 I'm running them as one discovery chain. Let's see how it goes.
3
5
37
10,515
ramyun retweeted
So refreshing to hear Lewis first year at Ferrari be discussed sensibly.
6
87
1,261
34,395
ramyun retweeted
Today, Copilot Notebooks is rolling out to more people across your team, making shared notebook collaboration broadly accessible in the Microsoft 365 Copilot app and OneNote. Learn more! msft.it/6018v9ZPk
5
41
183
16,663
ramyun retweeted
👀 Monaco’da Lewis, Mercedes’in Difüzörünü detaylı bir şekilde incelemişti ve bu hafta Ferrari, Mercedes’in Difüzör çözümünü yasaklattı. Babacım bütün tuşlara basıyor…
112
710
17,633
1,694,921
🚨| Valtteri Bottas on Lewis Hamilton's season so far. "It's been really impressive what he's done so far this year. He's got obviously great momentum, great confidence at the moment. At unique tracks like Monaco, he was really quick and made no mistakes at all. So yeah, it's good to see. I mean, he clearly made like a big step over the winter. I think he just gained that confidence in the car and in himself that he was lacking sometimes last year, which is natural. Yeah, very impressed, even a bit surprised." "I think he's shown that he hasn't lost any of his ability to do great qualifying laps, great races. And yeah, maybe this year's cars suit him a bit better; or maybe it's the first car that has a bit more of his DNA in it. Those small things can make a big difference, because in the end, this sport is all about such fine margins. But yeah, it's good to see." "[In 2025] It seemed like he was really hard on himself as well. So yeah, now he's more in his normal place and that's good to see. Every weekend he's challenged in a different way. And then with qualifying, especially, it's probably part of what he does best all year, right? He just keeps his cool. And it seems like every race he shows another level."
13
103
1,882
78,239
ramyun retweeted
Jun 10
you can use unlimited FREE deepseek v4 pro & flash, minimax m3, gemini 3.5 flash with zero credit card 😳 b. ai giving 500k free credits on signup, no verification needed what you get: - deepseek v4 pro & flash - gemini 3.5 flash - minimax m3 - more frontier models it's openai compatible so you can plug it into any agent or bot. you just swap the base url and your existing tools work full setup guide (bai 500k free credits): step 1: go to b.ai > click "try b. ai" in the top right step 2: sign up with google > any gmail works, burner is fine. step 3: credits appear instantly > 500,000 in your account. no card, no verification need step 4: swap your base url > replace your openai endpoint with b.ai's api endpoint > all your existing tools and agents just work step 5: repeat with a fresh email when you run out > use yourname 1@gmail.com, yourname 2@gmail.com etc > each account gets 500k fresh credits > incognito browser for each one there's also a 1:1 top-up bonus up to $100 if you run through it all meaning you deposit $10, they give $10 free extends your credits without creating new accounts 3 things to test with 500k credits: 1. stress test your agent pipeline across 4 models at once 2. compare model outputs side by side to find your cheapest option 3. run batch inference on a dataset without worrying about cost this is the most generous free credit offer live right now bookmark this and get this before the subsidy pool runs out
Jun 8
AWS gives every new account $200 in free credits and you can use it on Claude Opus 4.8, sonnet 4.6, haiku 4.5, all of them 😳 no anthropic account needed. no credit card required models you can access: - claude opus 4.8 (latest, best for coding and agents, 1M context) - claude opus 4.7 (strong agentic and coding tasks) - claude sonnet 4.6 (best balance of speed and quality) - claude haiku 4.5 (fastest and cheapest, great for high volume) here's exactly how: step 1: create a free AWS account > go to aws.amazon.com > click create a free account > enter your email and create a password > add a credit card (required for verification but you won't be charged if you stay within free credits) > complete phone verification > select the free basic support plan step 2: enable claude on amazon bedrock > go to aws console > search "bedrock" in the top search bar > click amazon bedrock > go to model access in the left sidebar > find anthropic models > click request access > fill out the simple use case form > approval usually takes a few minutes to a few hours step 3: test claude for free > in bedrock click "chat playground" > select your claude model > type any prompt and hit run > you are now running claude on your $200 free credits what $200 in credits gets you: - millions of tokens on claude haiku (cheapest, fastest) - hundreds of thousands on claude sonnet 4.6 - tens of thousands on claude opus 4.8 tips to make credits last: - use haiku for simple tasks (10-20x cheaper than opus) - use sonnet 4.6 for most things - only use opus 4.8 for hard reasoning and coding tasks - check billing dashboard regularly ⚠️ this is claude API access not claudeai pro perfect for developers, builders, and anyone testing AI tools your $200 credits are waiting right now
68
85
850
127,095
ramyun retweeted
Jun 10
Lots of people asked how I used Fable to edit its own launch video so I made a video about that! TLDR it wrote a lot of code & tool calls to use transcription services, ffmpeg, do colorgrading, use the figma mcp, make remotion UI and render it. I didn't touch a video editor.
292
618
9,211
955,952
ramyun retweeted
Jun 9

45
421
2,561
639,123
ramyun retweeted
Releasing a model this capable comes with risks. Without safeguards, Fable 5’s capabilities in areas like cybersecurity could be misused to cause serious damage. Queries on a narrow range of topics will instead receive a response from our next-most-capable model, Opus 4.8.
166
414
7,667
1,223,555
ramyun retweeted
Codex is not just for coding anymore. People are using GPT-5.5 to run farms, build iOS apps, design in Figma, launch businesses and automate workflows. 10 wild use cases. Bookmark this:
43
78
1,115
207,072