Ioannis Sintos

425 posts

Ioannis Sintos banner
Ioannis Sintos

Ioannis Sintos

@iocentos

Head of Applied AI @MiroHQ | Co-Founder & CIO @uizard (acquired by Miro) | Empowering teams to create the next big thing 🚀

Copenhagen 🇩🇰 / Greece 🇬🇷 Katılım Temmuz 2016
507 Takip Edilen1.1K Takipçiler
Sabitlenmiş Tweet
Ioannis Sintos
Ioannis Sintos@iocentos·
Autodesigner 2.0 is here. Our most capable design AI engine! You can now have chatGPT style conversations with your designs and iterate like never before. Watch the keynote ➡️ lnkd.in/dcqKkNsY
uizard ✨ by Miro Labs@uizard

✨ Next level generative UI design is here ✨ The most popular UI generator just got even better! With Autodesigner 2.0, type out your ideas in plain text to design, prototype and iterate in seconds. #autodesigner #uizard #generativeui

English
6
0
8
882
Mario Zechner
Mario Zechner@badlogicgames·
People of pi. Weekend release. Also unbreaks my keybinding breakage. Sorry.
Mario Zechner tweet media
English
5
0
47
2.6K
Ioannis Sintos
Ioannis Sintos@iocentos·
Don't have instability issues. But, oftentimes, when scrolling, you can tell the Algo has different personalities. Oftentimes, it focuses on my interests and feel like learning, and in the next session feels like I am on Instagram or tiktok, just click bait stuff, random videos regardless of my topics and interests. Not sure if it runs out of recommendations and then defaults to generic content.
English
0
0
0
14
Diana Dukic
Diana Dukic@diana_dukic·
Went from scrolling 24/7 to not even wanting to log in. X just hasn’t been hitting the same lately.
English
504
151
5K
1.3M
Ioannis Sintos
Ioannis Sintos@iocentos·
@rohit4verse Very interesting read, thank you. Also, +1 for the awesome harness repo reference, lots of material to follow up there.
English
0
0
1
100
Andrej Karpathy
Andrej Karpathy@karpathy·
Expectation: the age of the IDE is over Reality: we’re going to need a bigger IDE (imo). It just looks very different because humans now move upwards and program at a higher level - the basic unit of interest is not one file but one agent. It’s still programming.
Andrej Karpathy@karpathy

@nummanali tmux grids are awesome, but i feel a need to have a proper "agent command center" IDE for teams of them, which I could maximize per monitor. E.g. I want to see/hide toggle them, see if any are idle, pop open related tools (e.g. terminal), stats (usage), etc.

English
817
836
10.6K
2.4M
Santiago
Santiago@svpino·
Agentic AI is stupid, and brittle, and unreliable, but it's getting better every single week. I decided to spend my time right now learning, building, and dealing with all of these problems. You don't have to do this. You can wait until agentic AI is perfect, works every time, is production-worthy, and all of it is beautiful and pink. But I don't want to wait. I think I have an advantage by starting early. For those of you who can't handle nuance, I'm sorry to say this: 1. Agentic AI is both amazing and dumb right now 2. It doesn't work most of the time, but I'll keep using it 3. It's not reliable, but you should start building with it
English
127
29
412
34.7K
Ioannis Sintos
Ioannis Sintos@iocentos·
@Hesamation It was a matter of time anyway. The mold example would be true if we didn't move to anything new. Hopefully, we'll transition to more native paradigms in which case that knowledge base wouldn't serve any purpose anymore, besides helping the transition.
English
0
0
0
27
ℏεsam
ℏεsam@Hesamation·
this is a catastrophe. StackOverflow provided data to LLMs, LLMs replaced StackOverflow, and now no new Q&A hub exists to provide fresh data. it’s a self-undermining causal loop, like mold growing on food, consuming it, and dying once the food is gone.
Pedro Domingos@pmddomingos

RIP Stack Overflow.

English
917
3.8K
39.7K
2.4M
Ioannis Sintos
Ioannis Sintos@iocentos·
💯 We are "stuck" with text not because it's the best solution but because we haven't yet cracked the needed paradigm. "The GUI is an intelligent canvas" is exactly what we are building at @MiroHQ and already making great progress there. Plenty of work ahead of us to nail the experience, but early feedback is very positive. Glad you also see it that way. It's a great confirmation.
English
0
0
2
172
Andrej Karpathy
Andrej Karpathy@karpathy·
Imo this is along the lines of how talking to an LLM via text is like typing into a DOS Terminal and "GUI hasn't been invented yet" of some of my earlier posts. The GUI is an intelligent canvas.
English
69
132
3.2K
272.9K
Andrej Karpathy
Andrej Karpathy@karpathy·
Gemini Nano Banana Pro can solve exam questions *in* the exam page image. With doodles, diagrams, all that. ChatGPT thinks these solutions are all correct except Se_2P_2 should be "diselenium diphosphide" and a spelling mistake (should be "thiocyanic acid" not "thoicyanic") :O
Andrej Karpathy tweet media
English
322
953
8.9K
3M
Ioannis Sintos
Ioannis Sintos@iocentos·
The amount of AI generated content in the feed the last few months is through the roof and it's slowly making me less and less interested in using X. Any chance we get a human only feed where we know it's filtered to only show authentic human created content? @elonmusk
English
2
0
5
237
Ioannis Sintos
Ioannis Sintos@iocentos·
Or maybe @grok can actually help here with the steering of the algo. Either way, it's getting to a level that is a bit frustrating having so much fake content or so much non well thought out content. Obviously this is a problem across platforms but X here could lead the pack with an alternative or a solution to this problem.
English
1
0
1
53
jen cho
jen cho@jenfromjan·
love you figma but i'll be honest figjam is ass
English
12
1
105
37.8K
Alvaro Cintas
Alvaro Cintas@dr_cintas·
New study shows being rude to AI makes it perform better. Researchers tested modern LLMs with 250 prompts across 5 politeness levels (from Very Polite to Very Rude). The results? Aggressive prompts outperformed polite ones significantly: • Very Rude: 84.8% accuracy • Very Polite: 80.8% accuracy This contradicts older research that showed the opposite pattern. Something fundamentally shifted with newer model architectures. The dataset covered math, science, and history questions. Each one rewritten in different tones and tested 10 times. They tested this on ChatGPT-4o specifically, and noted earlier models (GPT-3.5, Llama-2) behaved completely differently.
Alvaro Cintas tweet mediaAlvaro Cintas tweet media
English
19
17
95
22.8K
Ioannis Sintos
Ioannis Sintos@iocentos·
@0xTib3rius I just flip the order of the letters in the word. Don't tell anyone. It's a terces 🤫
English
0
0
0
49
Tib3rius
Tib3rius@0xTib3rius·
Base64 is hands down my favorite way to encrypt stuff. So easy. 🔥
English
180
40
1.5K
126.4K
Faizan Syed
Faizan Syed@fa1zvn·
Just found out that Sam Altman is non technical 🥀🥀💔💔
English
258
166
6.7K
906.3K
Elliot
Elliot@elliotnorrevik·
i'm leaving Lovable at 16 y/o to build AGI. the bottleneck isn't smarter models, it's the tools and context around them. more soon.
Elliot tweet media
English
623
104
4.6K
3.2M
Ashley
Ashley@ashleydzhang·
can't shake the feeling that the only real way to prevent people from getting sucked into the digital slop vortex is to make the physical world more beautiful, nourishing, convivial, kind
English
212
1.1K
10.7K
380.7K
signüll
signüll@signulll·
openai’s real advantage is that they almost always close the product loop. every breakthrough finds a consumer form. chatgpt crystallized gpt. sora now has a social app that locks in video gen. nobody else even with great tech like google has managed to consistently do this. that discipline deserves credit.
English
109
131
2.3K
430.9K
Ioannis Sintos retweetledi
Milky
Milky@tanzela_·
What cleaning products and vacuum cleaner do you use? Very satisfied.
English
108
24
469
414.8K