Sabitlenmiş Tweet
Vikas Tiwari
15K posts
Vikas Tiwari
@pmvikastiwari
agentic ai product guy
Mumbai Katılım Mart 2025
693 Takip Edilen887 Takipçiler
Argentina had no chance tbh. Spain played astoundingly well.
English
Reminds me of 'gaddari karbe' meme
dennis hegstad@dennishegstad
I can’t stop laughing. This man clearly showed that Ostrich who’s boss.
English
@petergyang @trq212 Only reason he can do this is because of unlimited compute
English
One of my biggest takeaways from chatting with @trq212 is how much effort he puts into understanding what AI is doing.
It’s easy to let AI build something magical and feel like you’re making progress. But if you want to get better, you need to read its output, identify your unknowns, and fill those gaps.
For example, Thariq sometimes asks Claude to generate an HTML report explaining what it changed and then quiz him to make sure he understands it.
This is just one of many things I learned from Thariq in our interview.
📌 Subscribe to get the full episode tomorrow: @PeterYangYT?sub_confirmation=1" target="_blank" rel="nofollow noopener">youtube.com/@PeterYangYT?s…
English
Repo: github.com/vikast908/ORBUX
Website: orbuxloaders.vercel.app
English
Just open-sourced OrbUX ✨
237 state-aware loaders for AI / agent UIs.
One Web Component API for thinking, streaming, tool-calling, done, and error.
CSS · Canvas 2D · WebGL
Zero framework lock-in · MIT
Links 👇
English
Why tf are OpenAI and Anthropic valued at hundreds of billions while Kimi is sitting at just $20B?
Arena.ai@arena
Big news: Kimi-K3 by @Kimi_Moonshot is now #1 in the Frontend Code Arena with 1679 pts, surpassing Claude Fable 5. This is a 17-place jump from Kimi-k2.6 (#18 -> #1). In Frontend, Kimi-K3 ranked #1 in 6 of 7 domains: Brand & Marketing, Reference-Based Design, Data & Analytics, Consumer Product, Simulations, and Content Creation Tools, landing #2 only in Gaming behind Fable 5. The full model weights will be released by July 27. Congrats to the @Kimi_Moonshot team on this major milestone!
English
How come the GPT-4 source is appearing at the top of this query? The answer is right, so no problem with retrieval. Maybe the order of the sources is not sorted by confidence score, and it's just random
English
Can someone from the @OpenAI team help me understand whether I have selected 5.5 High or 5.6 Sol High?
English
The best use case for Hermes for me is cleaning up junk files and emails. I have never been happier.
English
@tldraw If you can get a clean SVG architecture diagram generated by AI, it would be a win. Mermaid sucks!
English
We are getting there!!
Btw, one shot-ted with Grok and Gemini!
Mark Vassilevskiy@MarkKnd
Kimi 3 could've never done this
English
Since @nikitabier is openly roasting and giving people insight into why they are not growing, I just want to know what I can do better. There is no niche to what I do.
English
@premwomp Dude, it's been 10 years and is hardly close to the average lot. I say good for them if it is real.
English
how are people getting ₹50–70 lpa straight out of college?
genuine question.
English
@mattpocockuk What do you suggest for folder structure and junk removal? Is there a skill?
English
New flow I've been enjoying
1. "/grill-with-docs <issue description>"
2. "Oh damn, this is way bigger than I expected"
3. "/wayfinder make a map of this"
4. Continue happily on
English
