
CEO at @datadashxyz | Crypto Data Nerd
Dubai
Joined June 2011
- Tweets149
- Following2.3K
- Followers222
- Likes2.7K
Arijit | Token2049 🇸🇬 retweeted
Every prediction market trader has the same 3 questions.
We’re answering all three as we participate in @colosseum’s Crypto World’s Fair.
The intelligence layer for prediction markets.
Arijit | Token2049 🇸🇬 retweeted
Introducing Signals
The easiest way to copy trade on @Polymarket
We score all 1M+ open positions so the ones worth copying are easy to spot in real time.
Insane Alpha on Polymarket unlocked
Introducing Signals
Discover the best traders on @Polymarket and see every bet they make
Designed to make copy trading simple
Now live on Datadash
Arijit | Token2049 🇸🇬 retweeted
🚨 POLYMARKET ALERT 🚨
"Will Ukraine recapture Crimean territory by Dec 31, 2026?"
@tsybka (Russia category rank #16) is in NO at 90.6¢ — a ~$45K position.
The same entry is still live: you can buy NO at 90¢ right now (Yes priced at just 11%).
Same trade, same price. 👀
Let's live track the wallet: datadash.xyz/@bomber
One wallet has spent the 2026 World Cup hunting the calls nobody else would touch.
Spain vs Cabo Verde
Qatar vs Switzerland
Then Belgium
Three long shots, three hits, +$250K
Up to 5x on a single call
The streak isn't over. Today the same wallet is fading Iraq, Senegal and Norway.
Skill or a hot streak? The next match settles it.
Arijit | Token2049 🇸🇬 retweeted
Replying to @Polymarket
@Polymarket trader @LATINAXBT just pulled off an impossible comeback.
Nov 2025: +$3.05M
May 2026: -$1.51M
Jun 2026: +$691K
Survived a $4.6M drawdown. Went seven figures underwater.
Then clawed all the way back to green in 18 days.
$61M traded, 56% win rate, ice in the veins.
Arijit | Token2049 🇸🇬 retweeted
That's right, to explain interleaved thinking more straightforward, I made a comparison html with M2! It visualizes the difference between regular thinking, interleaved thinking but reasoning not passed pack, and full interleaved thinking. We will post a tech blog with specific benchmark with/without reasoning passed back
Replying to @SkylerMiao7
The best part, just to check how well the 'vibe coders' will understand Interleaved Thinking, I asked Claude 4.5 Sonnet to produce a Deep Research report for me.
It did lot of web search and came back with a wrong description of Interleaved Thinking with Tool calling.
Most vibe coders depend Claude 4.5 for coding.
That doesn't get interleaved thinking right even with Web Search, how well it is going to implement handling of interleaved thinking in code?
The issue is not with the model, but with Anthropic documentation. You have to read it so careful and write code to see it in action.
(screenshot below: Claude thinks there are successive Think and Tool calls without Tool responses before the next Think block).
Context is the new RAM & LLM is the CPU. Agent development is nothing but applying the fundamentals of CS.
Arijit | Token2049 🇸🇬 retweeted
Context Rot
Great title for a report, but even better insights about how increasing input tokens impact the performance of top LLMs.
Banger report from Chroma.
Here are my takeaways (relevant for AI devs):
Arijit | Token2049 🇸🇬 retweeted
If Claude is really doing so much of the coding for Anthropic, why haven't they used it to create a fucking ui for Claude Code?
It's 2025. Why the fuck am I forced to use a cli for everything as if it were 1995?
Arijit | Token2049 🇸🇬 retweeted
Don't use structured output mode for reasoning tasks.
We’re open sourcing Osmosis-Structure-0.6B: an extremely small model that can turn any unstructured data into any format (e.g. JSON schema).
Use it with any model - download and blog below!
Arijit | Token2049 🇸🇬 retweeted
Some of you, vibe-coders, are the exact definition of Mount Stupid.
I was also young and cocky and thought I knew better than everyone else.
A bitter lesson I learned the hard way: good software is way more than what you see on the screen. A million micro-decisions hold it all together behind the scenes. You might not see them, but they are there and matter.
It's awesome that people are vibe-coding and learning how to build software. It's not the conventional way most of us went through, but it's also valid, and I hope it sticks.
But you gotta understand that it's unlikely you'll build good software after a day of talking to a model, especially with the current state of this technology. It will take time and much more work than these models can give you today.
So stay humble, have fun, and use this as an opportunity to learn and improve. You'll find a ton of people willing to help!
But if you get cocky, start disparaging "boomer" developers, make fun of those pointing out the problems you are creating, and in general, have a know-it-all attitude, don't be shocked when people exploit every single vulnerability you created.
Tomorrow, we might all become obsolete, but that's not today.
























