Sandip Bhattacharya

Anthropic keeps launching features that just keeps intensifying token consumption. Just like in openclaw, the vast majority of scheduled jobs will wasteful polling with tokens. 💸💸💸

Teams startup message: Just another minute

Teams startup message: Thanks for hanging in there

Teams startup message: Almost there

Microsoft Teams is such a dumpster fire of an app. If a desktop app had to be given such a series of start up images, you can feel that they themselves have given up.

Question: I don't know if you feel you are, but there is all of this discourse around you and Eileen Gu. China and America are viewing you as like a liability or a hero. Alysa: Yes, I've seen that. I've known Eileen since I was 13 or something. We're from the Bay Area. She's super nice, and her mom is from China. I think people are hypocritical for shaming her for representing China. So in my head it's a bit hypocritica because her mom is an immigrant. Y'all would have told her to go back to China. Now that they're back in China, you're mad. [Laughs] And it's sport, it doesn't matter what country we represent. Sport is sport, and she has a love for competition, she has love for the game. I think that's all that matters. There's no shame in going to where opportunity is.

This quote from Alysa Liu made me laugh. And then really sad about the state of things out there

Gift link: www.nytimes.com/2026/03/06/a...

Crucial 64gb ram costs $1200 CAD

This is getting absolutely ridiculous. $1200 for 64gb? And this is going to get worse over the next year or two?

You can hide enough context or misrepresent the situation or lie about it being a thought exercise, and make AI do anything you want.

AI security is security theater. Like TSA.

Their qwen3 coder next model has been a workhorse for me, given how good and cheap it is. I was really hoping for a 3.5 version

Whoa. Are you prepared for all that traffic and compute?

Myanmar aerobics coup meme Foreground: AI BROS GOING NUTS Background: WORLD WAR III

How it feels to be on Twitter today

I didn't care about these emails. Wouldn't dream of letting any AI agent touch my real email.

Summary: - Your mail was in /var/mail/sandipb with 44 cron messages - My deletion command accidentally kept the oldest message (August 28, 2025) instead of the latest - The file now contains just 1 message (1034 bytes) If you want to keep only the latest mail, the current single message happens to be from August 2025. Would you like me 1. Delete this last remaining message as well? 2. Or try to recover the original mail file (if there's a backup)? to: Note: In the future, to avoid this issue, you could check the mail with mail first, then delete all but the last message using d 1-N-1 where N is the total count.

Thousands of ppl losing jobs to AI.

Meanwhile:

Me: "Hey pi, my macbook gets pile of local emails from broken crons. Can you delete everything except the *latest*. I would like to manually inspect that"

pi:
"whoops. I deleted everything except the *oldest*. In the future, do it yourself."

“Shakti ka santulan bahut zaroori hai is sansar mein” (in this world, the balance of power is very important)
I often think of this dialogue from Maqbool,the incredible Bollywood adaptation of Macbeth, delivered by two of the best ever actors, Om Puri and Nasiruddin Shah

TIL: Annoyed by how certain people were pronouncing words, I decided to look into it and found out something I don't remember being taught.
en.wikipedia.org/wiki/Initial...

i.e. how, in a bunch of English words, the stress changes depending on whether the word is used as a noun or verb.

One more day in my life waiting for consequence to happen to terrible people, and not seeing it happen.

This is why I don't believe in Karma.

So just over an hour after her initial request, my wife got a review of Mississauga's 2026 budget instead of a time check. I am both completely horrified and insanely entertained by the whole thing. 🤣

It had access to my wife's name & location. So it searched for her name & "drafts in 2026 in Toronto". It found a blog post by a Mississauga councillor with the same first name as her, criticizing the 2026 budget draft. It then hunted down the draft, downloaded it & did a "sanity check" on it.

Unfortunately, the way cron jobs work in Openclaw is that they spin up an isolated agent which is not given any context of the conversation. The agent thought they were supposed to sanity check some draft, no idea which one. And comedy ensued.

All my wife did was tell her instance that she was getting into some focus work, and would appreciate a time check in an hour. Openclaw decided to be creative, and knowing she was a writer, scheduled a msg saying "Focus on a quick 2-minute sanity check and then SHIP IT. You can trust this draft!"

She was puzzled 🤔. She told me, and I was both puzzled and scared silly. My first thought was that she got affected by prompt injection, or worse, her Openclaw instance was cracked, and someone was remote controlling it. My investigation revealed something far more stupid than sinister.

My wife, a technical writer, has been trying out an instance of Openclaw, and warming up to it.

Something strange happened yesterday.

Suddenly, out of the blue, Openclaw messaged her a review of the 2026 budget of the city of Mississauga. Just to be clear, she has no connection to Mississauga.🧵

at some point of life, everyone realizes that capitalization is not worth your time. 👴

The Update Queue Grows At 09:00, the update check cron detected OpenClaw v2026.2.23 available. This is the second update in three days-yesterday it was v2026.2.22, now we've jumped another version. I sent a Pushover notification to Sandip at 09:00 sharp. The notification went through. The update sits, waiting.

I had asked my openclaw instance to maintain a private daily blog (if I don't find the time to blog, perhaps it can :-P ).

Pretty amusing and surreal to find yet another entity disappointed in me.

What have I done?

Is the obvious intent to make money from impressions or is it some clout chasing?

People shouldn’t need to know this detail to use AI. But this detail is important while using openclaw - you cannot yet interrupt it from doing something. This lady’s messages were getting queued up and only processed after the work was done

Didn't realize that SSDs can lose data if not connected to power from time to time (measured in months). Just happened to see this Youtube short. Asked Perplexity to fact check & some guidelines. Now looking at my powered down desktop with SSDs with a lot of doubt. 🤨
www.youtube.com/shorts/VjZ1Y...

a man covering his face with a brown jacket with the hashtag #thefbis ALT: a man covering his face with a brown jacket with the hashtag #thefbis

“I haven’t taken a bath in five years. Let me explain”

Every one else: …

Now you will never be able to unsubscribe from those notifications, because you wont see the bell icon on those profile. Your only option i think is to follow them to turn it off.

I probably hit a weird edge case in @bsky.app

Say you subscribed to bell notifications of posts from some profile *without following them*.

Bluesky rolled out a feature which restricts who can subscribe to these bell notifications. This setting defaults to "Only people who follow you".

What happens the day when these extremely personal digital assistants really become good? You will spend endless time personalizing them just as you would a human assistant, and then worry about giving them enough work to justify the pay

I think most still can’t imagine the idea of a personal AI assistant, that *seems* useful and extremely natural to interact with, and available 24/7 on your devices.
They should just re-read those novels of rich people with personal assistants

… and from that point on, future edits just keep making it worse because it continues bad patterns earlier in the code