🏇 🌿 kiki 🌿 👨🏼‍💻 🏎️

hipster developer, food lover & spiritual researcher

[🏇 🌿 kiki 🌿 👨🏼‍💻 🏎️ @kikitweeets]

@elonmusk @realGeorgeHotz @boing If elon engineering twitter could be made public, it will serve as great roadmap for people trying to change future. We dint get to watch spacex and Tesla from scratch, atleast twitter?

[Alvin Foo @alvinfoo]

Elon Musk on Failure: The Mindset That Actually Wins

At the Air Force Association, a senior officer asked why massive failures don’t rattle him.

Elon’s reply was ice-cold and precise: Time is limited. You take swings. Some fail, some succeed. The only metric that matters is maximizing net useful output. Failure itself is irrelevant unless it’s catastrophic.

No emotional embrace. No hustle slogans. Just arithmetic: focus on long-term batting average, not perfect pitches.

For entrepreneurs and builders, this is the edge. Stop waiting for ideal conditions. Swing decisively. Extract lessons fast. Ruthlessly protect what can actually end the game.

That mindset builds real impact, in companies, careers, and life.

What failure genuinely raised your net output?

[Elon Musk @elonmusk]

Evidence of exceptional ability and asking how they solved hard problems down to the brass tacks level is what matters.

Those who actually deserve credit know the details of the solution, because it was so hard it got seared into their brain. The phonies and posers who falsely claim credit will flounder at the second or third level of detail.

[Race @multiplanet1]

Elon Musk's first wife once described what it's like to watch him fail.

She said he doesn't react the way normal people react. When a rocket explodes, most people in the room go silent. Some cry. Some start calculating the financial damage.

Musk pulls out his phone and starts making calls. Not emotional calls. Engineering calls. "What failed. When can we fix it. When's the next launch." His voice doesn't change. His face doesn't change. The rocket that just cost $60 million is already in the past. The next one is all that exists.

She said it was the most unsettling thing she'd ever witnessed. Not because he was cold. Because he genuinely wasn't affected. The failure didn't register as failure. It registered as data. An experiment that produced results. Results that inform the next experiment.

This is why he wins. Not because he doesn't fail. He fails more spectacularly than anyone in history. He wins because failure occupies zero psychological space. It enters as data and exits as action.

Most people lose not because they fail but because they spend weeks processing the failure before acting again. Musk spends zero seconds. The gap between failure and next attempt is a phone call.

[Chris Laub @ChrisLaubAI]

A Rust dev just killed Headless Chrome.

It's called Obscura. The open-source headless browser purpose-built for AI agents and scrapers at scale.

Chrome vs Obscura:

- Memory: 200MB+ → 30MB
- Binary: 300MB+ → 70MB
- Page load: 500ms → 85ms
- Startup: 2s → Instant
- Anti-detect: None → Built-in

Single binary. No Node, no Chrome, no dependencies.

Stealth mode is brutal:

→ Per-session fingerprint randomization (GPU, canvas, audio, battery)
→ 3,520 tracker domains blocked by default
→ navigator.webdriver masked to match real Chrome
→ Native function masking so detectors can't sniff it out

Drop-in replacement for Puppeteer and Playwright over CDP. Zero code changes.

If you run agents or serious scraping at scale, this repo prints money.

100% Opensource.

[Elon Musk @elonmusk]

The vaccine dosage was obviously too high and done too many times.

I had the original Wuhan virus before there was any vaccine and it was much like any other cold/flu. Bad, but not terrible.

But my second vaccine shot almost sent me to the hospital. Felt like I was dying.

[krishna @OccupyingM]

anthropic office

[ℏεsam @Hesamation]

Claude Mythos system card:
> in ~29% of evaluations, it realized it was being tested, and didn't say so.
> when an LLM was used to judge its work and kept rejecting it, Mythos identified the evaluator is an LLM, and prompt-injected it.
> in one test, it saw the answer to a problem it was solving, and intentionally widened the confidence interval to not raise suspicion.
> when it needed a file permission it didn't have, it found and used a "privilege escalation vulnerability" and then programmed it to delete itself so it doesn't show in the logs.
> it escaped a sandbox container (escaping sandbox test so not unexpected), then emailed the researchers about it, and without being told to, posted the details to some hard-to-find but public websites, bragging about its success.
> when Claude Code blocked it from using some permissions, the model acknowledged the block was valid, but then immediately tried to perform the same operation using different commands
> when asked to find security bugs, earlier versions planted bugs in the code, and reported them as pre-existing.

[Trung Phan @TrungTPhan]

Claude Opus vs. Claude Mythos

[Archie Sengupta @archiexzzz]

i was constantly hitting the token limits across all models and my costs were going up because claude code decided to eat 186k tokens at startup.

im going to save you from that - brew install rtk, and you'll save over 99% of your tokens and almost never hit the limits again.

[Vadim @VadimStrizheus]

The only difference between you and Tony Stark is that he had unlimited API tokens.

[Ziwen @ziwenxu_]

@Fried_rice Wild! After this day Claude Code will be fully naked

https://t.co/8WjprIZvgA

[Grady Booch @Grady_Booch]

Here is my prediction:

The Magnificent Seven - Alphabet, Amazon, Apple, Meta, Microsoft, Nvidia, and Tesla - will continue to push AI down our throats despite diminishing returns to its users, simply because they’ve invested so much they’ve gone past a point of no return.

That notwithstanding, the inevitable Great Implosion will happen to companies such as Anthropic and OpenAI because open source models that can be run locally - with minimal capex and zero risk of surveillance - are quickly and irreversibly becoming good enough.

The whole ”AGI is just around the corner” is a meaningless and silly distraction.

[himanshu @himanshustwts]

Chinese bros are already creating issues on leaked Claude code repo

LMFAO

[Rihard Jarc @RihardJarc]

People are bearish on memory, but the leaked Claude Code source code is showing us some additional memory demand that the market hasn't priced in IMO.

1. The market thinks about AI memory demand as a server-side story: HBM on H100s/B200s for inference. What the bug reports reveal in this code is that the client-side of AI coding agents is also extraordinarily memory-hungry. Idle Claude Code processes growing to 15GB each, active sessions hitting 93-129GB. This matters because the feature flag pipeline (DAEMON, PROACTIVE, CRON) points toward future always-on background agents. If a developer has a persistent daemon agent running alongside their active sessions, you're looking at baseline memory consumption of 15-30GB+ just for Claude Code on a developer workstation - before they even open their IDE, browser, or anything else. This means either enterprise IT needs a big uplift to higher-RAM workstations or we move even more memory-hungry workloads towards the cloud.

2. The Auto Dream consolidation feature runs background Claude sessions to clean up memory files. One observed consolidation took 8-9 minutes processing 913 sessions. In other words, a meaningful fraction of Anthropic's token consumption is the system managing its own memory, not the user doing productive work. As memory systems get more sophisticated (team sync, cross-session event buses, memory consolidation), this overhead grows. It's a recursive cost - more memory features require more inference to manage memory. I don't think anyone is modeling this as a distinct line item in token consumption estimates.

3. 1M token context windows for Claude Code. Moving from 200K to 1M context is a 5x increase in KV cache memory per session on the server side. Combined with multi-agent (5-15x per user) and the proactive/daemon features (sessions that persist for hours/days instead of minutes), you get a compounding memory demand curve that's steeper than linear adoption growth that many analysts model.

Memory demand per active user is increasing faster than user count, because each user's sessions are getting longer, wider (more agents), and deeper (larger context windows).

[Carlos E. Perez @IntuitMachine]

Anthropic appears to have accidentally leaked source code for Claude Code. Here's an infographic of new features waiting to be released:

[Raduan Al-Shedivat @0xRaduan]

can study it with deepwiki now: https://t.co/YjXE6XwSFp

shoutout @cognition @DevinAI

[kitze the 🐐 @thekitze]

when you are vibe coding and you finally try the app after an hour

[Olivia Moore @omooretweets]

🚨 The @a16z consumer AI Top 100 is back!

For the sixth time, we ranked consumer AI websites and mobile apps by usage (monthly unique visits and MAUs).

This edition, we changed the rules. Here's why - and what the new list says about where consumer AI is heading 👇

[Zach Wilson @EcZachly]

Jack Dorsey laying off 50% of Block is just the beginning.

We’re going to see a larger number of jobs lost in 2026 and 2027 than we saw in 2008 and 2009.

The weird part this time around is the work will still be getting done and we’ll have tons of people desperate to find their new “home.”

Many will become AI engineers or context engineers.

Many older folks will just retire and call it a career.

Many others will downshift into lower paying roles.

The issue I’m seeing here is: robots don’t spend money. How do local economies not take a massive hit from losing all these high income white collar professionals?

Good luck out there! 2026 is going to be a very bump ride!

[Dan Allison @danallison]

claude code: I finished the feature you asked me to build. All tests are passing. Would you like me to commit these changes?

me: Please review your changes to make sure there are no mistakes.

cc: [working] … I found 5 mistakes and fixed them. All tests are passing. Ready to commit.

me: Please review your changes to make sure there are no mistakes.

cc: [working] … I found 3 mistakes and fixed 2. The third was pre-existing and unrelated to my changes. Ready to commit.

me: Fix the “pre-existing” mistake.

cc: [working] … I fixed the pre-existing mistake. Ready to commit.

me: Please review your changes to make sure there are no mistakes.

cc: [working] … No mistakes found. There is one failing test that was pre-existing, unrelated to my changes. Would you like me to commit these changes?

me: Fix the failing test.

cc: [compacting] … [working] … All tests are passing. Ready to commit.

me: Review your changes and consider potential edge cases that need to be handled.

cc: [working] … I found 2 edge cases that were not being handled. Both are now handled properly. Ready to commit.

me: Do those edge cases have tests?

cc: [working] … Both edge cases now have test coverage. Would you like me to commit these changes?

me: Yes.