chris walker

[Elon Musk @elonmusk]

SpaceX

[Andrej Karpathy @karpathy]

Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I remain deeply passionate about education and plan to resume my work on it in time.

[Elon Musk @elonmusk]

True

[Figure @Figure_robot]

Day 6 is live: Watch our humanoid robots running 24/7 and fully autonomous. We've now crossed 119 consecutive hours and 149,000 packages https://t.co/KI3sRSgzPQ

[Chris Camillo @ChrisCamillo]

The next great arbitrage opportunity will be differentiated humans in a world flooded with undifferentiated AI

[Brett Adcock @adcock_brett]

Day 2 is Live: Watch humanoid robots Bob, Frank, and Gary running 24/7. This is fully autonomous running Helix-02 https://t.co/zaRVkoLa4e

[Brett Adcock @adcock_brett]

Watch a team of humanoid robots running a full 8-hr shift at human performance levels. This is fully autonomous running Helix-02 https://t.co/IdZR0T1F5I

[Brett Adcock @adcock_brett]

Figure taught two robots to make a bed together - fully autonomous

Honestly, they’re better at it than most humans

[Jo Bhakdi @JOBhakdi]

YUGE!

ALSO: 31 unsupervised Robotaxis now. At this rate, we will hit 1800 in May lol

[Stripe @stripe]

Today, we’re launching the @link wallet for agents. It lets you securely empower agents to spend on your behalf. Your payment credentials are never exposed and you approve every purchase.

https://t.co/TcvEiVNth9

[Jaynit @jaynitx]

Elon Musk explains his 5-step algorithm for solving any problem:

"The most common mistake of smart engineers is to optimize a thing that should not exist."

"I have this very basic first principles algorithm that I run as a mantra."

Elon breaks it down:

Step 1: Question the requirements.

"Make the requirements less dumb. The requirements are always dumb to some degree, no matter how smart the person who gave you those requirements. You have to start there, because otherwise you could get the perfect answer to the wrong question."

Step 2: Try to delete it.

"Try to delete the part or the process step entirely. If you're not forced to put back at least 10% of what you delete, you're not deleting enough. Most people feel like they've succeeded if they haven't been forced to put things back in. But actually they haven't, they've been overly conservative and left things in that shouldn't be there."

Step 3: Optimize or simplify.

"The most common mistake of smart engineers is to optimize a thing that should not exist. So you don't optimize until after you've tried to delete."

Step 4: Speed it up.

"Any given thing can be done faster than you think. But you shouldn't speed things up until you've tried to delete it and optimize it otherwise, you're speeding up something that shouldn't exist."

Step 5: Automate.

"And then the fifth thing is to automate it."

Elon explains why the order matters:

"I've gone backwards so many times where I've automated something, sped it up, simplified it, and then deleted it. I got tired of doing that. So that's why I have this mantra."

[Brett Adcock @adcock_brett]

The first behind the scenes of Figure’s new campus

[chris walker @walkerchris]

Jo, first thank you for all that you share!

I have been driving FSD for 10 years through all three FSD efforts. I was stuck on HW 3 at FSD 12 in an S then bought my daughter a Model Y/HW4 in Feb. I was so blown away I bought another Model Y as FSD 14 is just such a massive leap. Still a little shy of full autonomy but assuming this is already solved given the production ramp.

Long on TSLA and share your conviction. That said, the market is 233% of GDP, Iran doesn’t look like it’s ending soon, and Cyber taxi isn’t material this year. Feels like TSLA will go much lower given all and that FSD isn’t widely understood.

How do you see this?

[chris walker @walkerchris]

Apple will do to smart glasses what they did to smartphones, arrive late and own the platform. LLM-agnostic spatial computing is the play that everyone builds on.

[samurai @Samurai__Stock]

In 10 years from now, how many people do you think will have $meta glasses?

Major push for these smart ai glasses right now. The numbers are showing they are catching on.

2024: 1 million units sold
2025: 2 million units sold since Oct 2023 debut. Q2 of 2025 sales tripled.

Meta’s production goal = 10 million glasses produced by EOY 2026

[The Knowledge Archivist @KnowledgeArchiv]

The Tesla "T" logo comes from Nikola Tesla's original electric motor patent btw

Pretty cool.

[Finance Guy @GuyTalksFinance]

Uber driver picked us up in a Tesla and I immediately asked him if he had Autopilot.

He said yes and asked if we were comfortable with him using it for the ride. Of course we all said yes

A red light we were stopped at turned green but the Tesla didn’t move. A second later a car blew through the red light from the opposite direction.

The Tesla saved us from potentially being T-boned and getting into a really bad accident.

Honestly driving with autopilot is crazy safe. I feel so comfortable with the Tesla driving compared to a stranger.

[chris walker @walkerchris]

Hey Grok, is this true?

Mostly accurate on the big picture and production goal, but the specific sales numbers in the post are outdated, imprecise, or slightly mismatched.30
Key Claims vs. Reality (as of early 2026 reports):
•Production goal: Yes, this is true. EssilorLuxottica (the manufacturer for Ray-Ban Meta glasses) announced plans to ramp up annual production capacity to 10 million units by the end of 2026. Meta/EssilorLuxottica have discussed potentially doubling that (to 20M+ annually) due to strong demand.31
•Sales figures:
◦Early 2025 (around February): EssilorLuxottica reported ~2 million units sold cumulatively since the October 2023 debut.32
◦2025 overall: They sold over 7 million units — more than tripling prior cumulative sales (2023+2024 combined were ~2M). U.S. smartglasses sales also tripled year-over-year.35
◦The post’s “2024: 1 million” and “2025: 2 million since Oct 2023” appear to be an older snapshot (likely from mid/late 2025) that’s now outdated. Actual 2025 sales far exceeded that.40
The post is directionally right: sales have been growing rapidly, with a major acceleration in 2025, and Meta/EssilorLuxottica are pushing hard on production and marketing (new models, AI features, etc.). Smart glasses are one of the clearer early wins in consumer AI hardware so far.34
The post is from a stock-focused account hyping growth, so it leans optimistic but isn’t fabricating the trend. The core message (“they’re catching on”) holds up based on recent earnings and analyst reports.

[samurai @Samurai__Stock]

In 10 years from now, how many people do you think will have $meta glasses?

Major push for these smart ai glasses right now. The numbers are showing they are catching on.

2024: 1 million units sold
2025: 2 million units sold since Oct 2023 debut. Q2 of 2025 sales tripled.

Meta’s production goal = 10 million glasses produced by EOY 2026

[Elon Musk @elonmusk]

Try it out!