They aren’t usable? I’ve been using them a bunch and have been having good results. Dogfooding is always good, but I don’t think there’s some kind of major problem here.

They’re not killing anything. Search revenue is up this year.

And it’s not like they can stop the long-term move towards AI from traditional search engines.

All they can do is try to compete with their own AI. Otherwise OpenAI and Anthropic will run away with it.

Somehow OpenAI and Anthropic have been releasing new models on the day of announcement.

Seems like Google could do it too.

They have to announce it now because by the time they are ready to release it, it won't be the best at anything.

Anthropic and OpenAI are not releasing their best models for several months, because their second best models are still better than everything else available.

Not really, since I’m pretty sure we all know what they meant. They meant it was up to 92x faster in their testing.

There was plenty of bad code long before LLMs came around. Let’s be real.

Being hand written is no guarantee of high quality, just like using LLMs is no guarantee of low quality.

Using LLMs is not a guarantee of low quality, but it does make low quality vastly more likely.

Eh, not really. It just lowers the barrier for lazy people who never would have tried contributing before.

I’ve read a lot of code hand-written by programmers. By smart and hard working people. And I know from experience that the code the average programmer writes is not great either.

They made $11.5B just in Q2 2026, which is $46B annualized, or 10x their 2025 revenue of $4.6B.

That's a lot already and growing quickly.

Their profit on that was reportedly $559 million. But, this is after you realize that Anthropic got a discount on May/June from their new agreement with xAI's Colossus data center. So their first profit positive quarter happened during the time when their costs were artificially lower than they will be going forward.

Lots of people seem to love to do the simplest extrapolation that benefits their point. It's the same with "AI is improving at rate X, therefore if we linearly extrapolate, we'll hit AGI in a year."

I could start a business with a similar growth trajectory. We can mail people $100 bills for a low low payment of $10. I just need $500 billion dollars of startup capital and I can show you a 10x yoy growth for a few years.

I'm in. I would like to predicate the entire US economy on your business model.

That sounds fun but this is people paying for real products and services. The demand is there (and it's growing faster than any other commercial technology in history). They just need to work on inference (and potentially training) costs. I think that's clearly achieveable.

For the record, growth plays have been common in Silicon Valley for many decades. It's how we ended up with all the major tech companies we see today. Of course, it's high risk, high reward.

Except Anthropic had an operating profit in Q2, and your scheme never would.

You're just parroting a headline. They did not actually make a profit in Q2 when you take all of their expenses into account.

You’re just parroting another headline. Adjusted operating profitability is still a milestone.

Tech companies are capital intensive. AI ones especially. Not a surprise that they don’t have GAAP profitability after 5 years.

If they, through standard accounting practices, cannot show they are profitable how do we know they are profitable? I assume they can't just say "we are profitable assuming you ignore the costs we paid to build up XYZ". I'm guessing they could pre - rent compute for 10 years or something and maybe that's all on the balance sheet but you'd just amortize that and I think that falls under GAAP?

You can’t just “annualise” your best day. That’s not how it works.

Everyone is cutting back their AI spend because of the ridiculous cost, and a price war is emerging between AI companies.

Oh spare me the pedantry. What else are you going to compare? The year-on-year for Q2? That’s certainly going to have a much higher multiplier.

Your guess is as good as mine on whether these companies will continue growing, stall, or decline. Don’t try to pretend your methodology is more sound though.

What part of this is annoying? They made the barcode invisible so the envelope looks better. That’s wildly unnecessary, but cool.

That’s what makes Apple different than other tech companies. They have an extreme attention to detail that extends even to their packaging.

You can just tell it to write out a plan.md file.

I greatly prefer this, since it lets me iterate on the plan with Claude for a while without it repeatedly asking if I’m ready to implement the plan.

Once I’m satisfied, I usually start a fresh session and tell it to implement the plan.

For smaller plans, you don’t need the file. Just ask it to come up with a plan. I don’t recall the last time it just started implementing if I only asked for a plan.

This is the process I generally use too. Small plans you can just ask for, and big plans you work through building a plan.md file before you build it.

That also makes it easier to adversarially review the plan (I have Fable write the plan, then review it with Astra and another Fable instance).

How do you think the war could have ended? With Ukraine’s surrender?

Not such an easy thing to say if you’re the one facing that threat. Nobody wants their own country to be invaded and conquered.

And Russia would take that as a green light to keep on conquering other former Soviet states. Where do you draw the line?

Well yeah, that’s the whole idea. If speed and cost don’t matter, you could use Astra.

Obviously it’s the speed and cost that make it compelling. The tradeoff is accuracy.

Enough to matter? Maybe, maybe not. It’s not like it’s way down the chart. It’s probably good enough for a lot of tasks.