passive

For whatever reason, I get very few push notifications on my phone. Compared to my days at Blackberry, it's probably 10% as frequent that I get interrupted by my phone.

So good for me.

But there's some really scary stuff in here happening to other people that I'm not even aware of.

That's not generally true in the US over the last 40 years, where the gains from productivity increases have been accumulated almost entirely by the top classes.

Yes, lower classes have access to many more conveniences then they might have had in earlier decades, but they are working far more hours, and their expected lifespan has started decreasing.

I was using Gemini and Claude quite a bit over the last year, mostly with pro or opus for planning and flash or sonnet for implementation.

MiMo is the best one I've used so far, but I haven't done anything interesting with the Claude 4.7 models. It seems conservative with generally good "instincts", getting things working quickly without too much complexity. I've also embedded it in several different projects so far, and it's been pretty easy and effective.

I think this does a very good job of describing the real gaps agents are hitting in practical usage, along with a fairly compelling rationale for why those gaps aren't likely to disappear any time soon.

If we're going to stabilize the software industry, we need to have more discussions like this that identify what constraints apply. (We should have had those discussion before pushing AI out this widely, but that wouldn't have gotten anyone rich.)

I actually think that there's a world of software systems agents can change, but it's materially different from the one we have now, and has a different set of constraints that we've also mostly done a poor job identifying. So hopefully the discussion can help those of us on both sides. ;)

Yeah, I think they did switch the unit type.

I worked part time with MiMo 2.5-pro over the last month, and barely managed to use 500 Million of the 700 Million tokens I had allocated.

My plan was just upgraded to 38 BILLION tokens per month. That's at least 10X the tokens I've used in my entire agentic development so far.

I should probably downgrade my plan, but we'll see. :)

Oh, I don't want mean for myself, I mean as an experiment at the other end of the four-day work week spectrum.

Though for myself, I like having time to think about ideas in between when I collaborate with folk on them, so I have a lot of optimism about the success of the experiment. :)

It's a little bit snark, but I do think it would be an interesting experiment. Wish I had lots of money to try it out.

Four-day work weeks are for cowards.

Take all that AI productivity and found a one-day work week company. One day of focused collaboration each week, let bots and brains chew on stuff in the interim.

Yes. I tried a couple of weeks with non-Pro, and it was pretty good, but I had too many spare tokens, so I switched back to Pro. :)

I've gone through ~600m tokens in Xiaomi Mimo though Claude, and it's been the most effective use of an agent I've had yet. It's very capable, but generally not ambitious, picking simple but effective solutions to most problems I give it. Going to write something longer about the experience when I get to a billion tokens.

Made kagi.com my default new tab (which requires a chrome extension) and duckduckgo my default search.

It's totally plausible, just pointless for most of us to spend any time thinking about.

If someone with $200,000 wants me specifically dead, I'm going to die, one way or another. This tech doesn't substantially change the likelihood of their success.

If they want to cause a mass casualty event, there are already much easier ways. Once we tackle some of those, we can start worrying about this.

Uh, so it says this dates from Nov 2025.

Nov 2025 was also when most of us learned about the acting Chief Security Officer at DHS, whose name AND photo seem exactly like the calling card of someone who had these "keys to the kingdom". https://bsky.app/profile/andylevy.net/post/3m6ivhnthts2o

I want to believe...

If anyone visited my blog I could say they were inspired by me: :) https://writing.unified-designs.com/ai-coding-fomo.html

Maybe I missed it in the article, but it's less:

"AI uses more water than other things"

and more:

"AI's water usage is being approved without proper planning, because of the arguably fake sense of urgency around it."

Other industries that use significant water have significant regulations already . AI has been desperately trying to avoid ANY regulation (unless it forces folk to use AI.)

I don't personally think water usage is the biggest issue with how AI is being rolled out, but it's one that is easier to engage the public on then copyright, or societal context collapse. :)

I've built a developer platform around GitLab, and it's got some nice stuff, but it's not revolutionary.

But that's not all that relevant to the opportunity in front of them.

The opportunity, generally, exists because of their place in an industry that most folk believe will be very different a decade from now.

That belief is going to lead a lot of CTOs to try new things. When a company tries something new, it almost always picks a new vendor to work with, rather than adding complexity or risk to an existing vendor engagement.

Yes, there are other alternatives, but they are less well known, require self hosting, and/or are secondary products of companies with very broad focus.

Atlassian might be another, given how much of the rest of the software development cycle they have their hooks in, but many tech leaders have unresolved JIRA trauma. :)

My extremely cynical, but not yet proven wrong view:

Tech, more or less, has a group of investors centered around Silicon Valley. Not the only ones, but especially now, the most active. Generally, these folk have a lot of exposure to AI, and probably mostly believe the hype around it.

Which means they believe companies using AI should produce better results, which in the current market means short-term cash. So if a company doesn't do layoffs, no matter how well it is doing, it is seen as irresponsible and investment is withheld from it.

GitLab's announcement felt illustrative of this dynamic:

- The actual reductions were focused on simplifying org structure, nothing to do with AI

- They identified MORE work that was on their roadmap because of the way AI is changing software engineering

- They made sure to include a special section for investors

Seems to me they should have made the org changes in an unrelated announcement, and celebrated the opportunity for new work and the possible hiring that might be required to accomplish it all.

Like, GitLab is in an incredible position to moonshot the next generation of software. AI needs new substrate to work most effectively, and GitLab is the most popular "alternative" substrate to the fragile dinosaur that Github has become.

But AI needs to be seen as cutting costs above all else, so they can sell more of it everywhere, and this is what we get.

OH GOD! MY NOSTALGIA!!!!

My response to this, as a generally satisfied CloudFlare customer who was excited to try out agentic email, is that it's not a good time to increase the amount of business I do with them.

I am curious about this myself, as it's a major company that I would think is worth taking seriously. But this and the previous release got suspiciously few comments.

I applied to the Head of Engineering and Infrastructure role two months ago, and got a fairly generic rejection almost immediately that suggested I had been automatically screened out.

I've cleaned up my LinkedIn a bit since then, so perhaps that would help?

Given that you're still looking, and technically it's almost identical to my last role, seems like it's worth having a conversation about.

Yup, completely confusing Warner Bros and Disney. Thanks for catching that!

So Ellison's big investors wouldn't back his ridiculous (-Disney) Warner Bros bid without him juicing the performance of Oracle in this way?

(thanks for the reply correcting the company)

This is terrible, perhaps the worst thing this administration has done (which is an incredibly high bar.)

Because it provides a pathway to full government control of the internet.

Content that demonizes the current administration's enemies will become easier to find. Evidence of their crimes will vanish.

When they murder someone in the street, fewer people will find out about it, and those that do will be more likely to hear the government's side of the story.

Mobile networks are already owned by the billionaires, and they've shown plenty of willingness to shape traffic for their interests.

Managing this kind of information at scale is an incredible challenge, but one that LLMs are very well suited for.

Even if you are confident the current administration doesn't have the competence or longevity to exploit this (as I mostly am,) we can easily predict future admins of either party will happily make use of these capabilities.

Bad for the US, but also very bad for the world, because it will make it much easier to manufacture consent for or hide future international crimes committed by the government.

We've excused the complete loss of traditional journalism with a reliance on the Internet instead. Not anymore.

Can savvy individuals work around it, of course. But the general public will treat them like conspiracy theorists, because all they will see is content that reinforces the administration.

The technical discussions in here sound like: "silly Caligula, his horse won't be able to sign his name to cast a vote in the Senate."

Yes, that's what is happening here, except it goes beyond surveillance.

This is about full domestic control of the internet. For both ingress and egress.

Remember how Iran likely murdered thousands of protestors a few months ago, but we don't actually know? They want to be able to do that here.

In the US, automakers are still a big source of union power, which is at least part of the reason Trump is pushing them to drop EVs. In a fascist state, you want all powerful industries closely tied to the rulers.

Make that $6.91, despite only having $5 in my Anthropic account. I would love to know why it took so much more and didn't finish the job, but I'll have to set up a smaller experiment context.

Considering I just paid $5 to have Sonnet 4.6 fail to complete something Gemini Flash 3 was doing for ~$1, I'm very curious to try it out on more models, in particular cheap ones like this. :)

Applied to the Product Manager role. Most of my experience is on the engineering side, but I've done a fair amount of developer advocacy and SDK building, along with a bit of product management, so it seems like it could be a good fit.