passive

This is bad advice in 2026 for most people who would read it, since it advises taking a terrible security posture (give the agent access to everything,) in exchange for a relatively small improvement in workflows.

I say small improvement because my experience is that modern Agents are pretty good, so by the time they've handed it back to me to test it, there are usually only one or two remaining issues that I'll discover as we roll it out to Production.

(In general, I think we don't do enough to emphasize best practices in the era of AI, but...)

What Kent completely ignores here, as far a I can tell, is that there is significant value in finding out sooner what the needed features are. Building speculative structure can be a forcing function to establish requirements, because at least you start exposing failure modes. It might be more expensive than waiting, so hopefully you don't do it for most of your requirements, but sometimes it's your best option.

Building the wrong thing is now a much less expensive option, and that means the calculation around YAGNI is different. But it's still a calculation, and for now, each team needs to figure out how it has changed for them.

This is my concern as well. If critical open source packages become dependent on these corporations for "secure" releases, does that enable them to force ID verification into packages, for example? Related, but most of the smart folk I know think Open Source AI means Anthropic and OpenAI are financially impossible. A lot of the companies signed onto this are heavily, heavily leveraged by those two, and have significant incentive to disrupt Open Source AI before all their customers get sticker shock. I've been waiting to see what their move would be, and this might be part of it.

They default it to talking to a free version of their model (which is incredibly cheap if you decide you like it.)

But it seems trivially easy to run it against local models. Their onboarding guide offers that option, though I have no idea if it changes any functionality.

Interesting. I've been using their models quite a bit, through Claude Code, might try switching to this.

I also built a couple of harnesses, I wonder if I could swap this for Claude in those...

(Lots of interesting ideas in the blog post, but like all the AI developments these days, hard to be sure what's valuable without extensive experimentation.)

Because this isn't the first collection they've stolen from someone, presumably.

It's a lot easier to become a really successful company if you can keep your inventory costs down. Perhaps by investing in local law enforcement instead, to make sure no one looks too close at said inventory?

Donald Trump is famous for not paying even really cheap contractor bills, because he knew he could get away with it.

So we have this, and the Google employee polymarket trading:

https://news.ycombinator.com/item?id=48302822

I'm totally not surprised, except that Trump's admin is actually catching and prosecuting these people.

I assume that means this is just the tip of the iceberg, and the grift is so predominant that they can't help but catch some people.

Firm, but partial, disagreement.

People, especially in remote jobs, benefit from being organized into groups intentionally, with distinct rituals that enable them to operate effectively while they get to know each other better. Another person needs to design and oversee all that.

While you can provide templates for that structure that allow oversight to scale so that one person can oversee larger groups, that tends to be more effective in non-remote, and more predictable, work environments. Modern software development is very little of that.

I don't have much in-person experience with middle management in contexts outside of software development, and I suspect there are some opportunities to use AI to bring engineers closer to customers.

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.