dools

Networks still send WAP pushes but you can't just send randomly formatted WAP pushes to your friends. You can, however, use a stingray to MITM your friend's Android phone and send whatever you want to them, because now there is no network firewall to protect them. The combination of MITM and a bug like this could be pretty devastating.

> I doubt they will block automatically the number if you are under that DOS for a few days in a row.

You doubt correctly. The law is about blocking IMEI numbers of phones that use the 3g network to dial 000 despite being 4g devices.

It didn't. The 3g network was shut down. There were several older devices that were 4g but still used 3g to call 000, so they had to be blocked from connecting.

Have you any idea how it feels to be a Qwenputer living in a Qwenbot's Qwenputer's world?

That’s just renting GPU clusters

I’m not shocked, the HN crowd is heavily under the influence of Musk propaganda.

Oh cool they released the roadster

Oh no, they are letting people “reserve” their roadster

How is anyone still falling for this grift?

This is interesting to me because I only started using JetBrains IntelliJ IDEA specifically to do AI coding.

It was the first time I'd used an IDE, the first time I'd built a cross platform app, first time I'd used Kotlin, and the first time I'd tried AI coding.

The journey started with choosing KMP as the stack, then I figured "here's the company that released KMP, they have an IDE, they have AI, I'll use that".

It was really useful, and convinced me that AI coding was the future. I didn't know Kotlin (I still don't) and I don't look at any of the code. I do look at diffs sometimes (less and less). My main "review" is "reviewing test failures", which is a workflow I developed over the past year.

It was about 4 months into using it that I figured out that the IDE was really doing nothing.

I rewrote their worktree functionality as a couple of bash scripts. The build and test functionality was all gradle on the command line anyway. I was just using it as a chat interface and a markdown reader.

So I set up tmux and used Junie CLI (I liked Junie as an agent), Kimi Code and Pi Coding agent simultaneously on different projects. Junie CLI was pretty good, but it had too many instructions and when I started getting particular about my workflows, compliance was too difficult.

Kimi Code and Pi kept winning, eventually I stopped using Junie altogether. The name of the game was doing things in parallel and in the background. Editing the code had nothing to do with it.

The thing I missed was how JetBrains AI credits worked. I loved switching between models, and didn't want to tell everyone on the team to have their own accounts. I looked around and saw some LLM gateways and stuff like OpenRouter, but then they are all still charging extra, so I just wrote my own LLM gateway and connected it to Pi.

But then I was like "what is Pi really doing here?". I wanted a thing I could use from my phone, and using tmux over Termius is pretty weak, so I was like "Oh maybe I can have a mobile app that uses Pi as an API or something" but then I kept hearing the creator of Pi talk about how simple the coding loop was so I just wrote the coding loop into my LLM gateway and then created clients for it for iOS, android, macOS, windows and web, all using Kotlin Multiplatform.

Now I've got my dream coding agent: I create work trees at the touch of a button from my phone, I discuss with the agent using the "reply mode" interleaved reply feature, I have a flexible bash script based workflow engine, a centralised script/skill distribution framework, centralised billing/model gateway, all built into a single dev box that runs everything and can be deployed using one of those fancy curl -> bash pipeline things. I can deploy to dev, staging and production at the touch of a button from my phone. Dev and staging are IP gated behind CloudFlare tunnels, the production deployment goes straight to GCP, using a standardised framework.

My colleagues and I use it to ship real internal and external products and they're not even developers.

I haven't read any code or reviewed any "PRs". I don't even use GitHub or linear!! But man when I go for a walk and sit down on park benches and dictate to my coding agent in my phone, set the workflow running and then keep walking it feels like a super power!

And this was more or less 1 year from starting my first project using IntelliJ IDEA + Junie + OpenAI GPT 5 and winding up using a mix of models on my own platform that I share with my colleagues.

I don't understand how an IDE development company or, really, any "coding agent development" company can maintain a competitive edge in the face of that kind of pressure.

EDIT: I did find their Air product very intriguing but they didn't get it released quickly enough and it didn't solve the problem of having things running in the background easily enough. Also their worktree setup and teardown functionality was a bit of a drag. I built my own platform and started using it to build itself quicker than they got Air to the stage where I would want to use it. They STILL haven't released their mobile client.

It’s also the case that there are always humans using AI to try and do whatever nefarious thing an AI might try to do on its own.

The solution is to not give agents access to MCP servers.

The entire MCP ecosystem is ludicrous. You’re paying for inference for an agent to make the same decisions over and over again, and yet the actions they’re taking can be so easily written by those same agents into a bash script you can run again and again, deterministically and for free.

MCP is the problem. Having agents “use a product on your behalf” is the problem.

The pattern you’re looking for is that agents should write scripts that use products for us, and that doesn’t need a new protocol.

“Federal judge rules” is a phrase whose impact has been dramatically reduced during the trump era. You know that all flock need do is donate a few mill to trumps idiotic ballroom project or buy some of his idiotic meme coin or hire one of his idiot sons as a consultant and the problem disappears. The US is a despotic kleptocracy.

Smallulator

Agents just do this anyway, how is it a “mode”? I always see the agent writing scripts in a tmp dir to execute or even just inlining bash and python scripts.

What’s the difference between sub agents and separate sessions?

All of a sudden getting competitive on token pricing over the past couple of releases tells me they’re about to kill subscription pricing big time. The subsidised tokens aren’t going to survive the IPOs but if they can capture baseline dev tasks at a cost competitive with open weight models through Luna then capture the frontier token spend as well they could be pretty well placed. The Jarvis bros aren’t going to be able to afford their dashboards though.

Did you actually play the games? The Luna version is super buggy. Like when you eat a cherry you don't properly eat the ghosts, and you don't see your points when you eat a ghost. The DS looks worse but is more solid gameplay.

The DS one used Claude Code via OpenRouter, the Luna one used Codex. I'd say a big difference in cost is coming from the harness, and quite possibly the different meanings of "one shot" in each of those harnesses. The Luna one probably spent less money, but might have also done far less real browser testing and testing/verification is the expensive part.

The better graphics is probably just Codex system prompt.

In terms of real world coding usage, I am finding that DS v4.1 Flash is about half the price of Luna for comparable workloads. G6L is super cheap for sure, and super capable. It's by far the best coding model from a frontier lab for everyday coding work, but DS v4.1 is even cheaper and no less capable in my experience.

I go for weeks without topping up my Deepseek balance, and have to top up my OpenAI balance at least every week.

GPT 6 Luna closed the gap significantly for sure (it seems to be about twice as expensive as DS v4.1 Flash), but Deepseek v4.1 Flash is still the best value model and capable enough for almost everything I need to do. Sometimes if it's babbling or can't nail down a solution I switch to Sol for one prompt, get the solution, then switch back to DS. I use 4.1 Flash almost exclusively though for both planning and implementation these days.

I was a heavy Kimi k2.5/2.6 user but since 2.7 Kimi has gone way downhill -- even the previous models. I think they got under heavy load and had to quantise their models to avoid going broke.

Deepseek v4.1 flash is way cheaper and comparable intelligence

Deepseek 4.1 flash is back to peanuts pricing and more capable than 4 pro

Isn’t ASML a European company?

Randall Wray frames this as “tax bads not goods”. In other words: don’t tax payroll, we want companies to hire. Don’t tax labour: we want people to work. Don’t tax company profits: we want profitable companies. DO tax pollution. DO tax interest income: we don’t want people to get money for doing nothing. DO tax resource usage. If your houses are too big tax house volume. If your land is being banked tax vacancy and so on.

I’m not sure that deploying a custom clock synchronisation system would be warranted to show a countdown timer on the screen. The fix is to accept that the interface may be potentially inaccurate by a few seconds and send the relative time rather than the expiry time. Also probably to make the expiry UI stable (ie. have a “try again” button rather than flipping back to the start screen when the timer expires).

I also think that expecting that a computer connected to the internet in 2026 has the correct time isn’t too much of a long shot and things like 2fa QR codes rely on correct timing anyway.

Haha I’ve seen apps that never got RELEASED because of code base design issues. As I said maybe there’s a cliff somewhere but I’ve managed enough teams where I wasn’t reading the code to have an understanding of what unsalvagable looks like. I’m not seeing any red flags!

I dunno, I've built a production billing system for my small telecom company, a first version of a Multiplatform app with some novel technical features, and multiple internal tools for a company I work for, which replace a bunch of tools that were strung together using various off the shelf tools. I've been working with agents for about a year. I haven't noticed any cognitive or comprehension decline. I've built things that would have taken a team of offshore devs multiple months on my own in 4 - 6 weeks, including my own coding agent harness which runs an LLM gateway and has mobile, desktop and web apps which is now in use by non-technical colleagues to build and maintain apps on the same platform.

I don't know any more about KMP, Kotlin, Compose, Bash or React than I did a year ago. I'm not that familiar with any of those technologies (well, I am pretty familiar with bash but not to the level at which it's coded by agents), and I have never run into a situation where I felt like it would be better or faster for me to learn them and go hunting through the code to find some problem or other.

Maybe I'm heading towards a cliff somewhere in the future, but based on my experience of building software for 20+ years I'm not feeling anything but optimism so far.

I don't read the code my LLM produces unless I am investigating the code. I actually don't know Kotlin, or React.

My version of "code review" is "test failure investigation" and I have a hard rule in my repos that agents never modify existing tests while they're implementing features. This means that when I run the tests after they do a bunch of stuff, I see all the tests break. Mostly they're stale assertions and we patch them up. Sometimes they're regressions and we patch those up, and sometimes I notice something dumb and dive deep into a facet of the architecture that can be improved, spend some time exploring it then get the agent to implement.

I think it's a better approach than trying to read everything and catch bugs or improve quality because you wind up focusing the things that actually matter in the real world rather than the things you think might matter.

This is how I've always approached working with offshore devs too. Focus on testing for quality control, not "code quality". After all, you're going to look at the code you wrote 5 years ago and think it's shit anyway right? So all your code is shit.

Regarding "lack of understanding", here's a recent anecdote: I had a bug in a production (but relatively new) system. The customer was texting me saying that they couldn't scan a QR code because it kept "skipping and glitching". They sent me a short video. I described the problem to the agent and it figured out WAY faster than I would have been able to that the customer's clock was set incorrectly. They turned on network time and bingo bango, the thing worked straight away.

I don't thing "comprehension debt" matters at all, because if you want to know something about the code you ask the agent. I can't remember how anything works after 12 months anyway, so I would frequently have to spend ages grepping my own code when a customer came back and asked me to change something in a system we hadn't touched since last year. Asking an agent the same thing takes minutes and is way more accurate (and fun!)

Tax golf courses

But can they build their data centres ... IN SPACE?! (spoken like the dude from half baked who insists you need to try everything "on weed")

I’ve been using cloudflare tunnels quite a bit in places where I would have traditionally gone for a reverse port forward and they’re working really well. The quick tunnel concept seems really great but the non-quick tunnels are also very useful and can be entirely automated.

Que? Division is the opposite of multiplication of course it does.

If you divide 81 by 9 you subtract 9 from 81 until you get to 0. The number of TIMES you do that is the result “81 divided by 9”.

Saying something is 9 times bigger is also a shorthand because “times” is a shorthand for repeated addition. You are adding a number “9 times” to make it “9 times larger”. But we don’t say the “adding” part.

Likewise if I repeatedly subtract a number 9 times to make it “9 times smaller” I can omit the subtracted bit.