brabel

The post seems to be talking about a html injection via a postMessage call where the receiver didn’t check who sent the message, which is a well known vulnerability entry point. Did I miss where OAuth had anything to do with this??

Yep that’s a great summary of what my wife, a professor, tells me about every day.

The funny thing is that you can easily get a LLM to introduce typos and grammar mistakes if you ask it.

I have a theory that every typo you make distracts the LLM from whatever you are trying to get it to do, so I avoid typos as much as possible. I have no evidence that this is true though.

I used to scour through server logs, build logs, test reports etc to figure out why tests were failing in CI. That was exhausting work and could take days of investigation. Now I get the exact root cause in a couple of minutes. Just had to give LLMs a token to call Jenkins API and it knows how to do the rest. What an unbelievable experience. Never ever thought computers would be able to do this in my lifetime.

I think you may want to look at ChatGPT Apps. It’s like a React app you can embed in the chat directly. The LLM cannot see the app itself , only whet your MCP actually sends to the agent. We did this with a customer and it looks very cool and we can do all sorts of advanced things like any UI can without agent calling tools unless you want it to.

emacs 31+ started emiting this warning for my custom Lisp files:

Warning (files): Missing ‘lexical-binding’ cookie in "~/.emacs.d/custom.el". You can add one with ‘M-x elisp-enable-lexical-binding RET’. See ‘(elisp)Selecting Lisp Dialect’ and ‘(elisp)Converting to Lexical Binding’ for more information.

I am still trying to figure out what to do! The manual is quite verbose and I haven't had the patience to go through it yet.

What are trying to say exactly? That only beliefs in a god or gods are really religion? But that any strongly held set of principles is given the same benefits by law as a real religion? What’s the point? If it is treated like a religion by people and by law, who cares if it involves believing in a god, or many, or none??

The whole argument that you always know when Zig allocates is just wrong, as this shows. They “fixed” the hidden allocation by making it explicit in the append function but now you can pass in the wrong allocator. Not great is it? It is just all so fragile and relying on convention rather than hard checks. People sometimes pursue a bad idea to incredible lengths and then everything else is justifiable based on that initial, bad idea that just causes much more pain than it solves.

Haha same here. The M1 Pro is such a powerful machine and it still works great. I did buy a MacBook Air M5 for non work, and I think it’s about as fast as the M1 Pro, but the latter has 64GB of RAM so I can actually work. Will probably request a new one next year though, it’s time.

I worked at a company that tried that 15 years ago. The problem is that the incentives for such businesses is perverse. It’s basically impossible to avoid people trashing a competitor’s product to promote their own, paid reviews, taking fees from manufacturers for making good reviews more visible for them (gotta pay the bills), all sorts of things that eventually makes your business unreliable just like all others.

That’s just not true especially when the author designed the language with the LLM like he says in the end (the AI is very good at forcing you to be specific and make decisions on ambiguous terms): all decisions can be included in the repository in a way the computer can follow and understand, which is a pattern called specification graphs. You can just document things in the docs as well if you want a more basic method. If you are claiming this language is worse in every way than others that were made by humans alone, could you be specific?? What are the bad things you’ve found? What part of the docs are incorrect? Or are you just commenting without having looked at any of that?

I've tried ThinkRail now.

I am a paying user of IntelliJ IDEA Ultimate, but lately I've been using mostly Claude Code Desktop App.

This is a cool product. Clearly, they made the agent chat pane the primary feature, while things like the Project Files and the editor itself is secondary (you are not even allowed to change files manually!).

The chat is very well done (I think it's just Pi?). People are saying how they use the IDE mostly for reviewing code, and ThinkRail makes that a primary feature as well: every change the agent makes gives you a "Review Turn" button that lets you look at exactly what was done. And the diff viewer is very good (not the same as IntelliJ, seems more like the VS Code viewer?).

It stores everything the agent does as a "Turn" so you can review every change at any time, like a git history. It also has the git log similar to IntelliJ, so you can still click on each commit in the history as well. In fact, the two things seem very similar, since each "Turn" normally results on a commit as well. It's stil unclear to me how "Turn"s are useful beyond the commit history.

It also has a fully functional terminal so you can try out things easily without leaving the tool.

JetBrains seems to have figured out how people are using their tools nowadays, and decided to go all in with this "Innovation Lab" tool.

I would still expect to be allowed to edit code/text myself in it, and maybe navigate around like in IntelliJ, but I guess I'm in the minority :P and most people just need something like this?! It's definitely much lighter than IntelliJ (it shows way down in my process list by memory, with around 140MB after quite a bit of usage, and it's highly responsive), so perhaps that's the main advantage, and bringing code navigation/editing/highlighting for all languages (it highlights the most common ones, but not LISP for example) would just result in a heavy tool again.

Its way of working with git worktrees exclusively is something I was already doing in the Claude Code App, so I think they got this right. However, CC App can also use a SSH remote connection (like TRAMP in emacs) to a devcontainer, and I've been using that a lot, so would be nice to have that option as well.

In conclusion: I like it and I think they may be going the right way with how things are going: the "IDE" becomes primarily a means to interact with agents. But at least for me, it's a bit too early to leave the full IDE completely, and I guess they could've made this just a "mode" inside IntelliJ without losing anything except for being very lightweight, and perhaps that's what they're going to do eventually?

I think you didn't understand my claim. My claim is simple, my long explanation above was meant for you to arrive at these conclusions yourself:

* people are nice when they still behave in the old, tribal way.

* the tribal way is always going to be creating individuals who are racist and conformant/conservative.

* not behaving the tribal way means going outside the conformist mold, which means you take risks and eventually learn by experience that taking more risks come with consequences. You become less trustful of everyone, while almost paradoxically proclaiming yourself to be more open.

This fits observation. If you believe it's wrong, you must demonstrate why with supporting evidence without contradicting the evidence I've used, obviously.

I love JB, IntelliJ IDEA is just great, but I am using it less and less with agents now. I see JB Toolbox has "Junie CLI" available for me. Have you tried both that and ThinkRail or Air? Which would you recommend for someone who is currently mostly working on the Claude App (which also manages worktrees seamlessly, which looks like what ThinkRail does)?