spockz

In the scenario mentioned in the GP post where a giant tropical storm hit resetting the grid for 7+ days, how big is the chance that your solar panels installation has survived? Also, if the grid is gone, won’t the fast chargers also be out of service?

Don’t get me wrong, I think you’re right for most cases but I also think for some more end of the world type of scenarios there is little that beats a generator and stored fuel.

And all of their problems started 12 years ago? That seems unlikely.

Look at Venezuela.

Is it an issue for every package manager? In theory, yes, in practice no. Debian and arch etc have so many mirrors that it isn’t an issue.

That would actually be a brilliant treatment to give wedding bouquets! I’ve never heard of Cosmoline. Going to look it up. Thanks!

I purely intended to use it for review and architectural design given my bad experiences with Gemini coding. The bad experience stemmed from it getting stuck in loops and burning quota. The code quality when it worked was great.

I now asked Argon for a pretty elaborate review and it used only 2% so I will be giving it another shot.

Another thing that can be of influence is that for subscriptions, Google uses some proprietary idea of “work done” for the quota instead of simply how many tokens were burned. I can imagine that this heuristic is sometimes quite off.

I think it should classify as an escape or leak.

If one microVM can use the cpu in such a way that the registers can be used to communicate or exfiltrate/spy (the only difference being the directionality of the intent) by another microVM that is a leak on that microVM separation level.

I had to read this a few times. The difference is that with the OpenAI case there were two willing and determined parties, whereas the typical attack vector a microvm traditionally deals with is one malicious or compromised microVM trying extract data from another unwilling one.

I’m using the default anti gravity setup. 3.8 medium is my daily driver. This gets me pretty far. (Definitely not as far as Luna and Sol). When I ask the same question to Argon it is 50% of my weekly usage limit gone. So either the usage limit is really a lot smaller or somehow argon thinks a whole lot more even for simple tasks.

Im using pro on a discount. I got argon a few days after the release but the usage limits are worthless. Asking it for a simple review of a blog post blows through 50% of the usage limit. And in the limited experimenting I have been able to do because of that it also isn’t smarter than 3.8 flash.

For me it is that cmd+` only cycles between windows of the same app in the active desktop. It makes it hard to switch back to a window of the app that was put in full screen.

I get that that behaviour shouldn’t just be changed but I would appreciate it if there were another key combination that would allow cycling through all windows of an app.

Intelligence is a paid product so I cannot test it. I would say that code intelligence and proper refactoring support instead of scratching around what agents do now is the direct next step for IntelliJ.

And probably something to understand what your agents are doing and why. With which reasoning.

Otherwise also stay a damn good IDE. We still need that. My agents are floundering on our bigger codebases and only produce warts.

Not sure. They flagged it. I appealed and told them what I was doing and the flag got lifted with a sorry our bad.

> You must not attempt to extract protected reasoning through unauthorized access, reverse engineering, or circumvention of safeguards.

This is the only mention of reverse engineering on their ToS. It only applies to trying to reverse engineering their models not others.

Moreover, their ToS is all about protecting security and privacy, which is what I was using it for.

But why do we have such a (imho unfounded) desire to be a be able to open a file in a proprietary format from 30 years ago and expect to be able to edit it like nothing happened in the mean time?

If we care so much about that it actually looks the same after all that time, why is it not a pdf?

I’m so confused that anyone would get hung up enough about this to let it block a migration of this size.

Yes a personal subscription. Individuals can also request it. only blue for defensive questions. Red for offensive is gated to organisations that are proven to be using it for protecting.

https://chatgpt.com/cyber

In my efforts to reverse engineer the LG firmware to validate Gamers Nexus claims, I got a warning very quickly. I appealed that quickly and successfully.

Then I applied for daybreak blue and haven’t had any issues since.

It also a matter of phrasing. Say what you want to achieve not how if it is approaching defensive or cyber stuff.

Also state you are working on your own devices and software. (If that is the case of course.)

Yes that if reactive. But I think GP meant what their responsibility in this is given that they signed and thereby vouched for an intermediate ca that now has become untrustworthy.

But do those tools have to be directly exposed to the web at the same place the content is being hosted?

That you want your content to be readable from everyone doesn’t mean you want the admin interface to be available globally.

It just means that the safeguard we put in place over decades of software engineering with humans also need to remain in place when engineering with agents.

Having properly validated libs with separate concerns and a lot of eyeballs (and agent sensors) on the code so that it can be integrated cleanly in other products. Static code analysis for our apps. System prompts that require output to be secure, etc.

All of these practices that have been touted to be obsolete because agents can now just generate tailor made code just when and where you need, are anything but obsolete. On the contrary, they are paramount to the future of software engineering.

Why would you use boring tech to dynamically create sites that are inherently static?

Codex happily removes things I ask it to all the time. Do you have a special phrasing in agent instructions such as AGENTS.md?

I do pass the wheel over on long trips. We take turns and we swap when someone feels to tired to remain sharp.

Will we at Some point start slamming two stars into eachother to make gold pressed platinum bars? Or will the energy expenditure required for that be sufficient to create gold and platinum straight?

Interesting that this hasn’t been my experience. ChatGPT has often gave me with pages of text dripping with confidence about a solution for my problem. Diving very quickly into implementation details. Even if I tell it to stay in the problem and product fit level. Gemini on the other hand somehow always outputs at the level that I am expecting and reasoning.

I even found it was capable of stepping back from code implementation and bug hunting to “hang on, it’s not the algorithm that is incorrectly implemented, it is the wrong algorithm for the goal.” GPT Sol (5.6,6 and 6.1) just kept hammering in the problem.

Gemini 3.8 for me always outputs in a concise way at the level understandable for any computer science masters graduate. Clear, to the point, a bit of formula for background when really required instead of the same formula in Prose, etc.

GPT stays too much in text imho.

This is why I am working on https://github.com/spockz/semantic-editor. To bring more powerful editing functionality to agents. In a way that attaches to their chain of thought and deals with their probabilistic framing in json so it all works out cheaper and faster.

Ill check for this in my setup. I thought it came with only one thinking level causing the “meandering” as it refers to its own long CoT.

I’m doubting the quality of the model, even comparing with luna 5.6, it is giving such bracingly wrong answers. It claims other tools have changed the code when pressed why it made a mistake. That code or tool didn’t come close to working on the project. It is scary.

That was the case with the M1 indeed. Subsequent releases have been allowed to consume more power. My M5 Pro gets too hot to use on my lap when full out compiling or playing games.

This hits a note. It has so many aspects.

People who made something their professional life goal to become good at something have their work marked as AI, and even worse, like effortless or slop. Just because a tool has been trained to match that good style or type of output. A good system (tailwind) is not used directly anymore because the LLMs take all the wind of their sails by embedding the knowledge in the model.

This happens all without any form of attribution or compensation.

It’s not nice. But I don’t know what to do about it.