terabytest

This is exactly the issue I have with what I'm seeing around: lots of "here's something impressive we did" but nearly nothing in terms of how it was actually achieved in clear, reproducible detail.

Your point is fair, but it rests on a major assumption I'd question: that the only limit lies with the user, and the tooling itself has none. What if it’s more like “you can’t squeeze blood from a stone”? That is, agentic coding may simply have no greater potential than what I've already tried. To be fair I haven't gone all the way in trying to make it work but, even if some minor workarounds exist, the full promise being hyped might not be realistically attainable.

So far I've found https://github.com/jae-jae/fetcher-mcp which mostly does what I want, but it only started working well when I asked Codex to run it with `disableMedia: false`.

How do you prevent DoS attacks?

This is about Groq (the semiconductor company), not Grok (xAI’s LLM).

No experience in the field, other than 2048, so take this with a grain of salt.

In my opinion it’s about your ethical stance and who your target audience is, and whether you’re trying to make a ton of money or just enough to survive. You’re obviously going to fight an uphill battle if you don’t employ any such (predatory?) marketing tactics. However, you could position yourself as explicitly standing against those and that might attract a smaller but loyal user base.

If you’re lucky, and build something good, and people talk about it, you might find that you’ll get users regardless. However, at the end of the day, what matters is whether you can keep the lights on, so you may have to relax some of your stances and rules or find ways to market your product that don’t fall into the categories you’ve described.

How does Opus 4.5 compare to gpt-5.1-codex-max?

This one’s hilarious. What was your prompt?

Can you point out the issues with the article?

I really struggle to wrap my head around how this engine works. I haven’t used it, but I have experience with Source 1 and its systems and I imagine Source 2 is an extrapolation of that. But I really can’t wrap my head around how they’ve turned it into a scene-based game engine when Source 2 is map-based, how they’ve managed to build a completely different editor that still leverages Hammer maps somehow, and all the other stuff.

I haven’t heard about his views on Russia but that’s worth looking into since I also have his books.

Just a quick nitpick as a fellow Italian: “delusion” (“illusione”) is a false friend of “delusione.” Maybe you meant “disappointment”!

This website appears broken in a very unique way on my iOS device. Whenever I swipe to scroll, the page gets zoomed out and it zooms back in when I stop swiping, but half of the content is cut off.

Sounds like a bit of a chicken-and-egg problem. My main issue is to even get myself to sit and stare at the work to be done. It has been really frustrating seeing the lengths I go to, consciously or unconsciously, to procrastinate.

FSD is widely considered to be off its originally-stated goal by at least 5 to 6 years.

What’s with this trend of not capitalizing and punctuating? Are we running out of budget for capital letters? It makes the writing look sloppy and pretentious. Who is the author trying to impress?

This title had the garden path sentence effect on me.

https://en.wikipedia.org/wiki/Garden-path_sentence

It looks really nice. I wonder if it’d be possible to break it down even further by somehow instrumenting the actual processes and including their execution flame graphs as part of the chart. That would expose a ton of extra information about the large gaps of “inactivity”.

I'm confused by the author's diagram claiming that AGI/ASI are points on the same manifold as next token prediction, chat models, and CoT models. While the latter three are provably part of the same manifold, what justifies placing AGI/ASI there too?

What if the models capable of CoT aren't and will never be, regardless of topological manipulation, capable of processes that could be considered AGI? For example, human intelligence (the closest thing we know to AGI) requires extremely complex sensory and internal feedback loops and continuous processing unlike autoregressive models' discrete processing.

As a layman, this matches my intuition that LLMs are not at all in the same family of systems as the ones capable of generating intelligence or consciousness.

As a European, American culture baffles me in this regard. Things like school shootings, police violence, traffic deaths, healthcare, alternative (public) transportation, all seem to be linked by a common thread of inaction towards things that should in principle be solved. And it seems baked into the way the system works, if not the culture itself (due to the focus on U.S. exceptionalism/defaultism, individualism and bias towards individual freedom at others’ expense). But I wonder what causes such structural cultural/political issues to just be ignored.

As someone who doesn’t know much about this, I'm curious:

If humanity survived far into the future, could we plausibly develop ways to slow or even halt the decay of the universe? Or is this an immutable characteristic of our universe, meaning humanity will inevitably fizzle out along with the universe?

Critical alerts are available as an optional setting for medication reminders in the iOS Health app.

The large catalog of mixed DJ sets on Apple Music is the main reason I’m considering switching from Spotify.

In my city, I noticed that some shops in some streets keep changing hands over the years, and some are stable even if they don't look like they get a lot of traffic. I never investigated this or looked deeper into it, but I have a hunch that it also has to do with "fluid dynamics" in some sort of way. Meaning that the shop is located in a "low pressure" zone of foot traffic where people are either moving fast, distracted, or pushed away by some kind of obstacle. Or, the shop is somewhat less visible than the surrounding ones. This leads the shop to not getting many visitors, and eventually closing. I wonder if there's been any research behind this.

That’s amazing! Such a cool story. I’m really happy that 2048 was able to help you this way :)

I think 2048-AI had this, but I’m not sure. It’d surely be pretty evil. Imagine it turning on randomly when it detects you’re going too fast :)

This is interesting feedback. I always thought that ads being unobtrusive and not part of gameplay would be the saner choice. In my mind, when games ask you to trade watching an add for some kind of in-game benefit or currency, that feels like an unreasonable demand. The ads impinge on the gameplay. The way I've set up the site, ads are tucked in their own corner and should never affect gameplay (though there have been instances of ads spilling over the powerup bar, I'm working on that). Thanks for sharing!

Thank you for your comment. I wanted to add that credit should indeed be given where it's due and that while I didn’t mention Threes in my original post, it has played a significant role in 2048’s existence. Threes is credited on the play2048.co site (and now also on GitHub), and I’ve always tried to acknowledge its influence.

That said, I think there’s a balance to strike. As I mentioned before, I created 2048 before I became aware of Threes, and while it’s important to credit inspiration, I’m not convinced that every creative project needs to trace back every indirect influence. 2048 began as a small experiment without any intent of gaining popularity, and it grew into something distinct, shaped by the viral spread and its community of its open-source variations.

I understand the value of recognizing origins, but I also believe 2048 has developed its own identity over time. I appreciate the feedback, and I’m always open to improving where needed. Thanks for sharing your thoughts.

Again, I understand where you’re coming from, but I don’t fully agree. While Threes was an definitely inspiration along the chain, by your logic, any creative work would need a detailed credit trail, even when it grows and evolves into something different. 2048 was not intended as anything other than an experiment, yet it took on its own life, driven by the unexpected virality and maybe by its simplicity. I’ve always tried to acknowledge Threes’ role, but I don't know that I should attach this label on every mention of 2048. I appreciate the perspective you shared.

I wanted to address this, because I understand where you come from. Threes is actually credited in the about page[1] on play2048.co.

The frustration is completely understandable, as Threes is definitely where the concept originated. Due to the chain of derivative games that led to the creation of 2048, I had not seen or heard of Threes until after it went viral. I think the inspiration Threes provided, although valid, is somewhat indirect in the case of 2048. I did try my best to reflect this in the about page and when I talked about my experience here[2].

I noticed there's no mention of it on GitHub, so I'll add it there. I am happy to do better given the feedback, but I'm not sure what kind of improvement I could make here. Let me know

[1]: https://play2048.co/about

[2]: https://medium.com/@gabrielecirulli/2048-success-and-me-7dc6...