terabytest

If you can, please take a look at the discussion I started on the repo. https://github.com/saffron-health/libretto/discussions/227#d...

I haven’t used libretto myself yet but I’m excited about having this kind of tool at my disposal as it’s been a need in the past.

Are they selling this anywhere or is it just a marketing gimmick?

Looks awesome, but I wonder if its functionality could be exposed to existing CLIs such as Claude Code instead of having to run it through its own CLI, mainly because I don't want to spend on credits when I've already got a CC subscription.

EDIT: To clarify, I realize there are skill files that can be used with Claude directly, but the snapshot analysis model seems to require a key. Any way to route that effort through Claude Code itself, such as for example exporting the raw snapshot to a file and instructing Claude Code to use a built-in subagent instead?

Why did you choose this plan in place of a fixed price plan?

How is this on the front page? This reads like pure AI slop. It feels like an insult to the reader.

OP: if you thought you had something useful to say, why didn’t you write it in your own words. There’s no useful content I can discern while reading this post.

> FastRender may not be a production-ready browser, but it represents over a million lines of Rust code, written in a few weeks, that can already render real web pages to a usable degree

I feel that we continue to miss the forest for the trees. Writing (or generating) a million lines of code in Rust should not count as an achievement in and of itself. What matters is whether those lines build, function as expected (especially in edge cases) and perform decently. As far as I can tell, AI has not been demonstrated to be useful yet at those three things.

That’s not what I meant. What I’m asking is whether there’s any evidence that the latest “techniques” (such as Ralph) can actually lead to high quality results both in terms of code and end product, and if so, how.

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.