I find it very unlikely that it would be trained on that information or that anthropic would put that in its context window, so it's very likely that it just made that answer up.
No, it did not make it up. I was curious so I asked it asked it to imitate a posh British accent imitating a South Brooklyn accent while having a head cold and it explained that it didn't have have fine grained control over the audio output because it was using a TTS. I asked it how it knew that and it pointed me towards [1] and highlighted the following.
> As of May 29th, 2025, we have added ElevenLabs, which supports text to speech functionality in Claude for Work mobile apps.
Tracked down the original source [2] and looked for additional updates but couldn't find anything.
Eh, I'm no shill but their marketing copy isn't exactly the New York Times. They're given some license to respond to critical feedback in a manner that makes the statements more accurate without the same expectations of being objective journalism of record.
It's not what people mean when they say GC though, especially in reference to games, where you care about your peak frame time more than about your average frame time.
Reference counting can also have very bursty performance. Consider what happens when you decrement the last reference to an object which is the sole remaining reference to an entire large tree of other objects. This will trigger a whole cascade of subsequent decrements and deallocations, which can be arbitrarily large.
Of course, you might say, "Well, sure, but your reference counting implementation doesn't need to eagerly deallocate on dereference." That's true! You can write a ref counter that defers some of those deallocations or amortizes them across multiple operations.
And when you do that, now you really do have a garbage collector.
You should watch some of the more recent Gamers Nexus videos... the average frame pacing counts for a lot, and they're making a concerted effort to show this, as it does represent the level of "jank" in games very well.
More broadly than frame pacing, https://www.youtube.com/watch?v=Fj-wZ_KGcsg is a recent example of one of _many_ interviews going back years on why both frame times and frame rates are all flawed for explaining why some games feel smoother/lag more than others (there are GN videos dating back to 2016 on the subject)
Scroll through and read only the section headers. I would be shocked if this wasn't at the very least run through an LLM itself. For sure the section headers are, I'll skip the rest unless someone posts that it's worth a read for some reason.
It doesn't appear to be section headings glued together with bullet lists so maybe the content really does retain the author's perspective but at this point I'd rather skip stuff I know has been run through an LLM and miss a few gems rather than get slopped daily.
> I've only been using it a couple of weeks, but in my opinion, Opus 4.5 is the biggest jump in tech we've seen since ChatGPT 3.5.
Over Sonnet 4.5 maybe, but that's ignoring Opus 4.1 as well as Codex 5.1 Max.
In terms of capabilities, I find Opus 4.5 to be essentially identical to Codex 5.1 Max up until context starts to fill up (by which I mean 50% used) which happens much more quickly with Opus 4.5 than Codex AFAICT.
I think Codex is slower (a lot?) so it's not like it's just better, but I've found there are some tasks Opus can't do at all which Codex has no problem with, I think due to the context situation.
> Like, I have a 'Copilot' button prominently displayed in my New Outlook on MacOS (the only platform where the app-with-that-designation is sort-of usable), and it's a dropdown menu, and it has... zero items when expanded.
I guess that's worse than the Gemini button in Google Sheets that asks me to subscribe to AI services. I have multiple times been in a sheet and thought "asking an LLM how to do this thing I want to do right here in this product would actually be great if it works", remembered there was an AI-looking button in the top right, clicked it, and nope'd out of the subscription.
I just want to know if it works or not before I buy it.
I am an autist in a family filled with autists - some of whom I think you would CLEARLY recognize as autistic, but some of whom you'd have this "absolute nonsense" reaction to. I say that because that is the reaction I had myself, I was very skeptical of this whole thing until I came to learn a lot about it after my daughter was diagnosed.
I don't think it's mainstream science, but monotropism is a theory of attention which has been theorized as the central underlying feature of autism and you might be interested in looking it up. It makes a lot of sense to me. I think the more mainstream way of talking about it is bottom up processing (details, the trees rather than the forest) vs top down processing (holistic, the forest rather than the trees).
Either way - you can get a very diverse set of results depending on how which sorts of things the individual's attention gets commandeered by, and by how much. Some people can't stop paying attention to individual sounds or individual tactile sensations or any other individual sensation, some people have difficulty putting sentences together despite having an excellent grasp of each word, some get stuck trying to process specific individual facial expressions and fail to grasp the actual social dynamics going on around them - it goes on and on.
Some have special interests (deep attention to a specific topic) that are extremely economically profitable (programming) or simply socially mainstream (music or movies) which give them social cachet. Some have special interests that mark them as weird and socially outcast (collecting bugs, memorizing bus routes). Some are very intelligent and are able to make up for a lot of difficulties with effort. Some have a great focus on social dynamics and come off quite charming. All of this can add up to very different experiences though life, very different sets of difficulties, and that of course can compound.
I think you should expect there to be a very wide variety of autistic people, if there is an underlying similarity in processing things. There is a very wide variety of non-autistic people, too. Heck, I think there's a wide variety of people with only one hand, just because Jim Abbott was a major league baseball pitcher doesn't mean he actually had two hands, and just because Muggsy Bogues was a great NBA player doesn't mean he wasn't short.
From the article, Claude Code is being used extensively to develop Bun already.
> Over the last several months, the GitHub username with the most merged PRs in Bun's repo is now a Claude Code bot. We have it set up in our internal Discord and we mostly use it to help fix bugs. It opens PRs with tests that fail in the earlier system-installed version of Bun before the fix and pass in the fixed debug build of Bun. It responds to review comments. It does the whole thing.
You do still need people to make all the decisions about how Bun is developed, and to use Claude Code.
> You do still need people to make all the decisions about how Bun is developed, and to use Claude Code.
Yeah but do you really need external hires to do that? Surely Anthropic has enough experienced JavaScript developers internally they could decide how their JS toolchain should work.
Actually, this is thinking too small. There's no reason that each developer shouldn't be able to customize their own developer tools however they want. No need for any one individual to control this, just have devs use AI to spin up their own npm-compatible package management tooling locally. A good day one onboarding task!
reply