Ideally: no.

All new shiny new features shouldn't have waited for the (N+1).0 version, they should already have been part of the (N).(M) version.

In practice, the removing the deprecated cruft will remove blockers for some new features, but that should be rare.

In a true competitive Turing test, these reasoning pitfalls could be included in the system prompt, there are not that many of them. The tester would need to find a novel reasoning pitfall, but those aren't uncommon among humans either, so that would not make a very useful differentiator.

Another approach could be to probe the helpfulness of an AI. A human would likely not comply with a request to write a sonnet about tangerines.

I don't understand what you mean that "there are not that many of them". The models, even the best ones, still have clear problems with certain kinds of real world reasoning, and it's not a known, closed set. With some prodding and knowing this error mode, I think it's not hard to trip any model with a novel reasoning error like this.

And no, I don't think humans would make the same errors, the key reason for this failure mode is that there are some facts of human day to day life that are so mundane that they are virtually never written about, thus making them an ideal combination of universal human experiences but out of distribution for the LLMs.

Or atheists for that matter.

I was a bit put off by the implied hostility there, even if it was in jest. It's a risky choice to jokingly discriminate based on religion, ethnicity or political affiliation, mostly because such a joke is hard to distinguish from almost identical contexts where it isn't a joke.

It sounds like it didn't appeal to at least one atheist. Truth in advertising.

Would the world be a better place if no one told any jokes that 'might' upset others?

I'm an atheist too. I just gave a middle finger to the author and carried on reading.

I haven't really delved that much onto 9front but they do have an interesting style, see for example https://9front.org/propaganda/ yes it's probably going to rub people up the wrong way, but at least it isn't more corporate bs.

It feels different if someone has recently been discriminated against. Jokes land differently when they are too similar to reality.

That said, making edgy joking is definitely acceptable, you'll just alienate part of your audience. That's why the hollow corporate bs doesn't do it.

Do realize that the author is Czech. While being religious is the default and atheists face (mild) discrimination in places like the US, at least until the 1990s and the fall of Communism, things were reversed in (then) Czechoslovakia, with state supported atheism and religious people viewed as suspected dissidents.

Honestly, I don't take offense at the joke. There's a reason freedom of expression has some degree of protection in many countries, and it is so that people can slander each other's religion or lack of it with impunity. I mean, I'm pretty sure it wouldn't be constitutionally protected if it were about football clubs' rivalries. So I slander God at every opportunity I get, while actually being an atheist, because I find the given solutions to the problem of evil abominable and have mild objections to the morality of whoever swallows said solutions. Though I would never bar people of faith from using an operating system I contribute to; why in hell would I deprive them of a platform to read my slander?

There's a church of iconoclasts? Are they always starting over?

Oy vey.

The added value of the LLM here is probably zero. Just type a search propmt in a search engine. If the top 5 results don't cover the same ground your article is covering, at the very least, your article will expose new knowledge to people using that search term.

Typing up LLM instructions and reading the output is probably more work.

What would be the incentive for site owners to reduce the appeal of their site? The user has connected to the site, so there's obviously no immediate problem.

Back when Https deployment wasn't widespread, Chrome added a deliberate delay to http sites so Https sites appeared faster. That was the incentive for deployment for many, because until then Https was generally slower (extra round trips to set up the tls connection).

In the video you can see that the LED lights the logo less evenly than the EL lighting. While that's not important at all, this might be the reason behind this odd choice

A disposable sandbox wont protect you from secret exfiltration. Assuming you don't consider your code a secret, you could of course set up your sandbox so it doesn't have any secrets, but that would severely limit the kinds of tasks you can use the agent for.

On the one hand, you can set up a proxy that supplements secrets for API calls. On the other hand, you can whitelist what you need, in the simplest case with iptables (The devcontainer in the claude code repo is an example of the latter).

<< that would severely limit the kinds of tasks you can use the agent for.

Are we just talking about API calls to providers? If so, wouldn't local agent + sandbox solve all that?

If flying ever becomes efficient energy-wise, this may happen. However, right now, flying is very energy inefficient, so anything that doesn't need to be flown, is transported overland to save costs. A change of fuel won't change it, unless the underlying energy usage changes fundamentally.

Better batteries do not impact energy usage, only the means of energy delivery.

The data centre runs on a dedicated power line. My laptop runs on battery. Using coding agents currently drains battery quite fast, which is surprising, given that the vast majority of the work does not take place on my laptop.

Making the client side coding agent more efficient isn't about saving the climate. It is about extending the workday (which might actually make the climate worse)

I feel that grouping related change in commits can be challenging, as git really presents commits as grouping in time, not topic.

It is certainly possible to do topic-grouping in commits, but it requires significant effort to het that consistent on a team level.