jug

How would the NYT Cooking website even look like if it was entirely modularized into pieces that could be turned on and off to customize it to perfection for every taste?

This AI thing is not even active nor activated unless you use it. The complaints here sound more reactive to the word AI than anything else to me.

Above all, I think I like human docs because then I not only know someone has a deep understanding of it, but also that someone can actually be queried about it. With Claude, there is always the accountability problem. If something seems off, do I even have someone other than Claude that understand it all and who is accountable ?

Understandable choice. Let French users work around these controls in other ways rather than have authorities force you to abandon who you are and what you believe in.

I share the opinion that DNS is a purely technical system part of running the Internet. That DNS is attacked is only out of convenience rather than solving whatever actual problems the actors in question are facing.

In case of copyright infringement claims as in this article, the way to solve this is to deal with the criminals, not terrorize the road network that gets you to them or burn phone books just because it's "easiest".

Why is it that this so often is excused on the Internet? My theory is that it's because the inner workings of Internet is opaque to the common user; a takedown notice via a DNS redirect will look to an end user as if law enforcement got to the criminals themselves, so they get away with it. Even if they didn't because they did a too poor work, were too lazy or didn't want to spend the resources. But these factors shouldn't result in attacking others' valid business models for it and instead result in either accepting your situation or changing your situation.

Surely only in the specific meaning of "scientific theory"? E.g theory of gravity.

So 2/3 from those that are? It just means that those that are need to do more heavy lifting because there is at least a choice. Fair? No, but Earth doesn't care about what is fair and who does the most. It only cares about total output and so will the environment you live in.

And everything to a beat by Daft Punk.

From what I saw Flux 2 Klein or Qwen Image 2.1 might give you a less frustrating experience at comparable or better performance. We shouldn't be dealing with body horrors in 2026. Feels like a major regression.

Yeah rumor ahead of release was also that some Googlers were anxious about the known subpar coding given modern trends.

They're seriously using AI as a judge for what to file?

And soon Firefox will include it in Stable. During October it will go from Safari only to majority coverage. Eventful month!

While AVIF may have a slight edge in some cases like in fairly lossy compression, you won't really go _wrong_ with JPEG XL (unless strongly CPU constrained) and I think the strength of the format is its extreme versatility as a "be all end all image format" for some time where comparative performance depending on functionality ranges from respectable to excellent. It can work as a replacement for AVIF, PNG, JPEG, WebP, even certain TIFF required scenarios (high bit depth, multichannel, layers) depending on use cases.

I checked price per AA task and yeah Argon vs Opus 5.5 High are practically neck and neck both on "intelligence" and cost per task. So if you aren't pushing higher on Opus (which I think can quickly become very expensive and I always treat Max and those like "benchmark settings"), I think this becomes more of a matter of which platform you like more or prefer for various reasons.

Honestly, I think this will be a trend in 2027 when all those models become "good enough" for elite coding and whatever. I predict they'll have to branch out more and build their platform to differentiate themselves from each other, maybe even in terms of branding and trust, marketing towards various demographies, youth vs elderly, students vs employees, etc.

We also have Nerf Bench:

https://www.bridgebench.ai/nerf-bench

They test it on launch day, then benchmark it against that. A deviation of above 10% is considered a change. They're currently tracking Opus 5.5 and GPT-6 Astra.

This bench famously detected a degradation of Opus 4.6 which Anthropic later blogged about. I personally think people sense nerfs more often than they happen and that it's often about honeymoon effects.

It's apparently great at Max but extremely costly. Looks best to me at Medium and High. Over that and I'd go Opus. I consider Fable largely obsolete.

My favorite is "Defender scanned your computer 8 times. Nothing was found."

There are a few bad puzzles (especially one regarding infernal critters) that one can use a guide for, but mostly it was a blast to finish it back in the day. Such a unique story by itself and then in a rare comedy / noir style on top! It's kind of crazy how they even came up with it.

I still remember the feeling of the ending, and the end credits music when the violin kicked in as it played the Manny & Meche theme! The music is at least as good as this game.

And without this harness it scores about 62%+, a dramatic improvement over even Fable 5.1 at 30%. I thought it just bears saying for context.

Political? It's using a Chinese LLM trait. If it only refused to talk about a particular kind of soccer, we'd probe it with that instead. The goal is not to discuss politics, the goal is to find out which model it is. What's political here is the language model.

From what I'm seeing I do believe TikTok is worse.

I really like the combo 5.6 Luna & Sol for price and performance and would be perfectly happy if they stayed here for a moment without mucking about with sidegrades that I think AI evolution has often felt like lately.

This is true and is only becoming more important the more they improve. I am already moving to checking so they're at least somewhat following the status quo and otherwise prioritizing price and platform. I think this will be an emerging way of viewing AI in 2027 and the winner will probably be open models and China.

If that's marketed well it feels like it should cause a system shock like R1 did. It would also be interesting to see the reaction with code models becoming so good already i.e. cost efficient models aren't necessarily invalidated early by progress that matters.

Yes, I've seen this too and how Luna xhigh is so good that Terra doesn't really serve a purpose because beyond that you can continue at Sol medium. This can be the most cost efficient way, and especially now!

Kimi K3 is fairly cheap per token but thinks like a madman with poor self esteem.

So is this how Opus 5 ran it?

https://arcprize.org/results/anthropic-claude-opus-5

In my opinion, next step is to cut down on reasoning tokens while maintaining intelligence. The Chain of Thought and looping can still be an issue with these Chinese models. They in fact said K3 would improve in the area but it's still an issue that unfortunately harms the token cost wins a bit. OpenAI has been really impressive here, on the opposite end of this.

I agree and this is why I think open models will win in the end. There is just so much to gain on being 10% behind the curve. Especially when the curve is far beyond your needs.

This will also make it harder to compete because it holds true for everyone, not just you. I am already, this year, seeing vibe coders put out some decent stuff on App Stores but the problem is marketing it. You no longer automatically stand out just because you have a cool app. You may not even do so with reasonable early traction via social media. And then what? Throw venture capital onto the problem? In an AI saturated world? Really?

Yeah I've noted this behavior with best in class open weight models. They said K3 would have token efficiency improvements and I was hoping especially solving the thinking loop issue that plagued K2.x but even if this release helped somewhat, it looks like we still have a long way to go here... I'm not sure what's up here but I suppose lacking finetuning quality.

What OpenAI in particular have done with reasoning efficiency in the past few months since ChatGPT 5.5 is nothing short of remarkable. It's overshadowed a bit by the benchmark game and the Fable hoopla.

Now is the time to focus less on token cost and intelligence, but tokens to solve a particular set of tasks in closed benchmarks for a variety of categories.

What is the use of grand intelligence if it either costs you a kidney or can't complete at all within a token budget? Even if there are niche uses where you truly want "maximum power" above all, we need to at least more severely penalize such models versus those that does it just as fine within a tenth of the token cost.

I'm aware of some benchmarks at the Artificial Intelligence site, but CLEARLY we are not focusing enough on these today and still leaving the fun surprises to the users.

I think they're less and less advertised as true generalists these days, as they pivot to profits that obviously lie (for the time being) first and foremost in agentic coding. It's no longer unusual to see regressions in terms of more stiff prose due to the strong tuning towards coding, or how they structure their response. And prose is a LLM's home turf! Instead, progress in agentic coding capability is usually the headline feature, the headline benchmark, etc etc. At least looking at Anthropic, Google, OpenAI. There are of course other LLM's.

So then add a dash of cybersecurity and medical use and that's basically it. No "closer to AGI" advertising. I'd say the 2026 development has in fact been the opposite; optimizing AI for niches where there is most potential for profits and that your description died in circa GPT-5 era.

In fact, this problem (for this test) is also stated by the pelican test author:

"The biggest limitation of the pelican is that it doesn’t touch at all on the thing that matters most for today’s model: agentic tool calling and the ability to operate tools reliably as conversations grow in length.

So don’t go using pelicans to compare models!"

Addiction due to the dopamine hits of occasional struggle and then churning out apps that work: https://leaddev.com/ai/ai-coding-is-addictive-engineers-are-...