bird0861

How to spot a Claude user.

But seriously, Opus has been garbage after 4.6 -- the public seems very easily fooled into thinking breadth == depth. Anthropic, I'll grant them, has been and is still an extraordinary data team. As for model alignment though... I have to wonder sometimes if they are even trying beyond just chat training.

"Guys, SI is just around the corner... Huh? What production DB? Anyway GPT2...I mean Mythos is too good it would be dangerous to release to the public!"

You can disagree but no one has to care...unless you can mobilize an army.

Anyway it seems like much of this discussion presupposes the virtue of law and or has amnesia regarding its origins and its service to power. Sure there are exceptions, not every civilization has turned into a tinpot dictatorship because they adopted having a legal system. But without exception, it's those in power who make the rules. And quite often the powerful make rules that benefit them...often benefitting them exclusively.

I would rather live in a society with just laws than not, but again who settles what is just and what is not? Some people clearly have very different ideas. And yet geopolitics and world history aren't determined by the discourse.

And anyway, the law and justice are two different things. Many judges and attorneys will tell you so, I've known more than a few.

You should see Pixal3D. You don't even need a time-of-flight laser anymore. Images are enough. In fact, this sort of thing + image generation, and soon video generation, have lead to workflows that result in both 3D and 4D (time series 3D) gaussian splats.

Irrelevant. Open models are competent code generators. No you don't need millions of H100 hours to build them.

Let's see Paul Allen's card.

Just want to add to this that with custom calibration data it's incredibly effective and surgical, you can get VERY LOW KL divergence this way. Many MoEs are supported too, it's actively maintained.

A good general rule in life is that people get one chance to show why they're not worth communicating with, and that's it.

It's very easy to convince yourself it's true and then hand out punishment like it was on sale.

add that to your claude.md

Hilarious that this got a downvote, hello Satya!

With respect to the first issue you raise, I would perhaps start including prompts in comments. This is a little sneaky sure. And maybe explicitly putting them in a markdown would be better. But there's the risk that markdown won't be loaded. Perhaps it might be possible to inject the file into context via a comment, I've never tried that though and I doubt every assistant will act in a consistent way. The comment method is probably the best bet IMO.

Forgive me because this is a bit of a tangential rant on the second issue, but Gemini Pro 3 was absolutely heinous about this so I cancelled my sub. I'm completely puzzled what it's supposed to be good for.

To your third issue, you should maybe consider building a dataset from those interactions... you might be able to train a LoRA on them and use it as a first pass before you lift a finger to scroll through a PR.

I think a really big issue is that there is a lack of consistency in the use of AI for SWE. There are a lot of models and poorly designed agents/assistants with really unforgivable performance and people just blindly using them without caring about the outputs amounts to something that is kind of Denial-of-Service-y and I keep seeing this issue be raised over and over again.

At the risk of sounding elitist, the world might be a better place for project maintainers when the free money stops rolling into the frontier labs to offer anyone and everyone free use of the models...never give a baby powertools and so on.

Which Gemini model did you use? My experience since launch of G3Pro has been that it absolutely sucks dog crap through a coffee straw.

Rust.

Aren't they one of the worst physics channels apart from just outright fraudulent/fringe grifters like ElectricUniverse? Seems like every other week or so I see someone detail patiently why they have incorrectly explained something. I think the "[particles, like photons] take all possible paths" fiasco might be the latest one I can recall.

Typical quality of The Guardian unfortunately. Don't read their energy reporting if you're at all literate about any of those topics. Any time they do a story on fusion I just about have an embolism.