PunchTornado

I am the opposite. Find GPT 5.2 much worse. Sticking only with gemini and claude.

I don't think he meant like syntax errors, but thinking errors. I get these a lot with CC. Especially for example with CSS. So much useless code it produces, it blows my mind. Once I deleted 50 lines of code and manually added 4 which was enough to fix the error.

claude and gemini

Surprised that people still use chatgpt

What are you smoking? Gemini and Claude beat chatgpt at every metric.

Exactly. I don't understand how an article like this ignores the best models out there.

I doubt that gemini 3 cannot do it.

the thing is, I tried it and it took 10 seconds to import all settings from cursor. the moat for vscode clones is really small. i imagine people will jump a lot from clone to clone, like from model to model now.

sorry, but I don't understand you post. those links don't work.

You are the one who corrects america with usa?

it rivals a model that is obsolete? who is using openai deepresearch when there are so many better models out there?

almost no innovation? from transformers to alphago to the quantum stuff.

the reranker is a cross encoder that sees the docs and the query at the same time. What you normally do is you generating embeddings ahead of time, independent of the prompt used, calculate cosine similarity with the prompt, select the top-k best chunks that match the prompt and only then use a reranker to sort them.

embeddings are a lossy compression, so if you feed the chunks with the prompt at the same time, the results are better. But you can't do this for your whole db, that's why the filtering with cosine similarity at the beginning.

I don't understand how does this help if, yes, communicating, is what we are doing most of the time.

try being banned by msft. I am still banned for 6 years without doing anything wrong. still lost access to all of my accounts.

Downvoted because you didn’t mention the prompt and the issue.

I hope you enjoy the world you helped create

They are not equally bad, but they are both bad. Cancel culture was a very bad idea.

Wait. You moved from slack to teams? Why? We are in the process of moving to slack from teams and I can’t phantom something worse than teams.

Green energy like nuclear

The author is Jordan Lasker (also known by internet handle Crémieux). Much of Lasker's work and commentary focuses on race and IQ, and he has promoted eugenics. On X and Substack, Lasker is known for compiling charts on what he calls the "Black-White IQ gap"

why do you think they have to rename it because some company's IPO

anybody can help me with some tutorials on how to use this for mechanistic interpretability?

Funny that hinton is not mentioned. Like how childish can the author be?

because behind DDG is bing, microsoft, one of the evilest companies on earth.

wonder why euro capitals are heating up more than others on average? especially the nordic capitals. they are greener too.

I don't think comparisons are useful here. We are dealing with an evil corporation which we all know and it has been proven many times that it broke the law and every time gets away with it. who are you protecting?

here's another one: fb shouldn't use every piece of data they can collect.

> The app people were sending user data to meta with no restrictions on its use

And then meta accessed it. So unless you put restrictions on data, meta is going to access it. Don't you think it should be the other way around? Meta to ask for permission? Then we wouldn't have this sort of thing.

maybe with AI and things like guided learning from gemini we all can get a 1-1 instructor.