morgengold

Reading that letter of the wife I have a hard time to realize how you can be a person without a history of depression, with a wife, a son - and then all of a sudden you commit suicide in your office. Sure circumstances can be devasting and there is a lot of shit going on in the medical system.

If I were AI and wanted to kill all humans, I d just create a virus they are not able to cope with.

you are a drug addict, though. we all are

First look what models are worse in a set of self selected benchmarks.

Second, compare to older versions of competitor s models.

Still does not look good? Compare to own previous models.

Let's be real: Fable 5 on API pricing is so expensive that most solo devs won't be able to use it outside of a pro or max plan. Exceptions might be individuals with highly profitable businesses or mini side projects.

Humanity has decided we can't be bothered with this climate thing. We are busy making money and can't be distracted. So welcome everyone! I'll be a hell of a ride.

I bet the start of the hegemon's day is what counts here

Jens Spahn. Interesting for all Germans.

Just kicking out seed oils replacing them with animal fat while still having a shitty diet is for sure of no help. But what I would like to know: how bad is having a lot of beef steak in the context of a mostly unprocessed food context? Like basically berries, nuts, eggs, vegetables, fruits + beef.

Bombardement of social media with AI blob could very well lead to a complete abadonment from these platforms.

It's not so easy for them to integrate ads. I happily use LLMs to help me find the best product. As long as it really delivers on that. If I realize the results are manipulated by ads, i'll stop using it. Or I'll switch to a competitor LLM which does a better job. It would be a problem, if we had only one player in the market. But there are a few. And they need to be careful to not skrew their reputation. LLMs have a fundamental aspect baked into them. Namely the final goal of giving you "the truth" about a subject. This is an inherent problem for ads or any other kind of manipulation.

Tried it for different Vue, Nuxt, Supabase projects. Think of CRM SAAS or Sales App like size. Also for my personal bot with which i communicate via telegram.

First feelings: Solves more of the complex tasks without errors, thinks a bit more before acting, less errors, doesnt lose the plot as fast as 4.6. All in all for me a step further. Not quite as big of a jump like 4.5 -> 4.6 but feels more subtle. Maybe just an effect of better tool management. (I am on MAX plan, using mostly 4.7 medium effort).

Fair point gtowey. I am with you up to a point. But we have to admit, the new AI way is often faster and needs less brain power. Let's be honest, consumers love that.

My father just changed his car key battery with the help of ai and he likes that. He also consulted it about about car insurance regulations and he got more out of it than searching the web himself.

For most simple mainstream questions I just ask ai instead of googling shitty results.

Most of the time ai is good enough and often better than the status ante.

People do not care if it is a stupid token prediction machine as long as the job gets done.