singingtoday

I should add, this was for CS. I don't know about the other programs.

Only the dumb ones are obvious. In my school (SFU/BC) most of the students in almost all of my classes cheated. VERY FEW got caught.

I heard instructors say all too often that it was obvious when somebody was cheating, but somehow they missed the guy paying his cousin to write the final.

Gemini still gives up too easily

You can get near this point with scaffolding. Keep in mind, LLMs are next word predictors at their root. More abstractly, they capture and replay likely human intelligence by way of written language. Tokens.

With that concept in mind, it's clear how they can be made to "give up".

Yeah. I have 3 max20 plans.

Interesting. I've yet to find a model I consider sufficiently intelligent.

Fable is nice, but still requires a lot of guidance for large scope tasks.

We still run GPT 4.1 for some of our use cases. We want to replace it but are having trouble finding models that are as fast with similar or better intelligence.

Incipient better? Or are we in progress?

I've met a few people like that, through what appears to be pure determination, they force success to give up what it has. Very impressive.

98se, 2000, 7, 10

XP wasn't bad, it was basically 2000 with extra stuff.

I still never gave it a try. I assume it works in a VM? Maybe it's time to try Holy C.

What an odd thing to say

I have one of my projects on DeepSeek and it blows my mind how I can use tens of millions of tokens for pennies.

I don't find it suitable for everything, but there's some tasks it crushes for what feels like almost free.

That was my experience, and in the 90s as well.

How did we exclude ourselves? I went to the store, I got cassettes, discussed it with the people I came with.

We do the exact same thing now except use a phone or tablet.

That's awesome! How was shipping it? How was the product market fit?

Not yet anyways. Not all of them.

Ah, a true scholar!

Fantastic, thank you for the explanation!

I ported my company over to k8s to solve a concurrency and scaling issues.

What 15 concepts? You're making me worry that I missed something. It was straight forward: pods, nodes, hw type, lifecycle, deployment. They run almost the same docker as the old ec2s used.

What did I miss? Is there something important I need to read?

I mean, you can mostly. That's apparent all over. Money buys freedom.

This is very interesting to me because I find sol to be inferior at code generation, but superior at conversation and code review.

The kids and adults. That's what my mom calls it.

I'm more excited for 3.5 pro. Gemini has fallen behind in some areas, but is still one of the best multimodal models.

Has anybody found any models better at image or audio analysis?

Is the ai hate a global or western thing? A friend of mine in Japan says people don't hate it there. Maybe she's just in a bubble?

I don't buy that because China has very high home ownership rates.

So it can be done. Even today.

That's phenomenal. This would bring us so much fascinating information.

Depends how you use the tokens. It's not 10k, but I have an agent do an investigation automatically when I get paged, so by the time I get to the computer I have a nice summary. But that's costing me like $5/mo at most.

But you could use tons of autonomous agents for all kinds of things. Probably shouldn't, but you can.

I have 3 max20 subscriptions and usually max at least two of them out.

I'm doing lots.

I'm building a social media site that nobody will ever use. I'm printing an ancient game to Linux and expanding the features (such as adding hw acceleration where it isn't needed). I'm troubleshooting crash logs for an Xbox game that has maybe 50 active players. Im building a distributed customer service system that provides LLMs, RAG, tool calls for lots of integrations (Gmail, calendar, sheets) (this one actually has several paying users). I'm building games, and releasing them on the Google marketplace (play store?)

But what used the most tokens was a kind of agent swarm I experimented with to implement a complex desktop application for very specific data manipulation. That.. half worked.. but it's buggy.

I made several internal tools at my company that are actually getting used by pretty much everybody. That's my most successful work I think. Oh, and I created a backup deployment in Azure for my companies product because .. we had the azure credits, so why not?

It got a lot of clicks here. Clicks equal money.