Viewing profile — Frannky

Yes, it also opens up a faster recurring revenue model for hardware companies, faster model obsolescence than how often you change a computer, a server, or a GPU card. I hope they …

I just didn't want to spend time configuring an harness

It's usually one of two things. First, I say I want to build this system solving this problem with these requirements, what do you suggest? It suggests X, then I say, "Hmm, why not…

I'm using oh my pi with Kimi K3 as the planner and DeepSeek Flash 0731 as the implementer, with OpenRouter as the provider. Any suggestions for a better configuration? I mostly nee…

Fortunately one can leave and live elsewhere...

Working there feels like a trap. Why work there when you can start a company? You get to choose the problem you care about most, the people you work with, and your own pace—and if …

I think they're doing something wrong. I have access to better models, but I just use 4.6 and 4.8. Fable and Opus 5 burn tokens too fast for me. I also switched to a cheaper plan t…

People want to get from A to B. Someone makes a rule to stop them. So they go from A to C to B instead — or settle for something close enough to B. The rule-makers don't stop anyon…

I was hesitant to try the free trial exactly because I haven't found any info about what data was required to share...

It's pretty easy to vibecode a system that automatically gets news, papers, and books, has Speechify-like readers, and steps to filter out propaganda and make difficult papers easy…

Awesome. User wins when competition increases. I hope they cooked. Previous models did not make any sense in any of my flows. There were better options for each problem.

Why is this answer down voted? Isn't a reasonable question to ask? Are the lawmakers proposing laws the majority of the people want?

I think that even if you will never code, it will teach you how to think—especially if you also learn math, stats, and other engineering courses. You start to see patterns that let…

Zed with multiple conversations open. Each conversation is a problem to solve. The agent is a way to read code and logs rapidly to find what's causing the problem. The feedback loo…

I can use it but I'm not. I used it before the ban, it's better but the speed at which tokens are burned is not justified. And this makes me happy because it means I am ok with cur…

Hmm, I have access to A100s and a GB10, but if I use the models hosted there to code, I waste a lot of time waiting for answers and correcting errors. The amount of work I get done…

This is my opinion too. Even if you buy hardware like a cluster of 8xGB10s or 4 A100s, they'll still be slow and a little dumber than what you're used to. We need to wait a little …

There is a push from multiple directions at the same time: - new AI desktops with GB10s. They are relatively cheap and you can cluster them and load 1TB of VRAM - Nvidia, amd, inte…

So they will be able to know how each person thinks, block capabilities they want to block, boycott what they want to boycott, and influence perspective on reality. Fortunately the…

This is so cool and looks so fun. I want to play with robots. I just play with software :( I wanted to build something making bows automatically and damn, pretty complex and expens…

I read some cool posts of people trying MiniMax 3 on 4x GB10. I wonder if we are almost there that with 10k we can have Opus 4.6 level at home. I feel tweaking the harnesses and a …

Same

Someone knows how to get the subscription money back?

The model is very good. I was using 4.6, avoided 4.7 and 4.8, but this one is different. It follows my claude.md. I don't have to keep reminding it of things. I won't pay 10x via A…

The model is better than 4.6. I don't like 4.7 and 4.8. The forced switch to token usage is not acceptable for me. I feel there's room to optimize harnesses and small models for du…