You could still use an LLM to write and extend the tests, but running the tests would be deterministic and would use less resources.

I didn't want to say that they're not cheaper to run, artificial analysis also shows that they're cheaper. My main point was about it being important to also look at token efficiency, not only cost per token, to get the full picture.

For DS4 Pro there's a discount going on for the official API, which sometimes gets overlooked and mixed up in discussions. Simon uses the full price in the comparison, so that's not an issue here.

The other issue is that DS4 Pro and K2.6 often use way more reasoning tokens than the frontier models. In my testing there are certain pathological cases where a request can cost the same as with a frontier model because they use so much more tokens. To be fair I'm using DS and kimi via 3rd party providers, so they might have issues with their setups.

But if you look at the Artificial Analysis pages of the models you'll see that DSv4 Pro uses 190M tokens and K2.6 170M tokens for their intelligence benchmark, while GPT 5.5 (high) only used 45M.[0][1][2]

I recommend looking at the "Intelligence vs. Cost to Run Artificial Analysis Intelligence Index" ("Intelligence vs Cost" in the UI). The open source models are still cheaper to run, but not by as much as you'd think just looking at the token prices.

[0] https://artificialanalysis.ai/models/deepseek-v4-pro [1] https://artificialanalysis.ai/models/kimi-k2-6 [2] https://artificialanalysis.ai/models/gpt-5-5-high

Are you using LLMs for parts of the coding?

What's your work flow when approaching a new project like this?

[0] https://leadershiplighthouse.substack.com/p/i-went-all-in-on...

Comments URL: https://news.ycombinator.com/item?id=46186556

Points: 3

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=46086905

Points: 2

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=46013463

Points: 53

# Comments: 35

Comments URL: https://news.ycombinator.com/item?id=45834088

Points: 37

# Comments: 48

You might be interested to hear that Carolyn Cassadi, Neal Cassadys wife at the time, wrote a book about her life with Neal and Jack. Not only did their lifestyle not consider family, they where in a complicated love triangle that neither of them was prepared for. A real challenge for Kerouac with his catholic upbringing. She also writes about how Kerouac very intentionally left some of his short comings out of his books. As Bukowski reportedly said: "I'm the hero of my own shit." I guess Bukowski was more honest about his editorializing.

Either way, the book is called "Off the Road: Twenty Years with Cassady, Kerouac and Ginsberg" [0] and is well worth the read. It might disnechant the beat authors for some, but at the same time it humanizes them.

[0] https://en.wikipedia.org/wiki/Off_the_Road

Edit:

The interview with Alene Lee daughter is very moving. Reminds me of a story, maybe it's in On the Road?, how Kerouac meets a guy in a Jazz Club and he invites him over to his place to drink some more beer. They wake up his wife by being loud, but she doesn't complain and Kerouac goes on about how she's such a good wife. Lot's of moments in the books like that if you're looking for them.

It's very interesting for me to look back on how I didn't really register those passages when I was reading Kerouac in my teens, being swept away by the radical and breathless enthusiasm of his writing. I probably was a huge shit head back then myself.. :D

I think people that talk about GC'd languages being slow are usually not building Rails or Django apps in their day to day.

Is this the book you recommend people read to learn about "the gestalt"?

Are there any other resources/books/courses you can recommend?