[nikolay]

I can't recall the scientist's name, but he said months ago that DeepSeek is best for Physics (maybe it was on The Diary of a CEO podcast). So I had a long chat about the Simulation Hypothesis, and I was really surprised by how good, deep, and straight to the point it was.

What's brutal is that Google, which started this AI revolution, has literally the worst coding model! I tried 3.5 Flash last week (the stupid still pays for Ultra due to Google One's storage), and before I gave up on 3.1 Pro, I saw a coding agent hallucinate for the first time in months, even at the highest effort level!

Meanwhile, I've tried DeepSeek with the DeepSeek TUI (now CodeWhale), and it didn't do any worse than Codex or Claude Code. I know there are benchmarks and all, some of them gamed, I'm sure, but in real-world experience, DeepSeek is absolutely amazing for its price! If you have software engineering skills and are not an accidental vibe-coder, honestly, try it out and stop burning money. I'm sure you will get even better results with OpenCode! Human Intelligence + Artificial Intelligence beats the highest AI model without the guidance of a HI!

Meanwhile, I burned through my entire budget on the $200 Max for Fable 5, for a modest-amount project in Python using its own CLI coding agent. What a waste!

I keep hearing "always use the bestest model" - no, always use the most practical one for the job! I got so many issues with Fable on a very small project that even Copilot found that it's simply not worth it for 99% of your tasks!

[databrecht]

It's just insane how different experiences are. I've let it spin for 2 days on difficult tasks for my job, it found very complex esoteric race condition bugs which were genuinenly the type of "will take you 5 days to figer out what went wrong".

And on my personal account I was developing my own ORM in one session, on the other let it spin for 5h on "implement civilization II from scratch". It got quite far and everything it did genuinenly worked well, until they disabled Fable. The strange thing is that I was surprised by how little usage that actually costed, I didn't even hit the daily limit. Was expecting to be cut off directly with my subscription based on what people said yet it kept going and usage showed I had plently left.

How come, we all have such different burn rates or even results?

[ThePhysicist]

Yeah Fable 5 is good but feels incremental and overhyped, also burned through my entire Cursor allowance in my Ultra plan in a single day. Ridiculous. They just want to create FOMO and appear mysterious so companies and users will feel so special for being allowed to use this model and pony up more money. After all they have to grow a few order of magnitude to pump their IPO valuation as much as possible, so I think this is just a strategy to justify their increased token pricing which starts to become absolutely insane. 10-20k per month per developer, do companies really think that's a good way to spend their IT budget? I assume 99 % of software shops wrtite run-of-the-mill web/mobile/desktop apps or some legacy backend APIs and CRUD code, you don't need a superintelligence to crank that stuff out. It sounds so ridiculous to have a model that supposedly can design biological weapons and then 99 % of users vibe code spaghetti Javascript with it. But the spice must flow!

[mark_l_watson]

Thanks for your comment, I especially like “If you have software engineering skills and are not an accidental vibe-coder, honestly, try it out and stop burning money.”

I thought that using Opus with the Gemini Ultra subscription was in many ways awesome, but I simply feel happier using DeepSeek v4 flash with OpenCode (so fast!) of v4 pro when required.

[HSO]

steve hsu?

[nikolay]

> steve hsu?

Actually, just searched my history, and it was Alexander Unzicker [0], actually.

[0]: https://www.youtube.com/watch?v=JuLjsFMzZrE