Not a Lex Friedman fan, but I highly recommend the recent podcast he did with two leading engineers (and founder) from the ffmpeg project: https://www.youtube.com/watch?v=nepKKz-MzFM
In a world full of endless AI slop, it is refreshing to see that there are still folks out there hand-rolling assembler code to squeeze out another 5% efficiency.
It's frustrating that vibecoding has gotten so pervasive that it's impossible to tell when someone uses LLMs as an awareness-increaser and research assistant, rather than an unreviewable code vomiter. I still appreciate the design of code done via the former strategy, whereas I simply will not rely on the latter.
Can you elaborate on DeepSeek (deepseek-v4-flash, i assume?). What does your typical usage pattern look like and what is your weekly/monthly spend?
I gave it a try for a few days (pi + openrouter + deepseek-v4-flash via deepinfra) and ended up paying ~$18 for rather light usage. Yes it's still cheap, yes it's fast, but i feel i would still get a better deal with a Claude subscription plan.
I agree with parent. OpenRouter might be cheaper list-price, but i have been using 10$ on DS platform since April/May, still have 2$ left. Using OpenRouter i depleted the same dollar-amount in a 1-2 weeks with same usage pattern. No idea why.
Not used it but from perusing forums, consensus is OpenRouter has terrible/broken caching for Deepseek wildly inflating token use. The cache metrics are visible so you can verify for yourself (apparently, it's what others have done).
I will refuse to read such messages or documents. At the very minimum, i want a human-written TLDR-style summary to ensure the sender has read their own slop.
>Europe due to its lack of European competitors, has no current similar protectionist incentives [...] The genie is out of the bottle in the West already.
I agree, but you are underestimating EU regulatory incompetence
Root agents.md should be human authored. Even if you copy and paste into it. That's your only lasting thread into having any intuition on the behavior that will result
Blocking known bot identifiers via robots.txt does nothing by the way. Too many labs are running sneaky crawlers that do not respect robots.txt. You will need to take extreme measures: blocking basically all datacenter IP ranges, VPN IPs, aggressive rate limiting, etc.
Blocking LLM crawlers has become the number one use case for our IP database customers at https://focsec.com/
Jup, if you are using any mainstream VPN provider (the ones shilled on every tech YouTube channel) or anything that results in a datacenter IP, it is trivial to discover and block.
Add to that that half of these companies are registered in obscure offshore locations where it is practically impossible to even find out who are the ultimate owners.
In a world full of endless AI slop, it is refreshing to see that there are still folks out there hand-rolling assembler code to squeeze out another 5% efficiency.
reply