Just wanted to say a huge thankyou for being so patient in the forum; it's quite annoying that the comment section is a more a function of the title + personal opinions than a function of the blog content.
I love using obsidian, and thanks so much for all the work that you and the team have put in :)
I would suspect that for self hosted LLMs, quality >>> performance, so the newer releases will always expand to fill capacity of available hardware even when efficiency is improved.
The blog mentions checking each agent action (say the agent was planning to send a malicious http request) against the user prompt for coherence; the attack vector exists but it should make the trivial versions of instruction injection harder
I assume the high volume of search traffic forces Google to use a low quality model for AI overviews. Frontier Google models (e.g. Gemini 2.5 pro) are on-par, if not 'better', than leading models from other companies.
Helium is released from alpha decay (hence unlikely to run out in the near future) and is also obtainable from natural gas. That being said it is still non-renewable (in the sense that once the radioactive decays happen no more helium is released) and has quite volatile prices for some reason.