florianherrengt

Works with GeForce RTX 20 series and newer, RTX PRO (Turing and newer), DGX Spark and Apple M4 or newer.

It does not pool memory or split one inference request across machines. Adding machines increases parallel throughput but won't let you run bigger models.

I’m a big fan of simple things but I always go back to using a library or framework because it’s much easier to create a good, consistent UX

This paper puts words to something I’ve noticed repeatedly with LLMs, particularly Qwen3.6. When I read its reasoning, it appears to recognise the mistake and then carry on as if it hadn’t noticed it at all.

> models often determine their answers based on implicit biases tied to question templates, then construct reasoning chains to justify their predetermined conclusions > its reasoning was correct right until the final step (Yes/No answer)

> While a human may say “aha” to indicate exactly a sudden internal state change, this interpretation is unwarranted for models which do not have any such internal state, and which on the next forward pass will only differ from the pre-aha pass by the inclusion of that single token in their context. Interpreting the “aha” moment as meaningful exemplifies the long-neglected assumption about long CoT models – the false idea that derivational traces are semantically meaningful, either in resemblance to algorithm traces or to human reasoning.

This paper addresses something that has always bothered me about LLMs. You read their reasoning, see something like “Wait, that’s wrong” and then watch them make the exact mistake they just identified.

> PostgreSQL Replacing Your Microservice

I've done that before and the code was a mess. It works at the beginning but APIs do much more than piping data from the database. When you start dealing with ACL, external calls, code reuse, etc. It's just nice to have all the tools available to you from something like Python or Go.

I have a Pinephone Pro. It's nowhere near usable as a daily driver.

I'm surprised it took them that long. I always found it odd that they would support Google phones only.

It means the company is measuring the wrong thing.

I would much rather have someone on my team who ships less but whose work I can trust than someone much faster whose changes leave me wondering what problems we’re going to discover later.

And when production breaks (and it will), I need the person who made the change to actually understand it well enough to help fix it, instead of showing up with no idea what is going on.

You can obviously be an asshole about how you do it but I don’t think pushing back makes someone toxic.

You need to be flexible and compromise when the business trade-off makes sense. But you also need a backbone. If you think something is going to cause real problems, bringing it up is part of the job.

Then I’m not sure what you mean by calling them a bottleneck.

If the limiting factor is the rate at which experienced engineers can understand and validate changes, you have three options: generate less, find a genuinely better way to validate or accept lower quality.

Corrupted or lost customer data, security vulnerabilities, incorrect financial transactions, regulatory breaches, production outages, irreversible migrations, important product change effectively impossible without a full rewrite. Every feature takes longer, incidents take longer to resolve. Engineers spend their time fighting the codebase instead of building things, burn out and quit. I could go on forever.