Which is why test generation has to be carefully guided as well, and this is something at which I've incidentally been fast. Ultimately it's a constant battle between LLM handholding and doing things yourself.
I do not have the burnout but I certainly operate similarly to the author. I continue to be unable to establish a workflow where allowing the LLM to generate code that I review is faster than writing the code myself. Literally the only two ways out of this dilemma is to blindly trust what was generated or to generate an uncharacteristically exhaustive suite of unit tests to validate every possible scenario. I just write the business logic myself and have the LLM do a lot of the rest. Boilerplate falls into the latter as well.
> After this minor hiccup, the experience with MSI was actually quite pleasant. They prepared a patch for the vulnerability within two days of me reporting it and told me which MSI Center release it was to be bundled with, and when they planned to release the new version.
Was NOT expecting a happy ending.
I don't know if the part of MSI Center with the pipe vulnerability is automatically installed on desktops but this is the terribly written software that you need to turn off all the obnoxious lights on your MB and DRAM.
I'm old-man-yelling-at-the-clouds here. Everyone just uses Cloudflare, which is not a bad thing by itself. But do they _have_ to? Is managing your own edge really that terrifying?
> They've essentially gotten roped into maintaining a huge chunk of internet infrastructure, for free. If they ever shut it down the whole world would end up rioting because it's so widely used.
Not even remotely true. They regularly shut down products and services with impunity. If Gmail cost more than the data they directly or indirectly mine and sell from their users, Gmail wouldn't exist either.
General purpose, mostly internet research in the form of slow-crawling. (Emphasis on slow - I've ultimately landed on Scrapling's API for seamless content rendering, and I use image support so as not to exclude informative images or weirdly rendered text.)
For coding I don't need image support so I stuff the entire GPU with text-only mode. I don't have a workflow where I send LLMs off to generate thousands of lines of code but what little coding I did I did with Qwen3.6 and it was spectacular, as you likely suggest.
I'm using llama.cpp with Gemma and tool calling is mission critical. It's perfectly fine on my end.
There are definitely differences in the eagerness to tool-call that you'll need to manage. And for all local models I've ever used, I've had to micromanage the tools provided by servers to eliminate any possibility that they reach for something wonky or confusing.
A few days ago I switched again from Qwen3.6 to Gemma 4 - for personal use I've experienced better average performance with the 26B version of the latter than the 27B of the former.
For someone who's been running local models for a long while, these are very very exciting times.
The paper isn't concerned specifically with survival. It's saying that you cannot achieve "abstraction" (presumably the structure that underlies critical thinking, creativity, etc.) through shear mimicry.
Again, just echoing the paper here. I don't know that I'm doing it justice.
Also, embedded servers are now much much much more popular. Stuff an HTTP server directly into your application and do whatever you gotta do without gateways.