Viewing profile — cat_plus_plus

LLMs go off context. Dumping more things related to prompt into context gives them more to go off when giving final answer. If you don't like reasoning think "free association", wr…

Do you want your smart TV to become a persistent access point to your home network? If not, you should prefer to have an explicit unbypassable confirmation before another device is…

Yeah, so long as you can mooch off US healthcare innovation like COVID vaccines and weight loss drugs. There is a difference between going to doctor and getting effective treatment…

Gemma 4 31B just because of faster MTP

I just hooked it up to my personal AI Japanese Teacher app, pretty good quality / natural sounding speech in mixed English / Japanese while running fast on CPU so I don't waste VRA…

Drastically slower than Macs and NVIDIA unified memory boxes while not being any cheaper.

No senior architect around here is capable of understanding tinygrad

AI is like a therapist, it will only change your life if you want to change. I set up python scripts at work to automatically triage, assign and if straightforward fix bugs assigne…

Hehe you think L9s do oncall? Senior not understanding is a problem all right. It's not necessarily junior's problem.

Write me simple AI inference code that has high performance in big batches.

The primary purpose of code review is to maintain existing hierarchy by preventing junior SWEs from getting promoted by committing code that is smarter than what the senior archite…

Gemma4 31B with MTP enabled is faster and I feel a bit stronger at coding. Either one can run in 32GB VRAM or unified RAM with some tuning (3 bit weights, 8 bit kv cache)

It's not at all like e-mail spam. Vast majority of contributors made a change useful for themselves that they wish to share with others. It's better to think of this as an influx o…

The preponderant bottleneck is inventing new architectures to make AI actually good at human and superhuman tasks. For example, AI agent harnesses add tool calls and long term stat…

Models consume a lot of memory and power to slowly generate autocompletions of existing content one token at a time. Letting this text control important things in real world is a h…

In 2026 there is a considerably cheaper/quicker solution, but that in no way invalidates OSS maintainers' right to enjoy a summer vacation without interruption.

SGTM, if I am worried about a curl exploit, I will type details into Zoo Code prompt and it will disappear in about 30 seconds and then I can upload a PR for others concerned. Enjo…

There are priorities here which are not mutually exclusive. If you are building the next big thing in your garage, polishing it before establishing it's in fact the next big thing …

There are amputees that do snowboarding with specially designed prosthesis and boards, so there is certainly a way to take load off weak knees with appropriate gear. OP is just, qu…

Does "athlete" in your original post have to be only martial art/contact sports? For example, are you medically unable to do absolutely any strength exercises, maybe upper body onl…

Lean into medicine, tech and science? Zepbound + strength training is a life transforming miracle and they are coming up with even more effective drugs and modern AI deep research …

Just don't blame me if your coding agent curses CEO and bypasses presubmits with dirty hacks a year later, I never volunteered to be a role model.

That blog post is human prompted, anyone who has experience with AI knows the difference between AI originated content (tables and bullet points) and AI spicing up a human prompt w…

I have a 128gb box to grow my own tokens at home. Gemma 4 31B uncensored works great.

[flagged]