Path: ...!eternal-september.org!feeder3.eternal-september.org!news.eternal-september.org!eternal-september.org!.POSTED!not-for-mail From: Paul Newsgroups: alt.comp.os.windows-11,comp.os.linux.advocacy Subject: =?UTF-8?Q?Re:_Windows-on-ARM_Laptop_Is_A_=e2=80=9cFrequently-Return?= =?UTF-8?Q?ed_Item=e2=80=9d_On_Amazon?= Date: Mon, 24 Mar 2025 11:15:30 -0400 Organization: A noiseless patient Spider Lines: 32 Message-ID: References: MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 7bit Injection-Date: Mon, 24 Mar 2025 16:15:37 +0100 (CET) Injection-Info: dont-email.me; posting-host="f8f384255b80efb1876a8c5422bc608b"; logging-data="1241644"; mail-complaints-to="abuse@eternal-september.org"; posting-account="U2FsdGVkX1/rasjdP/KILUf/BMAURGgMWBUrRPtCURE=" User-Agent: Ratcatcher/2.0.0.25 (Windows/20130802) Cancel-Lock: sha1:S3n02EgkxjBIasCkmPBIkoBpIog= Content-Language: en-US In-Reply-To: Bytes: 2458 On Mon, 3/24/2025 2:21 AM, rbowman wrote: > On Mon, 24 Mar 2025 00:36:17 -0000 (UTC), Chris wrote: > >> Paul wrote: >>> On Sun, 3/23/2025 7:17 AM, Joel wrote: >>>> >>>> It's clear why Microsoft would use x86 emulation with ARM, countless >>>> reasons, but who cares about their Copilot bullshit, put Linux for ARM >>>> on that mother fucker. >>> >>> Some day, you'll be able to run an AI locally. >> >> You can. Have a look at Ollama. Totally local and open source. Works >> well too! > > Training and inference are two different things. Other than toy datasets I > doubt much training will happen locally. Realistically, I think it's going to be quite a while, if ever, before we can put together a decent box for inference. In this gold rush, all the excess profit is in "mules and shovels". A mule I was looking at today, the price is $8500 or so. This kind of pricing, is hardly encouraging. It would be cheaper, to build a wooden box, and put a midget inside the box, and have it answer questions. Can anyone give me a price on a PhD class midget ? Paul