News for hackers. Stuff that matters.
Re:GLM-5.1: Towards Long-Horizon Tasks by zozbot234 on Tuesday April 07, 2026 @09:50PM (#47683835)
Coding assistants are currently quite hard to run locally with anything like SOTA abilities. Support in the most popular local inference frameworks is still extremely half-baked (e.g. no seamless offload for larger-than-RAM models; no support for tensor-parallel inference across multiple GPUs, or multiple interconnected machines) and until that improves reliably it's hard to propose spending money on uber-expensive hardware one might be unable to use effectively.
Re:GLM-5.1: Towards Long-Horizon Tasks by dash2 on Tuesday April 07, 2026 @10:08PM (#47684024)
This is an argument against the grandparent's points (1) and (2), not their point (3).
Re:GLM-5.1: Towards Long-Horizon Tasks by zozbot234 on Tuesday April 07, 2026 @10:13PM (#47684063)
It's one clear argument for the (so get to work!) part.
Re:GLM-5.1: Towards Long-Horizon Tasks by sunir on Tuesday April 07, 2026 @10:42PM (#47684335)
Computers get better and cheaper. That’s not a forever problem.
Re:GLM-5.1: Towards Long-Horizon Tasks by doctorwho42 on Wednesday April 08, 2026 @12:32AM (#47685283)
Source?

GPU and RAM prices have definitely not made consumer PC's cheaper than they were before bitcoin blew up or before AI blew up.

Maybe you could make an argument that they are more cost efficient for the price point... But that's not the same as cheaper when every application or program is poorly optimized. For example why would a browser take up more than a GB or two of RAM?

And I'd postulate that R&D to develop localized AI is another example, the big players seem hellbent that there needs to be a most and it's data centers... The absolute opposite of optimization

Re:GLM-5.1: Towards Long-Horizon Tasks by sunir on Wednesday April 08, 2026 @12:58PM (#47692958)
Moore's Law.

We've had RAM shocks before. We nerds can't control the Wall Street or Virginians who like to break the world every so often for the lulz. However, a wobble on the curve doesn't change the curve's destination.

Re:GLM-5.1: Towards Long-Horizon Tasks by 0x457 on Wednesday April 08, 2026 @01:10PM (#47693138)
You have to look a bit more long term? 256Mb of what today is slow af RAM used to be pretty pricey. Price will pullback.