Hacker News: alexeldeib

New comment by alexeldeib in "Nvidia greenboost: transparently extend GPU VRAM using system RAM/NVMe"

alexeldeib — Thu, 19 Mar 2026 03:08:44 +0000

KV cache is, well, a cache that can fill up and trigger eviction. You require enough space to execute at least 1 fwd pass of 1 request at your context length. KV cache hits reduce TTFT by avoiding prefill. You don’t get to skip decode.

MoE is kinda related in terms of lower usage requirements vs a dense model of same total param size, but I think your mental model is a bit off.

New comment by alexeldeib in "Ask HN: Senior people, how did your career evolve?"

alexeldeib — Tue, 11 Nov 2025 17:55:18 +0000

“It depends”: what’s your prior experience, what kind of roles interest you, how big is the gap between what you have + a little ML knowledge/side projects?

I’d argue there’s a big need for people with solid fundamental CS, sysadmin, infra skills who can bridge the gap into ML practitioner/researcher understanding. Applications or inference generally are probably easiest to break into, especially if you already have service knowledge. If you want to work on distributed training or kernel/model optimization, you probably need to prove your chops there.

Neoclouds, startups in the AI space, maybe hw vendors are probably good places to look.

New comment by alexeldeib in "Show HN: Katakate – Dozens of VMs per node for safe code exec"

alexeldeib — Tue, 21 Oct 2025 17:09:36 +0000

as someone in the space this ticks a lot of boxes: kubernetes-native, strong isolation, python sdk (ideal for ML scenarios). devmapper is a nice ootb approach.

Glancing at the readme, is your business model technical support? Or what's your plan with this?

Anything interesting to share around startup time for large artifacts, scaling, passing through persistent storage (or GPUs) to these sandboxes?

Curious what things like 'Multi-node cluster capabilities for distributed workloads' mean exactly? inter-VM networking?

New comment by alexeldeib in "Apple M5 chip"

alexeldeib — Wed, 15 Oct 2025 18:45:19 +0000

Fun one: https://incident.io/blog/festive-macbooks

New comment by alexeldeib in "Ask HN: Abandoned/dead projects you think died before their time and why?"

alexeldeib — Sun, 12 Oct 2025 04:43:50 +0000

Oh nice! I just had an excuse to try mojo via max inference, it was pretty impressive. Basically on par with vllm for some small benchmarks, bit of variance in ttft and tpot. Very cool!

New comment by alexeldeib in "Ask HN: Abandoned/dead projects you think died before their time and why?"

alexeldeib — Sun, 12 Oct 2025 00:48:22 +0000

ouch, last “recent update” in 2023. Any idea what happened?

New comment by alexeldeib in "AMD signs AI chip-supply deal with OpenAI, gives it option to take a 10% stake"

alexeldeib — Mon, 06 Oct 2025 13:36:12 +0000

Larger memory, weaker comms. You can optimize for this by doing things like increasing batch size/data parallelism vs sharding schemes with more comms.

At scale training won’t be able to avoid comms entirely, while many models can fit in a single MI300 for serving.

New comment by alexeldeib in "PlanetScale for Postgres is now GA"

alexeldeib — Mon, 22 Sep 2025 16:57:30 +0000

can't speak to GCP specifically but usually the issue is they are host-attached and can't be migrated, so need to be wiped on VM termination or migration -- that's when you lose data.

Reboots typically don't otherwise do anything special unless they also trigger a host migration. GCP live migration has some mention of support though

GCP mentions data persists across reboots here https://cloud.google.com/compute/docs/disks/local-ssd#data_p...

note that stop/terminate via cloud APIs usually releases host capacity for other customers and would trigger data wipe, a guest initiated reboot typically will not.

New comment by alexeldeib in "About Containers and VMs"

alexeldeib — Fri, 29 Aug 2025 03:43:36 +0000

yeah, the system/application distinction feels somewhat superficial. The “multiple user space” inside a container thing sounds interesting (not sure what that means exactly), but maybe more similar to a Kubernetes pod, except maybe instead of different rootfs there’s another isolation mechanism?

New comment by alexeldeib in "BusyBeaver(6) Is Quite Large"

alexeldeib — Sat, 28 Jun 2025 19:12:57 +0000

The "first" link (after the home button) on bbchallenge is the header bar link to https://bbchallenge.org/story which cites Aaronson in the first sentence (double first!). I would not describe it like OP for someone trying to find the actual link ;)

"One Collatz Coincidence", the 2nd story on the blog, also mentions Aaronson

New comment by alexeldeib in "Matt Godbolt sold me on Rust by showing me C++"

alexeldeib — Tue, 06 May 2025 18:51:08 +0000

that's kind of a thing with https://docs.rs/no-panic/latest/no_panic/ or no std and custom panic handlers.

not sure what the latest is in the space, if I recall there are some subtleties

New comment by alexeldeib in "How to speed up US passenger rail, without bullet trains"

alexeldeib — Sun, 13 Apr 2025 23:41:23 +0000

Brightline https://www.gobrightline.com/

Never had the chance to use it, but one of the more exciting US rail developments I’ve seen recently.

New comment by alexeldeib in "Tmux – The Essentials (2019)"

alexeldeib — Wed, 05 Mar 2025 05:14:08 +0000

you seen kubie? `kubie ctx` is great for avoiding the first issue

https://github.com/sbstp/kubie

New comment by alexeldeib in "Render raises $80M in Series C financing"

alexeldeib — Sun, 26 Jan 2025 21:56:10 +0000

Supabase would be a good pick. Vercel and Cloudflare both do SQL DBs now too, curious how they are. Neon seemed interesting, haven’t heard much about them in a while.

None of those integrated of course, but easier than going big cloud or self hosted

New comment by alexeldeib in "CRIU, a project to implement checkpoint/restore functionality for Linux"

alexeldeib — Sat, 22 Jun 2024 07:01:30 +0000

great talk! I’m curious about an approach like this combined with CUDA checkpoint for GPU workloads https://github.com/NVIDIA/cuda-checkpoint

New comment by alexeldeib in "What the damaged Svalbard cable looked like"

alexeldeib — Mon, 27 May 2024 16:45:56 +0000

What was your takeaway? Any added insights/reading?

New comment by alexeldeib in "Infini-Gram: Scaling unbounded n-gram language models to a trillion tokens"

alexeldeib — Sun, 05 May 2024 23:58:32 +0000

Isn’t there an argument we’re simply better at brain statistics and modeling than current AI? Forget architectural limitations. What is the nature of the extrapolation? How do individuals balance their experiences and determine likely outcomes?

New comment by alexeldeib in "Linux fu: getting started with systemd"

alexeldeib — Mon, 15 Apr 2024 00:45:57 +0000

have you seen systemd-analyze?

New comment by alexeldeib in "Omg.lol: An Oasis on the Internet"

alexeldeib — Sun, 10 Dec 2023 21:24:07 +0000

This is the classic Dropbox criticism, no?

Moreover, the pleasure has nothing to do with self hosting or not, it’s just a pleasant and whimsical UX while being technically solid.

New comment by alexeldeib in "The weirdest bug I've seen yet"

alexeldeib — Fri, 01 Dec 2023 02:15:09 +0000

They allegedly tried chromium without luck.