Hacker News: Footprint0521

New comment by Footprint0521 in "How I changed teaching after AI managed to do all my homework assignments"

Footprint0521 — Sun, 27 Sep 2026 00:31:25 +0000

Dude, hop on the Gemini student plan and try Gemini Notebook and Gemini Live. Live is a personal TA, Notebook literally podcasts the readings and what you need to learn

New comment by Footprint0521 in "Show HN: Reladraw – A diagram language where you decide where to place things"

Footprint0521 — Sat, 26 Sep 2026 21:21:48 +0000

That’s what I have been using, but from glancing through this repository, it looks like the win here is that you can define where you want things and yet still have diagram as code

New comment by Footprint0521 in "Plunging test scores are a slow-moving catastrophe"

Footprint0521 — Sat, 26 Sep 2026 18:22:38 +0000

WALL·E

New comment by Footprint0521 in "Apple M6 Pro achieves the highest single-core CPU score in Geekbench 7"

Footprint0521 — Sat, 19 Sep 2026 11:35:41 +0000

The moment AAA gaming becomes possible on macOS, the floodgates open and windows is dead

New comment by Footprint0521 in "I tested 10 model/harness combinations on the same Three.js task"

Footprint0521 — Wed, 09 Sep 2026 02:34:16 +0000

Three.js with cannon.js is what you want, but the more you work with it, the more you realize how the difficult part is not so much the “game” or “engine” in that sentence but the word “web”… optimizing assets is a massive skill all in its own to be storage friendly and usable without the easy default of laggy and massive download size

New comment by Footprint0521 in "Why your local LLM feels dumber than it is"

Footprint0521 — Sun, 23 Aug 2026 00:37:23 +0000

Just curious, what is your ram and how many tokens per second do you get with that?

New comment by Footprint0521 in "DeepSeek peak/off-peak pricing update"

Footprint0521 — Fri, 14 Aug 2026 15:00:52 +0000

Yeah that sucks… unless it’s over the top export controls for DoD work that really doesn’t make sense

New comment by Footprint0521 in "GPT 5.6 Cyber"

Footprint0521 — Tue, 11 Aug 2026 01:02:26 +0000

Kimi code with k256 (I’ve heard you can easily one shot implement a proxy to other providers, even with deepseek v4 flash, if you don’t want kimi code) has stupidly low rate limits for and cost, compared to OpenAI which has massive rate limits and more cost

New comment by Footprint0521 in "Managing AI Coding Costs at Scale"

Footprint0521 — Sat, 08 Aug 2026 11:26:28 +0000

That is a wild article! Hopefully the recent US open source model initiatives can pan out to cut costs, because I’m not a fan of dependence on Chinese models either, but I’m in a spot where I need to maximize intelligence on minimal cost…

There’s not even a distant comparison US lab rn which is sad

New comment by Footprint0521 in "Managing AI Coding Costs at Scale"

Footprint0521 — Sat, 08 Aug 2026 11:18:56 +0000

Dude $3k? Holy heck you should look into K3/Deepseek V4 Flash

New comment by Footprint0521 in "Qwen3.8 Max now ranked as the best overall model by agentic index"

Footprint0521 — Thu, 06 Aug 2026 23:39:25 +0000

Facts lol, now all the Chinese models are 1/40th of the cost for the same intelligence

New comment by Footprint0521 in "Codex reimplemented in 8k lines of C++, <1MB binary"

Footprint0521 — Sun, 02 Aug 2026 14:14:26 +0000

Genuine question, what made you pursue C++ with this and not Rust?

New comment by Footprint0521 in "Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac"

Footprint0521 — Wed, 29 Jul 2026 19:07:56 +0000

Mythos alone proves the future of cybersecurity and software is agentic, and if you don’t believe that, run it back in 2 years when you are fired for someone who does..

+1 at least he cited his sources lol

New comment by Footprint0521 in "More Tailscale tricks for your jailbroken Kindle"

Footprint0521 — Wed, 29 Jul 2026 11:22:59 +0000

Nooo, now you can’t jailbreak it :,(

That’s what I did before I looked into KOReader and now I’m sad I did

New comment by Footprint0521 in "UK AISI / Caisi Preliminary Assessment of Kimi K3's Cyber Capabilities"

Footprint0521 — Sun, 26 Jul 2026 02:09:10 +0000

Playing devils advocate, does from scratch really matter if all frontier labs are training off each other anyways? Practically speaking, businesses/consumers just care about lowest inference cost for maximizing intelligence anyways (not to mention Anthropic/OpenAI forcing KYC/litigation barrier trash for access to any cybersecurity/IT capabilities) that I literally just cancelled Claude today.

Yeah it’s sad the CCP has my information. But it’s either them or the feds, and at least Chinese models actually work for cybersecurity tasks, not to mention aren’t stupid expensive

Artificialanalysis.ai rn on opus 5 is a joke. The main intelligence benchmarks it is like 1% better than Fable, but the cost difference between that and K3 is so funny lol. It’s the same with cars— you don’t have to do it from scratch, as long as you can do it cheaper and with the same quality, hence Toyota/Honda taking over

Yeah it’s sad that American models are censored more than Chinese ones lol (outside of asking them about the CCP) but it’s where we are at I guess :(

New comment by Footprint0521 in "UK AISI / Caisi Preliminary Assessment of Kimi K3's Cyber Capabilities"

Footprint0521 — Sun, 26 Jul 2026 01:44:42 +0000

Booz Allen is cute, but if china can train K3 on a fraction of the US compute availability, yet it benchmarks almost equivalent to Fable for a third of the cost, it’s game over for US labs in the long run.

Believe me, I wish this wasn’t the case, but open up the hardware on the device you are reading this on and tell me the majority of tech inside wasn’t made in China….

Manufacturing was lost a long time ago, this is really just another way

New comment by Footprint0521 in "Claude Opus 5"

Footprint0521 — Fri, 24 Jul 2026 21:54:47 +0000

Real… I’ve been using Deepseek v4 pro max as my main and then k3 in web (more usage credits) for automating what my deepseek agents do

New comment by Footprint0521 in "Claude Opus 5"

Footprint0521 — Fri, 24 Jul 2026 19:18:50 +0000

Switch to K3 and you won’t look back, I promise!! I got so fed up with Claude and finally bit the bullet to switch and it’s amazing

New comment by Footprint0521 in "Claude Opus 5"

Footprint0521 — Fri, 24 Jul 2026 19:17:26 +0000

Long live K3 lol

New comment by Footprint0521 in "Agent swarms and the new model economics"

Footprint0521 — Tue, 21 Jul 2026 17:27:49 +0000

Anthropic wants it that way so they can’t be sued… the correct answer is don’t, switch to Kimi K3 for much more usage, the same quality of model, and no hidden practices :/