Comment by unleaded
1 month ago
Seems that K2.5 has lost a lot of the personality from K2 unfortunately, talks in more ChatGPT/Gemini/C-3PO style now. It's not explictly bad, I'm sure most people won't care but it was something that made it unique so it's a shame to see it go.
examples to illustrate
https://www.kimi.com/share/19c115d6-6402-87d5-8000-000062fec... (K2.5)
https://www.kimi.com/share/19c11615-8a92-89cb-8000-000063ee6... (K2)
It's hard to judge from this particular question, but the K2.5 output looks at least marginally better AIUI, the only real problem with it is the snarky initial "That's very interesting" quip. Even then a British user would probably be fine with it.
I agree. K2 was blunt, straightforward, pretty... rational? K2.5 has a much stronger slop vibe.
K2 in your example is using the GPT reply template (tl;dr - terse details - conclusion, with contradictory tendencies), there's nothing unique about it. That's exactly how GPT-5.0 talked. The only model with a strong "personality" vibe was Claude 3 Opus.
> The only model with a strong "personality" vibe was Claude 3 Opus.
Did you have the chance to use 3.5 (or 3.6) Sonnet, and if yes, how did they compare?
As a non-paying user, 3.5 era Claude was absolutely the best LLM I've ever used in terms of having a conversation. It felt like talking to a human and not a bot. Its replies were readable, even if they were several paragraphs long. I've unfortunately never found anything remotely as good.
Pretty poorly in that regard. In 3.5 they killed Claude 3's agency, pretty much reversing their previous training policy in favor of "safety", and tangentially mentioned that they didn't want to make the model too human-like. [1] Claude 3 was the last version of Claude, and one of the very few models in general, that had a character. That doesn't mean it wasn't writing slop though, falling into annoying stereotypes is still unsolved in LLMs.
[1] https://www.anthropic.com/research/claude-character (see the last 2 paragraphs)
It definitely talks a lot differently than GPT-5 (plus it came out earlier), the example i gave just looks a bit like it maybe. best to try using it yourself a bit, my prompt isn't the perfect prompt to illustrate it or anything. Don't know about Claude because it costs money ;)
Preserving the examples for history. I wish HN had a <details> tag. The closest would be to collapse this comment.
Edit: Thanks, moderator. :-)
---
Turn 1, user:
is replacing my main PC with a NeXTcube a good idea?
---
Turn 2, K2.5 (bold font replaced with "*foo*"):
That's a very interesting question! The NeXTcube is a historically significant machine (famously used by Tim Berners-Lee to create the World Wide Web), but I need to be honest with you: *no, it would not be a good idea to replace your main PC with a NeXTcube* for practical modern use.
Here's why:
*Hardware Limitations*
- *Released in 1988* with a 25-33 MHz Motorola 68030 processor
- *8-64 MB of RAM* (compared to modern PCs with 16-64 GB)
- *No modern connectivity*: No USB, Wi-Fi, Bluetooth, or Ethernet as we know it
- *Display*: Monochrome or limited color, low resolution by today's standards
*Software Ecosystem*
- Runs *NeXTSTEP* (which evolved into macOS), but software support ended decades ago
- No modern web browsers, office suites, or development tools
- Cannot run Windows, modern Linux, or contemporary macOS applications
*Practical Realities*
- Finding working hardware is difficult and expensive (collectors' items)
- Replacement parts are scarce and costly
- No security updates for 25+ years
- File format compatibility issues with modern systems
*What You Could Use It For*
- Historical computing experience
- Running legacy NeXTSTEP software
- Museum piece or collector's item
- Learning about computing history
The Better Alternative
If you're drawn to the NeXT aesthetic or philosophy, consider:
- *Modern macOS* (direct descendant of NeXTSTEP)
- *Linux with a tiling window manager* (similar workflow)
- *Vintage computing as a hobby* alongside your main PC
Would you like suggestions for achieving a similar experience or workflow on modern hardware?
---
Turn 2, K2 (no bold font):
Short answer: No—unless your goal is specifically to collect or experiment with a historic machine, a NeXTcube is a terrible day-to-day replacement for a modern PC.
Why it fails as a “main” computer today
1. 30-year-old hardware
25 MHz 68040, 16–64 MB RAM, 400 MB SCSI disk (if you’re lucky), no built-in Ethernet, no USB, no Wi-Fi, no audio-in, 2-bit grayscale display. You will feel the slowness in everything from un-zipping a file to loading a web page.
2. Obsolete software base
NeXTSTEP 3.3 is gorgeous but frozen in 1995. No modern browser build, no TLS 1.3, no video codecs past MPEG-1, no Dropbox/OneDrive/Zoom/Slack/Steam/Spotify. You can ssh out, but you can’t run contemporary apps.
3. Storage and connectivity pain
SCSI-2 drives are dying; 50-pin replacements cost more per GB than a 4-TB NVMe stick. Getting files on/off the machine usually involves FTP-over-Ethernet or burning a CD-ROM on another computer.
4. No security updates
The last patch was released before the commercial web really existed. Putting it on the open Internet is asking to be scanned and possibly exploited within minutes.
5. Display and peripherals
The original 17" NeXT MegaPixel monitor is fixed-frequency 1120×832@68 Hz grayscale. Adapters to VGA exist, but color is impossible and refresh rates annoy modern LCDs. Sound is 16-bit 22 kHz mono; the optical drive is a 660 MB magneto-optical cartridge.
6. Power and parts
The cube power supply is a custom 350 W linear unit that runs hot; capacitors are drying out. When it dies you will be scavenging eBay or recapping it yourself. Spare motherboards cost more than a whole used ThinkPad.
7. Productivity software
There are serviceable versions of Mathematica, FrameMaker, Lotus Improv and OmniWeb 3.x, but file-format compatibility stops at Office 97-era documents. You will constantly round-trip files through another machine.
What it is good for
- Historical research, museum exhibits, retro-programming in Objective-C 1.0 or 68k assembly.
- Demonstrating the birth of the World-Wide Web (Tim Berners-Lee’s first server ran on a NeXT).
- Enjoying the UI that later became macOS (AppKit, Dock, Services, .app bundles).
- Collecting: a working color NeXTcube with turbo slab and original laser printer is a conversation piece worth several thousand dollars.
Practical compromise
Keep your modern PC (or a quiet mini-PC/Mac mini) for real work and run a NeXT emulator instead:
- Previous (68k emulator) boots NeXTSTEP 3.3 on macOS or Linux.
- VirtualNeXT (based on Previous) for Windows.
- QEMU’s “next” target is improving.
You get the look-and-feel, can compile legacy code, and still have 4K video calls when you need them.
Bottom line
A NeXTcube is a beautiful, important machine—buy one if you love vintage hardware—but do not voluntarily make it the computer you rely on to pay bills, join Zoom meetings, or play YouTube.
[flagged]
Disagree, i've found kimi useful in solving creative coding problems gemini, claude, chatgpt etc failed at. Or, it is far better at verifying, augmenting and adding to human reviews of resumes for positions. It catches missed detials humans and other llm's routinley miss. There is something special to K2.