Hacker News: ant6n

New comment by ant6n in "OpenAI Is Preparing to File for an IPO Soon"

ant6n — Thu, 21 May 2026 06:22:30 +0000

Tesla used to be a kind of “ethical” play. They made electric cars cool.

New comment by ant6n in "The last six months in LLMs in five minutes"

ant6n — Tue, 19 May 2026 07:45:12 +0000

I only used Claude first time in April, previously only ChatGPT and Gemini. And I struggle to see what the hype is all about - yes it seems a tiny bit smarter than the pack, but on the 20$ subscription it runs out of tokens in 5-20 minutes, and then you need to wait 3-4h.

ChatGPT 5.5 seems capable, although a bit stingy with “thinking” compared to earlier models, and I never run into session limits.

New comment by ant6n in "MacBook Neo Deep Dive: Benchmarks, Wafer Economics, and the 8GB Gamble"

ant6n — Thu, 14 May 2026 07:34:52 +0000

It’s a nice hardware. But that garden is full of bugs, not much less than if you have open windows.

New comment by ant6n in "If AI writes your code, why use Python?"

ant6n — Tue, 12 May 2026 07:34:41 +0000

That’s true. Once you have APIs and want to use classes to create larger structures, the language is full of warts.

New comment by ant6n in "I switched from Mac to a Lenovo Chromebook"

ant6n — Thu, 07 May 2026 19:14:39 +0000

...except the operating system. And the silly notch. And the weird keyboard. And the hard palm-cutting corner. And the reflective screen. and the finger-print-magnet materials. And the small amount of RAM. and the small SSD. And the weight.

Other than that, it's perfect! (On the blance,still better than any other laptop)

New comment by ant6n in "Wolfenstein 3D for Gameboy Color on custom cartridge (2016)"

ant6n — Wed, 06 May 2026 19:31:33 +0000

You need to do mid-frame tile updates just to show a full bitmap frame. There’s 360 8x8 tiles on the screen, but the tile indices are 8 bit (you can only reference 256 tiles). You can store only 384 tiles in VRAM - a bit more than a full screen. So the mid-screen update is to go from one tile dictionary to the other, so you can access 360 tiles in total.

You can update 1 tile per scan line (during hblank), so 154 tiles per frame (including 10 vblank scanlines). So you need 2.5 frames to replace all tiles.

If you are really smart about updates, you can “race the beam”, basically start updating tiles just as the frame starts rendering, just behind the active scan line. Then you can update maybe 280 tiles before the active scan line of the next frame catches up with you.

New comment by ant6n in "Neanderthals ran 'fat factories' 125,000 years ago (2025)"

ant6n — Sun, 03 May 2026 12:53:37 +0000

…so you were produced in Neanderthal fat factory?

New comment by ant6n in "Neanderthals ran 'fat factories' 125,000 years ago (2025)"

ant6n — Sun, 03 May 2026 12:52:25 +0000

Soap, soup, goop

New comment by ant6n in "Neanderthals ran 'fat factories' 125,000 years ago (2025)"

ant6n — Sun, 03 May 2026 12:47:13 +0000

Isn’t that what George Lukas said about Star Wars?

New comment by ant6n in "Kimi K2.6 just beat Claude, GPT-5.5, and Gemini in a coding challenge"

ant6n — Sun, 03 May 2026 06:20:44 +0000

What I would like to see is a comparison of how well the models work in long running conversations:

  * do they lie and gaslight

  *  do they start breaking down on very long chats (forget old context, just get dumber)

  * do they constantly try to tell me how smart I am vs solving the problem (yes man)

  * do they follow conventions, parameters set out early in the prompts, or forget them

  * if they cant read a given file (like pdf), do they lie about it

  * is there a branch function to go back to earlier state of conversation

  * what is the quality of the presentation of results (structure, wording, excessive use of tables, appropriate use of headings)

  * how does the bot deal with user frustration (empathy?)

For example Chatpgt 5.5 is fairly smart, but presentation of results is kind of poor and unstructured, and unnecessarily long. It will break down on long conversations (the long answers dont help here), and it can’t deal with that except lying and gaslighting. It also has very little empathy, and mostly ignores user frustration. But at least theres branching, so one can go back without completely starting over.

Gemini doesnt feel quite as smart these days. It does well with very long conversations. Except it has bugs where all context gets lost or pruned, and it will lie and gaslight about it. Theres also no branching, so once context is lost you have to start over. Presentation is decent. Empathy is fairly good, except if users get frustrated, it gets more and more flustered and breaks down.

New comment by ant6n in "DeepSeek v4"

ant6n — Sat, 02 May 2026 07:06:46 +0000

It’s not just about “good” UX. It’s riddled with bugs.

New comment by ant6n in "AI uses less water than the public thinks"

ant6n — Fri, 01 May 2026 23:40:46 +0000

This sounds like being concerned about the adverse health effects of a steak due to sugar.

New comment by ant6n in "DeepSeek v4"

ant6n — Thu, 30 Apr 2026 12:13:52 +0000

Not if Gemini Lost all context already. Also, it doesn't really work well, a lot of the nuance and information simply gets lost.

New comment by ant6n in "DeepSeek v4"

ant6n — Fri, 24 Apr 2026 04:52:39 +0000

Funny how Gemini is theoretically the best -- but in practice all the bugs in the interface mean I don't want to use it anymore. The worst is it forgets context (and lies about it), but it's very unreliable at reading pdfs (and lies about it). There's also no branch, so once the context is lost/polluted, you have to start projects over and build up the context from scratch again.

New comment by ant6n in "GPT-5.5"

ant6n — Thu, 23 Apr 2026 20:41:07 +0000

My impression has been that ChatGPT-5.4 has been getting dumber and more exhausting in the last couple of weeks. Like it makes a lot of obvious mistakes, ignores (parts of) prompts. keeps forgetting important facts or requirement.

Maybe this is a crazy theory, but I sometimes feel like they gimp their existing models before a big release to you'll notice more of a "step".

New comment by ant6n in "4-bit floating point FP4"

ant6n — Sun, 19 Apr 2026 00:34:22 +0000

That written document is prehistoric.

New comment by ant6n in "4-bit floating point FP4"

ant6n — Sat, 18 Apr 2026 20:47:51 +0000

> In ancient times, floating point numbers were stored in 32 bits.

I thought in ancient times, floating point numbers used to be 80 bit. They lived in a funky mini stack on the coprocessor (x87). Then one day, somebody came along and standardized those 32 and 64 bit floats we still have today.

New comment by ant6n in "Anonymous request-token comparisons from Opus 4.6 and Opus 4.7"

ant6n — Sat, 18 Apr 2026 17:11:51 +0000

I thought it would be to get better, to stay competitive with the competitors and free models.

New comment by ant6n in "Filing the corners off my MacBooks"

ant6n — Sat, 11 Apr 2026 10:31:45 +0000

Well actually, your not well actually to the well actually was actually a well actually of the well actually. Just sayin’.

New comment by ant6n in "Improving my focus by giving up my big monitor"

ant6n — Sat, 04 Apr 2026 17:25:04 +0000

I dunno. I wish as a start, MacOS would improve window management, so I don’t keep jumping around the various desktops all the time and get lost.