riskable

joined 2 years ago
[–] riskable@programming.dev -2 points 1 month ago (2 children)

stole all that licensed code.

Stealing is when the owner of a thing doesn't have it anymore; because it was stolen.

LLMs aren't "stealing" anything... yet! Soon we'll have them hooked up to robots then they'll be stealing¹ 👍

  1. Because a user instructed it to do so.
[–] riskable@programming.dev 1 points 1 month ago

I guess I get to merge my code and never work on this project again.

This is the way.

[–] riskable@programming.dev 230 points 1 month ago (4 children)

FYI: That's more Windows games than run in Windows!

WTF? Why? Because a lot of older games don't run in newer versions of Windows than when they were made! They still run great in Linux though 👍

[–] riskable@programming.dev 3 points 1 month ago

A pet project... A web novel publishing platform. It's very fancy: Uses yjs (CRDTs) for collaborative editing, GSAP for special effects (that authors can use in their novels), and it's built on Vue 3 (with Vueuse and PrimeVue) and Python 3.13 on the backend using FastAPI.

The editor TipTap with a handful of custom extensions that the AI helped me write. I used AI for two reasons: I don't know TipTap all that well and I really want to see what AI code assist tools are capable of.

I've evaluated Claud Code (Sonnet 4.5), gpt5, gpt5-codex, gpt5-mini, Gemini 2.5 (it's such shit; don't even bother), qwen3-coder:480b, glm-4.6, gpt-oss:120b, and gpt-oss:20b (running locally on my 4060 Ti 16GB). My findings thus far:

  • Claude Code: Fantastic and fast. It makes mistakes but it can correct its own mistakes really fast if you tell it that it made a mistake. When it cleans up after itself like that it does a pretty good job too.
  • gpt5-codex (medium) is OK. Marginally better than gpt5 when it comes to frontend stuff (vite + Typescript + oh-god-what-else-now haha). All the gpt5 (including mini) are fantastic with Python. All the gpt5 models just love to hallucinate and randomly delete huge swaths of code for no f'ing reason. It'll randomly change your variables around too so you really have to keep an eye on it. It's hard to describe the types of abominations it'll create if you let it but here's an example: In a bash script I had something like SOMEVAR="$BASE_PATH/etc/somepath/somefile" and it changed it to SOMEVAR="/etc/somepath/somefile" for no fucking reason. That change had nothing at all to do with the prompt! So when I say, "You have to be careful" I mean it!
  • gpt-oss:120b (running via Ollama cloud): Absolutely fantastic. So fast! Also, I haven't found it to make random hallucinations/total bullshit changes the way gpt5 does.
  • gpt-oss:20b: Surprisingly good! Also, faster than you'd think it'd be—even when giving it a huge refactor. This model has lead me to believe that the future of AI-assisted coding is local. It's like 90% of the way there. A few generations of PC hardware/GPUs and we won't need the cloud anymore.
  • glm-4.6 and qwen3-coder:480b-cloud: About the same as gpt5-mini. Not as fast as gpt-oss:120b so why bother? They're all about the same (for my use cases).

For reference, ALL the models are great with Python. For whatever reason, that language is king when it comes to AI code assist.

[–] riskable@programming.dev 3 points 1 month ago* (last edited 1 month ago) (5 children)

If I broke into your home, why TF would I carefully take apart your robot vacuum in order to copy your wifi credentials‽

Also, WTF other "secrets" are you storing on your robot vacuum‽

This is not a realistic attack scenario.

[–] riskable@programming.dev -5 points 1 month ago (11 children)

I'm having the opposite experience: It's been super fun! It can be frustrating though when the AI can't figure things out but overall I've found it quite pleasant when using Claude Code (and ollama gpt-oss:120b for when I run out of credits haha). The codex extension and the entire range of OpenAI gpt5 models don't provide the same level of "wow, that just worked!" Or "wow, this code is actually well-documented and readable."

Seriously: If you haven't tried Claude Code (in VS Code via that extension of the same name), you're missing out. It's really a full generation or two ahead of the other coding assistant models. It's that good.

Spend $20 and give it a try. Then join the rest of us bitching that $20 doesn't give you enough credits and the gap between $20/month and $100/month is too large 😁

[–] riskable@programming.dev 51 points 1 month ago (9 children)

NO! It'syour device, you should have root! The fact that the manufacturer gives their product owners root is a good thing, not bad!

I will die on this fucking hill.

[–] riskable@programming.dev 65 points 1 month ago (2 children)

Blathering blatherskite!

[–] riskable@programming.dev 9 points 1 month ago

This is the latest American version of The Monkey's Paw wish to be rich.

[–] riskable@programming.dev 70 points 1 month ago (2 children)

The health insurance death spiral has officially begun its final phase!

https://en.wikipedia.org/wiki/Death_spiral_%28insurance%29

[–] riskable@programming.dev 54 points 1 month ago* (last edited 1 month ago) (3 children)

He should play on all the girls teams, crush it like a total badass, then when conservative parents complain that "a boy is playing on the girls team" everyone can tell them to shut the fuck up because this is the future they always wanted. One with no exceptions or grey areas to speak of.

[–] riskable@programming.dev 5 points 1 month ago (1 children)

Yes. Better if they collect it from personal blogs running on people's PCs 👍

view more: ‹ prev next ›