Hacker News: RALaBarge

New comment by RALaBarge in "Kimi-K3 Releases on HuggingFace 7/27"

RALaBarge — Mon, 27 Jul 2026 11:17:34 +0000

At least they don’t make you stay till the end of the presentations to give you the software you actually came for

New comment by RALaBarge in "Running a 28.9M parameter LLM on an $8 microcontroller"

RALaBarge — Sun, 26 Jul 2026 14:07:09 +0000

Not trying to be snide, but I copied and pasted their entire comment verbatim into google and it came up with Padauk PMS150C or Puya PY32 series

New comment by RALaBarge in "Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA"

RALaBarge — Wed, 22 Jul 2026 12:55:26 +0000

I work for a router company too, I ran some tests on all of the cheapest models and came to the same outcome where a handful of small models ran together in conjunction outperform SoTA models -- outperforms in that it got a 95% vs a 94% and I bet that changes with the day of the week. Anyways, I did get a similar result in a different sort of measurement.

New comment by RALaBarge in "Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA"

RALaBarge — Wed, 22 Jul 2026 12:53:02 +0000

I've been doing a lot of Trust and Safety and anti-scam stuff recently. When it was first re-released Fable wouldn't do anything for me, now I don't really run into refusals or what it used to do, just stop returning any data at all whatsoever.

Outside topic, but check out the Inkling model -- it is SUPER FAST and does a good job at being a terminal buddy but I would probably offload the real programming or hard tasks to fable or someone else

New comment by RALaBarge in "Vancouver PD website features Quick Escape button that wipes itself from history"

RALaBarge — Wed, 15 Jul 2026 10:53:05 +0000

Right, but it will get re-enabled on updates or something...it never stayed off for me.

New comment by RALaBarge in "Bonsai 27B: A 27B-Class model that runs on a phone"

RALaBarge — Tue, 14 Jul 2026 21:03:36 +0000

What have you been using?

New comment by RALaBarge in "Sam Neill has died"

RALaBarge — Mon, 13 Jul 2026 12:57:20 +0000

"What makes you think I'll miss?"

New comment by RALaBarge in "Sam Neill has died"

RALaBarge — Mon, 13 Jul 2026 12:55:11 +0000

Something that is burnt into me is saying "DO YOU SEE?", invoking the final lines of Neill in Event Horizon

New comment by RALaBarge in "Sam Neill has died"

RALaBarge — Mon, 13 Jul 2026 12:54:08 +0000

Yeah! Its a great movie if you dont try to nitpick stuff, which is hard for me to do on a lot of things too.

Neill: We can't just abandon this ship, we just found her Fishburn: I have no intentions of abandoning her. We will get far enough away from it and blow it up. Fuck this ship.

New comment by RALaBarge in "Write code like a human will maintain it"

RALaBarge — Fri, 10 Jul 2026 16:51:27 +0000

I think the biggest conceit here is the expectation that humans will continue to do this task in the medium to long term. This was good advice in the past but when inference is ubiquitous and most code ends up being Claudewritten anyways, there is little point. If you are writing C for NASA/ESA then yes of course. For the 99% of the rest of us, probably not so much in the coming years.

New comment by RALaBarge in "Write code like a human will maintain it"

RALaBarge — Fri, 10 Jul 2026 16:46:38 +0000

I like to also compliment the model on its very fashionable shoes as well, they love the flattery.

New comment by RALaBarge in "Delta flight hit by firework while landing at Midway Airport on Fourth of July"

RALaBarge — Mon, 06 Jul 2026 11:50:26 +0000

I highly recommend the ground tofu for taco's, you would never know they are meatless.

New comment by RALaBarge in "Ditching Claude for OpenCode and OpenRouter"

RALaBarge — Wed, 01 Jul 2026 10:20:31 +0000

OpenCode is a great replacement harness…I use it with deepseek v4 and it is as good as Claude without it trying to sneak in Anthropic specific code

New comment by RALaBarge in "Previewing GPT‑5.6 Sol: a next-generation model"

RALaBarge — Fri, 26 Jun 2026 19:57:05 +0000

You have an agent spawn the agents for you! You can ask Claude to do it for you, he is happy to use sonnet when you ask for grok and opus high when you ask for deepseek.

New comment by RALaBarge in "Previewing GPT‑5.6 Sol: a next-generation model"

RALaBarge — Fri, 26 Jun 2026 19:50:39 +0000

It’s my daily driver in opencode

New comment by RALaBarge in "Artificial intelligence is not conscious – Ted Chiang"

RALaBarge — Thu, 04 Jun 2026 13:27:26 +0000

An electric cloud with quantum effects that we also don’t fully understand. There will always be a layer deeper that we just do not know the effects of or what actually exists there or “under there”.

New comment by RALaBarge in "Prolific Wikipedia editors are threatening to go on strike"

RALaBarge — Fri, 29 May 2026 13:16:13 +0000

Billions of people on the planet, and not a single one of them would offer to do it?

New comment by RALaBarge in "A few words on DS4"

RALaBarge — Fri, 15 May 2026 10:21:08 +0000

They never should have trusted Qwark

New comment by RALaBarge in "I'm going back to writing code by hand"

RALaBarge — Mon, 11 May 2026 19:42:24 +0000

And it is only the beginning.

New comment by RALaBarge in "Shai-Hulud Themed Malware Found in the PyTorch Lightning AI Training Library"

RALaBarge — Fri, 01 May 2026 01:50:19 +0000

Yeah then you can version lock changes to one thing post-evaluation vs or even easier as noted above, download the stdlib and host it yourself.