Hacker News: scirob

New comment by scirob in "Mistral Large 4"

scirob — Tue, 06 Oct 2026 17:19:09 +0000

no hugging face link :( ... but hey its on openrouter yay

Here are my results

https://dach.peerbench.ai/compare?models=mistralai%2Fmistral...

Looks like a bit better than the recent Kolibri-1 but still below Qwen3.8 27B

New comment by scirob in "Gemini 4 Argon"

scirob — Wed, 30 Sep 2026 20:16:42 +0000

"Rolling out soon" don't let them hype without any release

New comment by scirob in "Google’s Project Suncatcher to put ML infrastructure in space"

scirob — Fri, 25 Sep 2026 12:45:43 +0000

Nice we have a document we can point at of someone doing a space data center project pointing out all the flaws and benefits without hallucinations.

Putting data centers in Antarctica or extreme north Canadian islands would also put you out of the way of molotov-throwing joe public. Even in space your not safe from the voting public as long as your companies directors are sitting on earth somewhere.

New comment by scirob in "Google’s Project Suncatcher to put ML infrastructure in space"

scirob — Fri, 25 Sep 2026 12:45:04 +0000

New comment by scirob in "Hy4 preview"

scirob — Sun, 30 Aug 2026 20:36:53 +0000

Just got benchmarks done for German langauge eval index i help maintain. Hy4 is a big improvement over h3 but still below Deepseek pro and Significantly below GLM 5.3 Flash .

hy4 ranks ~14th overall

https://dach.peerbench.ai/compare?models=tencent%2Fhy4-previ...

https://dach.peerbench.ai/models/tencent/hy4-preview

New comment by scirob in "AurionMail: E2EE suite (CryptPad/Stalwart) with single-password UX"

scirob — Wed, 26 Aug 2026 16:29:45 +0000

love the direction have asked myself manytimes why this feature sent doesn't exist somewhere; for sure would need to see some high profile people start using this to think its bullet proof

New comment by scirob in "Thomson Reuters Launches Its Own Frontier Model"

scirob — Tue, 25 Aug 2026 06:59:16 +0000

Maybe it's my dyslexic brain but "it's own frontier model" in my head converted to foundational model that was trained from scratch.

But this is qwen based.

But w/e I'm pro AI so more companies having more people with skills for more post training is cool

New comment by scirob in "IPFS Maintainers Winding Down"

scirob — Mon, 24 Aug 2026 18:05:55 +0000

I tried to build a few non crypto decentralized apps. The killer was reliable always deliverability inside the browser. https://inbrowser.link/ was a huge jump in utility but came to late the ipfs.js just never worked consistently. In the end the only way to get good XP for yours users was that you provider the IPFS to http gateway for all content but then whats the point its just decentralization theater.

I remember in 2015 having the IPFS concept blow my mind its such a memorable moment when it really felt like someone designed something significantly different that current mainstream paradigms. But in the end it seems like it was still a case of a cool technology looking for a use-case not solving a real problem.

New comment by scirob in "IPFS Maintainers Winding Down"

scirob — Mon, 24 Aug 2026 17:58:22 +0000

oh man and when Brave removed native IPFS support. https://github.com/brave/brave-browser/issues/37735

New comment by scirob in "Claudette: Make Claude stop talking like a BuzzFeed article"

scirob — Sat, 22 Aug 2026 15:36:30 +0000

can this not be achieved through a system prompt adjustment ? Running yet another LLM call on top might not be the simplest solution.

New comment by scirob in "Death to the Self-Playing Game"

scirob — Fri, 21 Aug 2026 20:23:43 +0000

Vampire survivor is an amazing game. If you can't accept the value of entertainment then the rest of your life is probably to easy.

But fair enough everyone can have their take.

New comment by scirob in "Qwen 3.8 27B"

scirob — Sat, 15 Aug 2026 12:42:59 +0000

We maintain German Langauge index as no one publishes or reruns these sepeartly.

Qwen 3.8 27B is a small improvement with some regressions in our benchmarks not a huge jump like benchmarks listed.

https://dach.peerbench.ai/compare?models=qwen%2Fqwen3.8-27b,...

German language has never been a big focus for asian models but they still outperform Gemma models https://dach.peerbench.ai/compare?models=openai%2FQwen%2FQwe...

So in production we have been using Gemini Flash Lite as primary and fall back to Qwen when gemini servers are overloaded or just giving us 429

New comment by scirob in "Herdr: Agent multiplexer that lives in your terminal"

scirob — Mon, 29 Jun 2026 06:24:33 +0000

Same question.

I usually have one local clause orchestrating multiple remote Claude in different tmux . And then another orchester and remote vm worker sin tmux for another repo etc...

It gets a bit hard to keep the overview but I don't want to give up my parallelism, your too might help

New comment by scirob in "Deno Desktop"

scirob — Mon, 22 Jun 2026 12:02:55 +0000

They had this before I used it to ship some stuff but binaries were big . How small did they get it with this update

New comment by scirob in "A Call to Action: Stop the FCC's KYC Regime"

scirob — Fri, 12 Jun 2026 20:25:58 +0000

Yea pls protect it feels mega oppressive how most EU countries require you to have the SIM card guy in his corner store scan your passport.

New comment by scirob in "Gemma 4 12B: A unified, encoder-free multimodal model"

scirob — Wed, 03 Jun 2026 20:00:49 +0000

Quickly deployed it to check some benchmarks relevant for German language. These are results for CohereLabs/include-base-44 german only : Gemma 4 12B %61.9

  Gemma 4 26B (a4b MoE)    0.647
  Qwen 3 14B               0.621 
  Gemma 4 12B              0.618
  Ministral 14B 2512       0.604 
  Gemma 3 12B              0.547

The quwen 3 14B vs Gemma 4 12B difference is within random variance they same in some repeat runs they actually got the exact same score. Next step up Gemma 4 31B gets 0.676 on this. Or let in some reasoning Qwen 3 14B (reasoning) 0.676.

I'll run some cheat-proof benchmarks ones tomorrow see if qwen is still on top.

New comment by scirob in "Goodbye Visa and Mastercard: 130M Europeans switching to sovereign payment"

scirob — Wed, 20 May 2026 17:54:37 +0000

Idk n26 still not integrated. Twint in Switzerland has amazing penetration can pay at any terminal with qr code

New comment by scirob in "Mistral's CEO: Europe has 2 years to stop becoming America's AI 'vassal state'"

scirob — Sun, 17 May 2026 17:55:52 +0000

I wonder why googles biggest European office is in the low tax high salary country of Switzerland

New comment by scirob in "EU weighs restricting use of US cloud platforms to process government data"

scirob — Sun, 17 May 2026 17:52:46 +0000

OMG just do, EU needs some balls. Upcloud, Scaleway, Hetzner, OVH are all production ready . EU business leaders are so afraid of not using the biggest provider they are blind to how you IT can absolutely run 100% on compute from these providers and opensource

New comment by scirob in "New arXiv policy: 1-year ban for hallucinated references"

scirob — Fri, 15 May 2026 09:53:52 +0000

Great, it's so easy to automate checking ref super bad to not check