HNHacker News
TopNewBestAskShowJobs

mstkllah

64 karma · joined September 4, 2023

submissionscomments
mstkllah··on Introducing Kwi, a new KDE terminal emulator
Can you elaborate on that? I use yakuake and I don't understand the connection. (I am merely a user not a software development or engineer)
mstkllah··on Microsoft Decision-1: 9B Qwen Model Launch Explained
Reads like an ad for Microsoft and its model because it's an article about a decision model that doesn't mention Jev or other decision models at all.
mstkllah··on Nordwand Mono – A monospace font for coders and adventurers
And way more expensive.
mstkllah··on Putting Linux on my RTX Spark laptop because I don't have a Microsoft account
Which video card? Which specialized engine?
mstkllah··on Timestral: Mistral release time-series foundation models
Do those places also include companies focused on private markets?
mstkllah··on Tiny Little Office
Here you go https://getartcraft.com/
mstkllah··on Janas: Run LLMs larger than RAM by streaming experts from SSD
Is the inference engine open-source?
mstkllah··on Nvidia announces native GPU programming in Rust
It's actually creep.
mstkllah··on Ask HN: What are you working on? (September 2026)
Where do you source the lineups and match data from?
mstkllah··on Automattic's board forces CEO Matt Mullenweg into leave of absence
Hearing stories about HOA as a non-US person I think he is actually quite suited leading one.
mstkllah··on Quasar 438B: Europe's Leading AI Model
Seconding this, would also like to hear more about the proxy.
mstkllah··on Superhuman Attention
Those 25 instances of ":" are probably caused by author telling their LLM to replace em dash with colon.
mstkllah··on Nvidia agrees to acquire Hugging Face for $13B
What is the support like for them? Can they be seriously considered as alternatives to Nvidia or AMD cards? I have been looking into buying a GPU, specifically the Radeon R9700 AI Pro but noticed the Intel cards too and was not sure what you make of them.
mstkllah··on Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows
Where can I find more information on the cybersecurity breakthroughs adapted prompt?
mstkllah··on Hallmark – Anti-AI-Slop Design Skill for Claude Code, Cursor, and Codex
I have used skills like impeccable, ui-ux-max, and many, many others and they all seem to converge on the same thing. They are good to help out with some inconsistencies, accessibility, streamlining, but the design itself is the same unless you are extremely explicit.
mstkllah··on Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro
Check Open Notebook:

https://github.com/lfnovo/open-notebook

mstkllah··on Show HN: HackerNows – Native iOS HN Client
Frist three apps won't even load.
mstkllah··on SubQ 1.1 Small
Did not feel as an upgrade to me at all, felt way slower at the same quality level as 4.8 to me.
mstkllah··on OpenClaw is a security nightmare dressed up as a daydream
What are your uses for it? If you don't mind sharing.
mstkllah··on How I use Claude Code: Separation of planning and execution
And then you have to remind it frequently to make use of the files. Happened to me so many times that I added it both to custom instructions as well as to the project memory.
mstkllah··on How I use Claude Code: Separation of planning and execution
Would love to check it out too once you put it up.
mstkllah··on Claude Memory
That's what I have been doing. The poster made it sound like they had some magical way of prompting very precisely.
mstkllah··on Claude Memory
Could you share some suggestions or links on how to best craft such very precise prompts?
mstkllah··on I only use Google Sheets
I feel quite comfortable in Excel - used various tools like Power Pivot, Power Query, OLEDB, created my own functions, Python within Excel, etc. - but Airtable felt so confusing and limiting. Other former colleagues also struggled with Airtable; maybe it was not explained to us correctly.
mstkllah··on Claude Sonnet 4 now supports 1M tokens of context
Ah, the very extensive study with 16 developers. Bulletproof results.
mstkllah··on GLM-4.5: Reasoning, Coding, and Agentic Abililties
I asked about this and got:

(500, 'Content Security Warning: The input text data may contain inappropriate content.')

mstkllah··on Claude Code Pro Limit? Hack It While You Sleep
Do you have a demo of it one can check?
mstkllah··on Google shared my phone number
It looks like it's a fake number anyway as it's 07700 987654
mstkllah··on Sharing a ChatGPT Account with My Wife
Kagi?
mstkllah··on NanoKVM: Affordable, Multifunctional, Nano RISC-V IP-KVM
What would you recommend for that use case? Just remote into an always on desktop?
Page 1 of 2Next →