HNHacker News
TopNewBestAskShowJobs

NamlchakKhandro

-14 karma · joined September 9, 2025

submissionscomments
NamlchakKhandro··on New Mac mini, featuring M6 and M5 Pro
you're looking at the wrong device.

- Apple M5 Ultra chip

- 30-core CPU with 10 super cores and 20 performance cores

- 64-core GPU

- Neural Accelerators

- Hardware-accelerated ray tracing

- 32-core Neural Engine

- 1.2TB/s memory bandwidth

one point 2 terrabyte a second memory bandwidth....

512gb coming later this year

but at the cost of a small car

NamlchakKhandro··on New Mac mini, featuring M6 and M5 Pro
That's just because most people are bad at communication to start with.

Look at all the shit github README before llm. Most repos didn't bother because it was effort. those few that did, were because of autistic focus. Of those, very few were "great" user documentation.

now llms are here, the effort barrier is gone, and now we're inundated with shit README that provide no value to users nor respect their time.

Once you start applying SKILL.md that revolve around fixing HOW to communicate value to users in a way that respects their time, you'll see this story change in noticeable places.

I doubt it will change everywhere because it also requires that you give a shit about doing this in the first place, so those people Ed Zitron talks about... business idiots won't care, because they're ultimately nihlist.

NamlchakKhandro··on New Mac mini, featuring M6 and M5 Pro
lmfao ... inflation. are you trolling sir?
NamlchakKhandro··on Maiao: Gerrit-style code review workflow for GitHub, GitLab, Gitea, others
Who is creating a separate PR for each commit on their feature/fix branch?

sounds like crazy town.

I just dont understand why someone would operate like this.

Lets assume you're squash merging your feature branchs to your local main, then you're raising the them as prs.

why would you do this?

NamlchakKhandro··on Apple introduces M6 and M5 Ultra
LLMs and unified memory
NamlchakKhandro··on Apple introduces M6 and M5 Ultra
Lmao keyboard shortcuts in Linux are AMAZING.

In that I can make them what ever I want

NamlchakKhandro··on Apple introduces M6 and M5 Ultra
Make installing Linux on it easy
NamlchakKhandro··on fx :Tiny, open, native coding agent.
and like Barbara, i'm out.
NamlchakKhandro··on fx :Tiny, open, native coding agent.
anthropic hate freedom. what makes you think they want you thinking?
NamlchakKhandro··on Why your local LLM feels dumber than it is
word salad? again in english?
NamlchakKhandro··on Felony charges for citizen deleting phone data at US Border
Alex Jones entered your living room
NamlchakKhandro··on Show HN: OzBrain, a shared brain for knowledge between agents and your team
Meh
NamlchakKhandro··on Apple announces changes for apps in the European Union
Stop buying Apple products
NamlchakKhandro··on Qwen 3.8 27B is excellent, but it defaults to overthinking things
Don't bother with plans
NamlchakKhandro··on Working with AI feels more like leadership than coding
Fellow Apple product user. Join me in jeering at people who drink instant coffee.
NamlchakKhandro··on Qwen 3.8 27B
copilot isn't a model. it's a model hoster.
NamlchakKhandro··on Maximizing the value of your Claude Code sessions
There are no women on the internet.

I remember when the internet was an exchange of ideas instead of using gender to justify value of bad ideas

NamlchakKhandro··on Maximizing the value of your Claude Code sessions
https://cchistory.mariozechner.at

and as is normal for hosted models, almost everything... based on load flucation they may even send your prompt to a quantised model

NamlchakKhandro··on Maximizing the value of your Claude Code sessions
1000% warranted. not sure what level of peak echo bubble you live in where this level of critiscism feels like you need to defend a ONE TRILLION DOLLAH company.

seriously... priorities yeah?

NamlchakKhandro··on Maximizing the value of your Claude Code sessions
meah Claude is peak trash. Really fucking upset that they ban you for using a superior harness
NamlchakKhandro··on Qwen 3.8 27B
harness setup? how much vram ? how are you handling a 2hr long build ? multiple sessions? fan out sessions (subagents)?
NamlchakKhandro··on Qwen 3.8 27B
really? crush.... it's trash harness compared to pi.

I didn't realise there are people out there unironically using crush

NamlchakKhandro··on Qwen 3.8 27B
Woah woah woah buddy... suggesting that people use anything other than ClaudeCode or Codex is simply not allowed around these parts.
NamlchakKhandro··on Why does Opus 5 feel worse to work with?
I loath that claude still cling to CLAUDE.md and not AGENTS.md
NamlchakKhandro··on Why does Opus 5 feel worse to work with?
which is just the same as having it in your AGENTS.md and also having a agent_settled hook that reminds it on how to talk
NamlchakKhandro··on Hello, me. It's been a while
Picture yourself in a location where getting eaten is problem.

Now intersect those locations with internet coverage.

Your statement didn't make much sense anymore

NamlchakKhandro··on AI At Home Part 1: A Box Of Scraps
a heat stack chimney would make it silent
NamlchakKhandro··on Apple Silicon and macOS VMs: 11–16× Faster LLM Inference with Llama.cpp
No
NamlchakKhandro··on England set to be one of the first countries to eliminate hepatitis C
Do you think it's also helpful that they see these things being pushed "for profit)
NamlchakKhandro··on Silicon Valley misreads science fiction and undermines democracy
Zuckerberg style the idea from snow crash
← PreviousPage 3 of 12Next →