HNHacker News
TopNewBestAskShowJobs

anonyfox

2,005 karma · joined August 7, 2013

https://anonyfox.com
submissionscomments
anonyfox··on Cursor 3
Just switched to Claude code with a max20 sub for ~200$/mo. Getting the same load done as previously with cursor api calls going over 7000$/mo. Now using the vscode/cursor plugin and have CC within cursor tabs natively - good combo, can recommend!
anonyfox··on Google releases Gemma 4 open models
M5 air here with 32gb ram and 10/10 cores. Anyone got some luck with mlx builds on oMLX so far? Not at my machine right now and would love to know if these models already work including tool calling
anonyfox··on April 2026 TLDR Setup for Ollama and Gemma 4 26B on a Mac mini
M5 air here with 32gb ram and 10/10 cores. Anyone got some luck with mlx builds on oMLX so far? Not at my machine right now and would love to know if these models already work including tool calling
anonyfox··on Claude Code Unpacked : A visual guide
You guys all get it’s an April joke?
anonyfox··on Rank the 50 best Apple products
Well for me it would be the M1 macbook air - apple silicon, no fans, extreme battery life and after like 2 decades of barely changing laptop experiences whew this thing was _fast_ too. Such a small powerful thing to have it was amazing. (still have mine, going strong).

Plus Mac OSX Mavericks. Guess the last really nice OS launch that simply did fixes and perf improvements (memory compression, ...) instead of slowing the machine down or adding friction. these were the days when people would look forward to a new mac os, not fearing another bullshit.

anonyfox··on iPhone 17 Pro Demonstrated Running a 400B LLM
I could see apple doing just that because they can and then having this another selling point of selling their own hardware. like their software is hard customized to run on their own hardware and vice versa (at least on paper), they could totally get some LLM going that works perfectly well on their chips specifically as a good enough local model in the next years, and promote it as kind of you-don't-need-a-subscription-when-you-have-an-iphone kind of thing. given the advances in recent years in the LLM space sounds kinda realistic to arrive somewhere that locally just works mid-term.
anonyfox··on Anthropic, please make a new Slack
the sad part is ... its likely true.
anonyfox··on Claude struggles to cope with ChatGPT exodus
well I have a running model (ha!) in my head about the frontier providers thats roughly like this:

- chatgpt is kinda autistic and must follow procedures no matter what and writes like some bland soulless but kinda correct style. great at research, horrible at creativity, slow at getting things done but at least getting there. good architect, mid builder, horrible designer/writer.

- claude is the sensitive diva that is able to really produce elegant code but has to be reminded of correctness checks and quality gates repeatedly, so it arrives at something good very fast (sometimes oneshot) but then loses time for correction loops and "those details". great overall balance, but permanent helicoptering needed or else it derails into weird loops.

- grok is the maker, super fast and on target, but doesn't think deeply as the others, its entirely goal/achievement focussed and does just enough things to get there. uniqiely it doesn't argue or self-monologue constantly about doubts or safety or ethics, but drives forward where other stuggles, and faster than others. cannot conenctrate for too long, but delivers fast. tons of quick edits? grok it is. "experimental" stuff that is not safe talking about... definitely grok.

- gemini is whatever you quickly need in your GSuite, plus looking at what others are doing and helping out with a sometimes different perspective, but beyond that worse than all the others on top.

- kimi: currently using it on the side, not bad at all so far, but also nothing distinct I crystallized in my head.

anonyfox··on Claude struggles to cope with ChatGPT exodus
give 5.4 a shot - its straneg but surprisingly good for once. speaking as a daily opus user.
anonyfox··on Claude struggles to cope with ChatGPT exodus
because gemini, despite what stats say, still produces garbage once the problem gets harder. it nails it for lab conditions, but messy reality or creativity or even code quality is a far cry from opus or the latest gpt5.4 by a long shot. and always has been. its pretty good inside the GSuite because of integrations, but standalone its near worthless compared to even grok-code-fast which doesn't think much at all (but damn it is fast). At this point google keeps throwing noodlepots with AI against every wall in reach to see what sticks, which is more kind of desperation that still works to increase wall street highscores, but not exactly a streak or breakthrough. just rapid fire shotgun launches to see if anything sticks. No one serious talks Gemini because its not even worth considering still for real things outside shiny presentations and artificial benchmarks.
anonyfox··on Claude struggles to cope with ChatGPT exodus
not the poster, but I guess thats kinda american thinking that actually believes voting with your wallet will make any difference in this late stage crony capitalism in a post-facts world.

realistically: AI WILL get used in military and for killing autonomously, like it or not, believe it or not. I am also against that in principle but I do accept the fact my opinion just doesn't matter and practice radial acceptance or reality as-is. twitter/X is also alive and kicking, despite musk and anti-musk-hate. xAI/Grok is genuinely really good too compared to OAI/Claude, a bit different but very good. At this point all the "outcries" feel like noise I just skip on principle. But it could turn up the fire under the OAI team to go aggressive feature/pricing wise in order to retain/increase their userbase again, which is ... good, after all.

anonyfox··on Tell HN: I'm 60 years old. Claude Code has re-ignited a passion
Well, slightly different take: it's like telling an artist the world doesn't need another song about love, these already exist and can be re-heard as needed. Sharper formulated: a CRM or TODO-list is a solved problem in theory, right? tons of solutions even free ones to use out there. still look at what people are doing and selling - CRMs and TODO-list variations. because, in fact, its not solved, and always has certain tradeoffs that doesn't fit some people.
anonyfox··on Tell HN: I'm 60 years old. Claude Code has re-ignited a passion
youre getting it backwards. anyone can get to something that looks alright in a browser... until you actually click something and it fails spectacularly, leaks secrets, doesn't scale beyond 10 users and is a swamp of a codebase that prevents clean ongoing extension = hard wall for non techies, suddenly the magical LLM stops producing results and makes things worse.

All this senior engineering experience is a critical advantage in these new times, you implicitly ask things slightly different and circumvent these showstoppers without even thinking if you are that experienced. You don't even need to read the code at all, just a glimpse in the folder and scrolling a few meters of files with inline "pragmatic" snippets measured in meters and you know its wrong without even stepping through it. even if the autogenerated vanity unit tests say all green.

Don't feel let down. Slightly related to when Google sprung into existence - everyone has access and can find stuff, but knowing how to search well is an art even today most people don't have, and makes dramatic differences in everyday usage. Amplified now with the AI search results even that often are just convincing nonsense but most people cannot see it. That intuitive feel from hard won experience about what is "wrong" even without having an instant answer what would be "right" is getting more and more the differentiator.

Anyone can force their vibe coded app into some shape thats sufficient for their own daily use and they're used to avoiding their own pitfalls of the tool they created and know are there, but as soon as there's some kind of scaling (scope, users, revenue, ...) involved, true experts are needed.

Even the new agent tools like Claude for X products at the end perform dramatically different in the hands of someone who knows the domain in depth.

anonyfox··on How will OpenAI compete?
> ChatGPT has a good name

I don't know but around here common people all say "Chatty" nowadays, and also most people if writing the correct name fail to spell "gpt" right quite often in chat.

anonyfox··on Ask HN: Share your personal website
https://anonyfox.com
anonyfox··on Apple's slow AI pace becomes a strength as market grows weary of spending
this night I got accidentially the update to the latest iOS with this liquid glass stuff - and its schockingly bad in any dimension. keyboard input lags, many thing ned MORE clicks/touches then before, weird contenxt menu popovers that don't even register taps 50% of the time, general lags and sluggishness and UI artifacts everywhere. Its really really a degradiation of UI/UX even though I personally am a fan of that glass-style design in itself
anonyfox··on The past was not that cute
guess people upvote what they're right now interested in. still a lot better than the next AI slop trying to hype
anonyfox··on All it takes is for one to work out
Seeing the other comments I feel like the luckiest moment of my life was meeting my future wife when I was at school with 16 and having been together since for 20+ years, through higher education and kids and house mortgage and all. Zero drama, mutual respect and affection, both still preserving some independence to maintain a „self“, good double income.

Might sound stupid, but this major life area being just a rock solid fundament frees up so much energy my peers still struggle with nowadays quite often it’s insane in hindsight. Everyday life costs are lower, some risk taking is possible when someone has your back unconditionally and even supports it (as long as not going reckless), and a secure home base to return to is something I guess even money can’t easily buy. Short of being born already rich I guess that’s a cheat code with similar small odds, and I appreciate it.

Then the „business opportunities“ become just something way more relaxed. Not identity level validation attempts or despair to get into a better life. Which again allows better judgement calls and reintroduces more fun and creativity into many things.

Just my 2c for perspective

anonyfox··on Rebecca Heineman has died
actually a difference is also how many players along the supply chain siphon money out of the process. the more greed is allowed and acted on for the treatment, the more expensive it gets. introduce layers of insurances, hedgefonds, pension funds, lobbyism, ... it adds up to riddiculous amounts far beyond the original R&D/infrastructure/treatment costs.
anonyfox··on Ask HN: Who wants to be hired? (October 2025)
Location: Hamburg, Germany

Remote: yes when timezone is reasonable

Willing to relocate: no

Technologies: Rust, Go, Elixir, JS/TS, Cloud stuff, AI/ML/Math, ...

Résumé/CV: https://anonyfox.com/cv

Email: max@anonyfox.com

—-

Either Fullstack (senior/…/principlal), DevOps, Architect, or Team Lead/CTO, whatever - I grew up with having to do all the roles back in the day, from Startup Growth Hacking over Scale-Up Optimization to Enterprise Executive. Not crypto stuff or AI desperation.

anonyfox··on The Death of Utilitarian Programming
I don't know, my own DevOps practises evolve around straightforward shell/go/js snippets that try to enforce the absolute bare reasonable minimum of infrastructure as cheap as possible, but with scaling paths laid bare if needed ever. sometimes a few lambdas/workers+CDN solve problems for essentially zero cost, sometimes people are amazed how far a single VPS can carry them nowadays. Or how fast SQLite can be. DevOps is about the art of shipping value to customers as fast as possible, at scale, with minimum cost (but not being the developer itself usually). With continuous improvement loops. But I can count on a single hand how often I actually needed to "scale up" something so hard I needed full on data migrations and all.

Small, sharp tools, my friend.

anonyfox··on Cloudflare Email Service: private beta
Huge fan of Cloudflare here actually. It’s always such a breath of fresh air compared to the heavyweight configuration hells like AWS. And for doing super convenient stuff like make node:http work on cloud functions recently, but guess only certain DevOps guys realize how cool that is compared to other FaaS wrapping ceremonies.

Too bad you don’t hire senior folks in Germany currently, would probably join in a heartbeat for emotional reasons alone. Keep going, lightweight features on a tap and solid reliability over years is exactly what I need and want at least.

anonyfox··on API, Claude.ai, and Console services impacted [resolved]
meanwhile I am amazed by the raw speed of grok in cursor. night and day to claude sonnet, and don't even talk about gpt5
anonyfox··on iPhone Air
also in the thinner camp here, and would gladly have accepted a way worse camera if they made the back uniformly thin actually. the closer we get to the "just a glass plate" thin design from the expanse the better :-)

but yeah, everywhere around all day there is charging options easily even in many public transports here around europe, battery life is simply not a convern anymore for most people at all. the only time i even thin kis when I forgot recharging over night for some reason, but then in the office theres plenty of options to recharge too

anonyfox··on The Claude Code Framework Wars
isn't this textbook "bitter lesson" playing out here again? whatever "frameworks" people try to build, the next generation of models will make them obsolete, no?

---

link: http://www.incompleteideas.net/IncIdeas/BitterLesson.html

anonyfox··on AGENTS.md – Open format for guiding coding agents
Currently I am building a new JS web toolkit on the side with AI assistance for faster progress, and I came to have some prompts folder in the project root that I just drop into the agents (like cursor CMD+I) and point it to a direction (file/folder).

https://github.com/Anonyfox/raven-js/tree/main/prompts

I think we should not split README and AGENT into different documents - the way its heading is that the coding agents are optimized to "act as" humans and use tools like them more and more - and understanding how something works or how to do something should be aimed for humans and expecting AI tools to pick it up like a human would... if they don't currently then probably they will in the the future.

anonyfox··on The value of hitting the HN front page
Same here. And same day from posting to interviewing even.
anonyfox··on Ask HN: Who wants to be hired? (June 2025)
Location: Hamburg, Germany

Remote: yes when timezone is reasonable

Willing to relocate: no

Technologies: Rust, Go, Elixir, JS/TS, Cloud stuff, AI/ML/Math, ...

Résumé/CV: https://anonyfox.com/cv

Email: max@anonyfox.com

—-

Either Fullstack (senior/…/principlal), DevOps, Architect, or Team Lead/CTO, whatever - I grew up with having to do all the roles back in the day, from Startup Growth Hacking over Scale-Up Optimization to Enterprise Executive. Preferrably doing something _real_, not another purely digital product/service or crypto stuff. Connection to something physical I could touch, that also has a future.

anonyfox··on Sync Engines Are the Future
In Elixir/Erlang thats quite common I think, at least I do this for when performance matters. Put the specific subset of commonly used data into a ETS table (= in memory cache, allowing concurrent reads) and have a GenServer (who owns that table) listen to certain database change events to update the data in the table as needed.

Helps a lot with high read situations and takes considerable load off the database with probably 1 hour of coding effort if you know what you're doing.

anonyfox··on How close is AI to human-level intelligence?
thats the jackpot question I think.

personally I am leaning towards yes, the human mind is nothing magical here, just more advanced wetware.

← PreviousPage 3 of 24Next →