HNHacker News
TopNewBestAskShowJobs

apetresc

5,902 karma · joined March 30, 2010

[ my public key: https://keybase.io/apetresc; my proof: https://keybase.io/apetresc/sigs/YlA9ZbsGbGbQQt7Ib8XYtagd6gFtbJZRe5qpXR4TMbY ]

---

meet.hn/city/43.4652699,-80.5222961/Waterloo

Socials: - github.com/apetresc - mastodon:fosstodon.org/@apetresc

Interests: Books, Education, Open Source, Programming

---

submissionscomments
apetresc··on Woxi: Wolfram Mathematica Reimplementation in Rust
What percentage of the overall code was written primarily by agents?
apetresc··on Show HN: Echo, an iOS SSH+mosh client built on Ghostty
Amazing-looking UX. My biggest feature suggestion: implement support for SSH jump hosts. I suspect having a single SSH gateway in your homelab that you configure all other hosts with ProxyJump in .ssh/config is a super-common setup amongst your target audience.
apetresc··on Osaka: Kansai Airport proud to have never lost single piece of luggage (2024)
Why would a knife be a problem in a checked bag, even if it hadn't been sealed in the original package?
apetresc··on Discord Alternatives, Ranked
Yes, Discord will obviously never lose its network effect edge and get supplanted. That's simply what always happens with network effects.

Now excuse me while I go post to my Facebook about my new MSN Messenger and ICQ addresses.

apetresc··on GPT-5.3-Codex
Which model, 5.3 or 5.3-Codex? Yes, 5.3-Codex was announced and released. 5.3 wasn't announced. None of it is "absurd", and it also wouldn't have been "absurd" if they announce something but don't release it that same day (which they didn't do, but if they had - what exactly is absurd about that? Companies make announcements about future releases ALL the time.)
apetresc··on My AI Adoption Journey
Honest question, when was the last time you caught it trying to use a command that was going to "nuke your system"?
apetresc··on GPT-5.3-Codex
I mean… yeah? It sounds biased or whatever, but if you actually experience all the frontier models for yourself, the conclusion that Opus just has something the others don’t is inescapable.
apetresc··on GPT-5.3-Codex
Scott Alexander essentially provided editing and promotion for AI 2027 (and did a great job of it, I might add). Are you unaware of the actual researchers behind the forecasting/modelling work behind it, and you thought it was actually all done by a blogger? Or are you just being dismissive for fun?
apetresc··on GPT-5.3-Codex
Why is it absurd?
apetresc··on Claude Opus 4.6
Impressive that they publish and acknowledge the (tiny, but existent) drop in performance on SWE-Bench Verified between Opus 4.5 to 4.6. Obviously such a small drop in a single benchmark is not that meaningful, especially if it doesn't test the specific focus areas of this release (which seem to be focused around managing larger context).

But considering how SWE-Bench Verified seems to be the tech press' favourite benchmark to cite, it's surprising that they didn't try to confound the inevitable "Opus 4.6 Releases With Disappointing 0.1% DROP on SWE-Bench Verified" headlines.

apetresc··on Claude Opus 4.6
I literally came to HN to check if a thread was already up because I noticed my CC instance suddenly said "Opus 4.6".
apetresc··on OpenClaw is what Apple intelligence should have been
It depends on whether you're running the models locally. If you're just using a Claude or OpenAI token (as probably 95%+ of OpenClaw users are), the RAM requirements are minimal. My first-gen M1 Mac Mini runs it just fine.
apetresc··on OpenClaw is everywhere all at once, and a disaster waiting to happen
Would you mind telling me which model and version you’re using and what authentication mechanism? Is it piggybacking your Max/Pro subscription or did you settle for using pay-as-you-go API costs?
apetresc··on Clawdbot - open source personal AI assistant
I think you're conflating two different things. It's entirely possible (and, I think, quite likely) that AI is simultaneously not anthropomorphic (and is not ACTUALLY "excited" in the way I thought you were objecting to earlier), but also IS "intelligent" for all intents and purposes. Is it the same type and nature as human intelligence? No, probably not. Does that mean it's "just a flaky integration" and won't have a seismic effect on the economy? I wouldn't bet on it. It's certainly not a foregone conclusion, whichever way it ends up landing.

And I don't think AGI is a "myth." It may or may not be achieved in the near future with current LLM-like techniques, but it's certainly not categorically impossible just because it won't be "sentient".

apetresc··on Clawdbot - open source personal AI assistant
We say that a shell script "is trying to open this file". We say that a flaky integration "doesn't feel like working today". And these are all way less emotive-presenting interactions than a message that literally expresses excitement.

Yes, I know it's not conscious in the same way as a living biological thing is. Yes, we all know you know that too. Nobody is being fooled.

apetresc··on Clawdbot - open source personal AI assistant
It can be absurdly expensive, yes :( It's definitely not in an off-the-shelf plug-and-play state yet. But with the right context/session management (and using a Claude Max subscription token instead of an API key), it can be managed.
apetresc··on Clawdbot - open source personal AI assistant
The phone plan or Clawdbot?
apetresc··on Clawdbot - open source personal AI assistant
I have an old iPhone with a broken screen that I threw an $8/month eSIM onto so that it has its own phone number, that I just keep plugged in with the screen off, on Wifi, in a drawer. It hosts a number of things for me, most importantly bridges for WhatsApp and iMessage. So I can actually give things like Clawdbot their own phone number, their own AppleID, etc. Then I just add them as a contact on my real phone, and voila.
apetresc··on Clawdbot - open source personal AI assistant
I found this HN post because I have a Clawdbot task that scans HN periodically for data gathering purposes and it saw a post about itself and it got excited and decided to WhatsApp me about it.

So that’s where I’m at with Clawdbot.

apetresc··on AI coding assistants are getting worse?
Yeah, that is what I meant. I mean, it's kind of the system administrator's/user's responsibility to run processes in whatever user context they want. I don't wonder why, like, nginx doesn't forcefully switch itself to an nginx user. Obviously if I want nginx to run in some non-privileged context (which I do), then I (or my distro, or my container runtime, or whatever) am responsible for running nginx that way.

Similarly, it's not really claude-code's job to "come with" a claude user. If you want claude code to run as a low-privilege user, then you can already run it as a low-privilege user. The OS has been providing that facility for decades.

apetresc··on AI coding assistants are getting worse?
What's stopping you from `su claude`?
apetresc··on I switched from VSCode to Zed
Because the point is just to loudly proclaim how virtuously anti-AI you are, how disruptive it actually is to your workflow is irrelevant.
apetresc··on Beating myself at chess
Bug report: I got to a late-middlegame position and then the bot crashed because it tried to castle illegally (after its queenside rook had already moved):

``` Uncaught Error: Invalid move: {"from":"e8","to":"c8"} at Chess.move (chess.js:2530:23) at cm-chessboard/:75:23 ```

There didn't seem to be a way to recover besides refreshing.

apetresc··on Trump says Venezuela’s Maduro captured after strikes
This particular quote isn't dementia, he's making a joke, it's the "Donroe Doctrine" because DONald Trump is now expanding it or whatever.
apetresc··on NYC Mayoral Inauguration bans Raspberry Pi and Flipper Zero alongside explosives
Literally not a single prospective RPi customer would have even known Mamdani banned them from his inauguration party if Adafruit hadn't gone out of their way to point it out. And literally not a single one of those prospective customers would have cared, similarly to how nobody cares that "strollers" are also banned.

This is the stupidest thing to get mock-offended by.

apetresc··on GOG is getting acquired by its original co-founder
I'm not sure I understand your figures. What is "32 thousand PLN", surely their entire annual profit for all of 2024 was not literally 32K PLN (approx. 9K USD)? Is this measured in millions? And whatever they're measured in, surely 32K to 910K in the span of a year is considered excellent progress?
apetresc··on Skills Officially Comes to Codex
This seems great and all, but to my surprise the default $plan skill in Codex prefers to writing plan files to ~/.codex/plans. Is this intentional, or an idiosyncrasy of my particular instance of Codex? Every agent tool I've ever seen before puts planning documentation in the repo folder itself, not in a global user directory. Why this weird decision?
apetresc··on Mozilla's new CEO is doubling down on an AI future for Firefox
Didn't the most recent manifest version update for Chrome extensions drop the ability to block ads at the network level? Extensions can still prune them from the DOM but only after the request has finished; something like that, I don't remember clearly.

I'm pretty sure that's what the quote is a reference to.

apetresc··on Ask HN: What Are You Working On? (December 2025)
Bug report: I tried to create a new cafe with a name that contained a space character in it. The form told me the ID was invalid but seems to have created my user account anyway. When I log in now, the CafeID I get is 'undefined'; as in, I am now the proud owner of https://mytinycafe.com/undefined/barista. I'm assuming this is not intended :)
apetresc··on Screenshots from developers: 2002 vs. 2015 (2015)
I completely misread '2015' as '2025' and thought these were from this November rather than November 10 years ago. I couldn't believe so many people were still using what appeared to be Aqua-era OS X.
← PreviousPage 3 of 33Next →