HackerLangs
TopNewTrendsCommentsPastAskShowJobs

eknkc

4,367 karmajoined 14 anni fa
https://github.com/eknkc

comments

eknkc
·23 ore fa·discuss
Someone here recently said, “Dishonesty is a core value of Anthropic,” and that aligns with my experience of the company as a user. All their talk about AI safety since the company’s inception now feels like pure theater, given their conduct in everyday operations. It’s a shame how quickly their image has deteriorated.
eknkc
·4 giorni fa·discuss
I agree the general premise but do not agree when it comes to browser support.

I feel like we should be building for the 98% or even 95% and force the remaining to upgrade their browsers. I've built for the IE6 - IE11 era for a painful and long time. I do not give a shit if you want to use a 3 year old browser at this point. Go look at a blank screen.
eknkc
·7 giorni fa·discuss
Last year I built a new computer and made sure that I'd not use a single piece of hardware that will require some shit software from the manufacturer.

I'm really happy with my absolutely no RGB, AIO controlled with a pump header boring PC.
eknkc
·26 giorni fa·discuss
I opened the page and prompted it `Which 3d printer is the best`. I mean this is a stupid question but I was looking at some 3d printers so it popped into my mind.

Seeing this log is interesting: https://link.ekin.dev/6RzYGGX7

It came up with a decent response but I guess Opus or GPT 5.5 would do fine anyway. Gotta try it on different stuff. But this feels like it would work great on some situations.
eknkc
·mese scorso·discuss
I was hoping for some kind of a Siri LLM API for providers to implement so that I'd be able to use Gemini, ChatGPT, maybe Openrouter, SELF HOSTED or whatever the fuck I want. Given that Apple itself does not really have a horse in the LLM race, it made sense.

Say the ChatGPT app would provide the functionality to the system and I'd allow a scary popup saying "these guys will own you, sure?".. I guess they are going all in into Gemini instead.

But I don't want Gemini..
eknkc
·mese scorso·discuss
BTW, the openai responses api has a store parameter and a thread id input. Makes it possible to send a thread id and append a new message, ask for completion. So it feels like keeping the conversation going.

Technically it does retrieve the entire history and reevaulate it since the LLM is stateless. Just more ergonomic for the developer.

And prompt caching helps cut the costs down when a conversation drags on.
eknkc
·mese scorso·discuss
Yeah.. Also, after they fucked up the CC, released that 4.7 etc. I switched completely to Codex and honestly do not wish to go back to half assed harness of Claude. Codex somehow got extremely good in a couple of months.
eknkc
·2 mesi fa·discuss
I’ve been driving a Model Y for a year now. Used to have a Volvo with android automotive and before that a Mercedes Benz with the.. I’m not sure whatever that OS is called.

Tesla sw is miles better than the previous two. It is responsive and laid out well. When you get used to it, it is intuitive. Android was not that bad but the visual design was much worse and it was laggy.

The MB software can die in hell. It is the worst piece of shit ever been built by humans. And it is running on hopes and dreams instead of a capable processor. Note that this was an E class so not an entry model. (Even then, there is no excuse)
eknkc
·2 mesi fa·discuss
I've been using the SSH remote editing on Zed too and it works great. No issues whatsoever.
eknkc
·3 mesi fa·discuss
I mean he also invented the fucking JavaScript.

At that rate one needs to abolish all modern technology and go tribal. Cause I’m certain my toothbrush runs JavaScript.
eknkc
·3 mesi fa·discuss
The blog post says they prune them now not to charge you. That’s the change they implemented.
eknkc
·3 mesi fa·discuss
I’m not familiar with the Claude API but OpenAI has an encrypted thking messages option. You get something that you can send back but it is encrypted. Not available on Anthropic?
eknkc
·3 mesi fa·discuss
Not at the moment apparently. They remove the thinking messages when you continue after 1 hour. That was the whole idea of that change. So the LLM gets all your messages, its responses etc but not the thinking parts, why it generated that responses. You get a lobotomised session.
eknkc
·3 mesi fa·discuss
Well anectodally, 5.4 was already better than opus 4.7 so it should not have been hard.
eknkc
·3 mesi fa·discuss
I’ve been using codex cli and GPT 5.4. It is better at coding than Opus anyway. I did not really test Opus 4.7 but older versions generated worse results compared to GPT.

Which I would not even try and test though if Anthropic did not ban my account. The shadiest thing I did was to use it with opencode for a while I think. Never installed claw or used CC tokens somewhere else.

This is a weird company doing weird shit.
eknkc
·3 mesi fa·discuss
This is a completely baffling website but as far as I can tell, the 2.7 WASM thing is the MCP runtime this is marketing? The globe thing is independent of that, just showing there the MCP calls are running.
eknkc
·4 mesi fa·discuss
And also htmlx with htmx I guess?
eknkc
·4 mesi fa·discuss
I thought I hated React until I saw the samples on this page...
eknkc
·4 mesi fa·discuss
I have a desktop computer that I use for gaming so it had windows forever. Lately it started running laggy. Occasional frame drops and stuff. Reinstall, bios update etc nothing helped.

For debugging I installed Bazzite (Linux gaming distro) assuming compatibility would be shit but I can at least test native linux builds of some games to see if there is a hardware issue. The thing runs perfectly. I've been playing propert windows games on Proton with higher / more consistent FPS. It is kind of funny at this point. Granted I do not play any competitive / multiplayer games.

I guess Valve did a great job on the Steam Deck sw.
eknkc
·4 mesi fa·discuss
At least in codex you can configure agents as you wish: https://developers.openai.com/codex/subagents

Might work out fine on codex.