Hacker News: disiplus

New comment by disiplus in "ChatGPT Desktop (Codex Desktop) for Linux"

disiplus — Thu, 13 Aug 2026 13:25:06 +0000

You don't care what were you trying to build but for a quick me alone Linux app I used Flutter. Honestly it's my go-to when I want to have a quick native app on any platform but dont want to bundle electron.

New comment by disiplus in "France to ban unsolicited telemarketing calls"

disiplus — Tue, 11 Aug 2026 13:02:54 +0000

It's not that they don't care, it's just that the protocol behind it was never designed for it.

Compared for example to email where when you want to send email to somebody, you discover its MX settings on the DNS level and then send it directly and the receiver can verify are you allowed to send those emails. With phone calls it's basically a network of interconnects so I'm sending the call directly to my provider but that provider to reach the destination has multiple steps and they have to trust each other with the numbers signalling. Compare it to a regular snail mail where everybody can write anything as a sender.

What most of the providers are switching to now is for enduser the case is if the phone number that you want to signal is not registered with us, you are not allowed to signal it. Which is fine and covers most of the cases but imagine that you are a business and have multiple providers And you have boughta number block with one provider and another one is offering you better minute price for outgoing calls. Or you want to have a forwarding to your cell phone number. Or you want to signal your number when you're calling prospects from CRM. The regulation usuall differs from country to country, but most allow you to signal any number that you own with any provider that you use. And this is correct, but the problem is verification.

New comment by disiplus in "Kimi Work"

disiplus — Tue, 21 Jul 2026 11:18:39 +0000

They all are pretty similar. And if it was copying anything, I would say more inspiration from claude desktop then codex. The Zcode is more like codex.

https://drive.google.com/file/d/1JFfgfMO0nO7HR0WHwEqEEjXIIQj...

New comment by disiplus in "Annoying and alarming things about OpenCode"

disiplus — Mon, 20 Jul 2026 16:04:04 +0000

I found this part funny.

> People familiar with OpenCode internals (if you are on the OpenCode dev team I assume this doesn’t include you) might have objected to my python3 example above.

New comment by disiplus in "Annoying and alarming things about OpenCode"

disiplus — Mon, 20 Jul 2026 14:09:51 +0000

Cache Misses are pretty bad, i have a locally running deepseek v4 flash, i have tuned it now to have 1100-1300 prefill. Its not great but properly useable. Imagine having a session with already 100k and half of it has to be prefilled it would be waiting minutes with worse numbers. And if you are paying by the token, for hosted models, you are wasting money.

New comment by disiplus in "I think Anthropic and OpenAI have found product-market fit"

disiplus — Sun, 31 May 2026 16:30:48 +0000

Which model are you running ?

New comment by disiplus in "The solution might be cancelling my AI subscription"

disiplus — Sun, 31 May 2026 16:24:54 +0000

Diagnosed with ADHD, ultimately does not change anything for me even through i had the same idea as you. Reason is that i can now start even more stuff in parallel. And some part of them get finished more before i can just prompt more when in focus, but instead of finishing i add more features.

New comment by disiplus in "I think Anthropic and OpenAI have found product-market fit"

disiplus — Wed, 27 May 2026 20:31:07 +0000

same, but you need more then 100k of hw to run something like kimi k2.6 for a bigger team. on the other hand there is a ds4 flash that you can run on a macbook with 128gb ram. an that one is perfectly usable for a lot of tasks.

https://github.com/antirez/ds4

New comment by disiplus in "Agents can now create Cloudflare accounts, buy domains, and deploy"

disiplus — Wed, 06 May 2026 10:13:36 +0000

The problem is not website, the problem is discovery and discovery is on Instagram, TikTok, and social networks. You don't have any incentive to build a website for a regular audience. What you might do is build an audience on a social network and then try to move them to a website.

But at that point you're big enough to build it properly.

New comment by disiplus in "Accelerating Gemma 4: faster inference with multi-token prediction drafters"

disiplus — Tue, 05 May 2026 17:31:16 +0000

depends, a super small one finetuned to do function calling instead sending it to big model and waiting, instead, you ask for a revenue in last month, i do a small llm function call -> show results. some bigger ones, analysis, summary, classification. what is great with smaller ones, and im looking at 2b, 4b is you can get a huge throughput with just vllm and a couple of consumer gpus. what i usually do is basically distillation of a big one onto smaller one.

New comment by disiplus in "Accelerating Gemma 4: faster inference with multi-token prediction drafters"

disiplus — Tue, 05 May 2026 17:02:13 +0000

i dont know what are you talking about, i replaced an older gpt4o with a finetuned qwen. there is a huge amount of "AI, that can be done with those models, or partly by those models." Huge amount of people would not notice the difference. And if you prepare the context correctly, even bigger slice of people would not notice.

New comment by disiplus in "Accelerating Gemma 4: faster inference with multi-token prediction drafters"

disiplus — Tue, 05 May 2026 16:54:27 +0000

nice, will run it later agains qwen3.6 27b, the speed was one of the reasons why in was running qwen and not gemma. the difference was big, there is some magic that happpens when you have more then 100tps.

New comment by disiplus in "DeepSeek v4"

disiplus — Fri, 24 Apr 2026 05:06:19 +0000

Depends how many users you have and what is "production grade" for you but like 500k gets you a 8x B200 machine.

New comment by disiplus in "Kimi K2.6: Advancing open-source coding"

disiplus — Mon, 20 Apr 2026 20:40:05 +0000

was part of the beta, its properly good model, in some sense i forgot that im not on opus or gpt. opus is still better. gpt is the one struggling for me. it has some niche in backend work but you can get the same with opus with skills, its lacking in almost all others.

New comment by disiplus in "ChatGPT Pro now starts at $100/month"

disiplus — Thu, 09 Apr 2026 18:42:32 +0000

It looks like its called prolite.

https://snipboard.io/jmGKfM.jpg

New comment by disiplus in "I've sold out"

disiplus — Wed, 08 Apr 2026 10:53:43 +0000

yet

New comment by disiplus in "GLM-5.1: Towards Long-Horizon Tasks"

disiplus — Tue, 07 Apr 2026 19:18:09 +0000

i have glm and kimi. kimi was in most of the cases better and my replacement for claude when i run out of tokens. Now im finding myself using glm more then kimi. Its funny that glm vs kimi, is like codex vs claude. Where glm and codex are better for backend and kimi and claude more for frontend.

as kimi did a huge amount of claude distilation it seems to be somewhat based in data

https://www.anthropic.com/news/detecting-and-preventing-dist...

New comment by disiplus in "GLM-5.1: Towards Long-Horizon Tasks"

disiplus — Tue, 07 Apr 2026 19:13:55 +0000

Yeah it seems they did not align it to much, at least for now. Yesterday it helped me bypass the bot detection on a local marketplace. that i wanted to scrap some listing for my personal alerting system. Al the others failed but glm5.1 found a set of parameters and tweaks how to make my browser in container not be detected.

New comment by disiplus in "GLM-5.1: Towards Long-Horizon Tasks"

disiplus — Tue, 07 Apr 2026 19:08:51 +0000

basically my expirience as well. Sometimes it can break past 100k and be ok, but mostly it breaks down.

New comment by disiplus in "GLM-5.1: Towards Long-Horizon Tasks"

disiplus — Tue, 07 Apr 2026 18:15:07 +0000

When it works and its not slow it can impress. Like yesterday it solved something that kimi k2.5 could not. and kimi was best open source model for me. But it still slow sometimes. I have z.ai and kimi subscription when i run out of tokens for claude (max) and codex(plus).

i have a feeling its nearing opus 4.5 level if they could fix it getting crazy after like 100k tokens.