disiplus

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...

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.

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.

Which model are you running ?

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.

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

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.

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.

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.

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.

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

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.

It looks like its called prolite.

https://snipboard.io/jmGKfM.jpg

yet

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...

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.

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

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.

The post mentions, france, germany and nordic nations. France, Holand and nordic nations helped in the early stages of US.

It will also cost openai dearly if they don't communicate clearly, because I for one will internally push to switch from openai (we are on azure actually) to anthropic. Besides that my private account also.

I have them all. They're not just as good. Whoever tells you that looked only at the benchmarks, not real use. They all fall short at some point.

Kimi K2.5 is the best one, but it's still not at the level of what Anthropic released with opus 4.5.

I think in the West we think everything is blocked. But for example, if you book an eSIM, when you visit you already get direct access to Western services because they route it to some other server. Hong Kong is totally different: they basically use WhatsApp and Google Maps, and everything worked when I was there.

Yeah, they're the good guys. I suspect the open source work is mostly advertisements for them to sell consulting and services to enterprises. Otherwise, the work they do doesn't make sense to offer for free.

Even if its a different session it can be enough. But that said i had times where it rewrote tests "because my implementation was now different so the tests needed to be updated" so you have to prompt even that to tell it to not touch the tests.

As a father of two boys, i can give you some feedback. The AI stories you will generate will probably be crap and not worth paying for. What my kids love is when i put them (like i take a picture of them, and then generate them in jungle or whatever setup it is with gemini banana) They want that i print them those out, i know it's temporary but its fun for us all. So you could combine those two things.

Tell that to linkedin group. they keep doing that, they dont credit it, but i assume at least 60% of other people can tell.

thats by design, you know all those huge security implications. now image if it was so easy to setup and install and use.

they are source of data, so they are not fully without value.

This is real, so im a freelancer, i used this small invoicing platfrom to create invoices for my customers. At "work" im working on accounting systems, and erp-s. So with AI, why would i pay monthly for invoicing when i can build it myself. After i day i had invoicing working. Like the simple thing where you get PDF out. Then i started implementing doube-entry booking. And support different tax systems. And then, but we need a sales part then crm, then warehouse. Then projects to track time and so on. And now i have a full saas that i dont need and im not going to waste time on competing in that market. Now im thinking of puting it as open source.

im downloading it as we speek to try to run it on a 32gb 5090 + 128gb ddr5 i will compare it to glm 4.7-flash that was my local model of choice