Hacker News: _davide_

New comment by _davide_ in "Claude has the worst pricing – but people want it"

_davide_ — Mon, 06 Jul 2026 20:54:33 +0000

Yep, that's me. the only real blocker is that American companies don't trust Chinese providers, but i could just find a good American provider that hosts DeepSeek and/or GLM. I would at least be able to choose my own agent instead of a quite mediocre one that wastes time and output nonsense verbs in a pathetic attempt to gain sympathy. The only reason that stopped me from doing it is the absence of a subscription, and I did believe I couldn't get the same value with API pricing, but I'm starting to see that it's a blatant lie and true only for anthropic and openai...

New comment by _davide_ in "It's not about physical vs. digital games, it's about ownership"

_davide_ — Mon, 06 Jul 2026 08:16:55 +0000

A simple law: everything the customer buys must always behave *in favor of the customer over anything else*. If the product/service contradicts this, it must be fully stated before the purchase and cannot be updated. <= This would be a sane balance.

New comment by _davide_ in "Claude Fable 5 Promotional Access"

_davide_ — Wed, 01 Jul 2026 20:31:20 +0000

I'm tempted as well, just out of spite

New comment by _davide_ in "Claude Fable 5 Promotional Access"

_davide_ — Wed, 01 Jul 2026 20:29:42 +0000

It isn't a promotion, it's 2x the parameters of opus and we are paying with 2x the consumption rate. They just want to get rid of the subscription model.

New comment by _davide_ in "Claude Fable 5 Promotional Access"

_davide_ — Wed, 01 Jul 2026 20:16:36 +0000

"promotion" like they are doing you a favor just this once out of their goodwill... Really really really pissed me off

New comment by _davide_ in "Can China build its own ASML?"

_davide_ — Sun, 28 Jun 2026 09:32:04 +0000

What a well written article!

New comment by _davide_ in "Stop making swap partitions–use swap files instead"

_davide_ — Fri, 19 Jun 2026 10:10:01 +0000

just buy more RAM, it's cheap enough...

New comment by _davide_ in "AMD Ryzen AI Halo for AI Developers"

_davide_ — Tue, 16 Jun 2026 13:24:36 +0000

the threat is non-existing for agentic flows. Local interfere could catch up on high end phones

New comment by _davide_ in "Feds freaked over Fable 5 after 'fix this code', not jailbreak, say researchers"

_davide_ — Tue, 16 Jun 2026 11:40:20 +0000

Sounds like a good solution my Führer

New comment by _davide_ in "Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?"

_davide_ — Mon, 15 Jun 2026 19:22:13 +0000

you can absolutely use it for some workloads, but as soon as you have some extra complexity for a big repo it'll take forever and the economics are so silly to the point that the electricity bill would be comparable to a subscription. I love having the possibility of running things locally if some random dude decide to pull them plug, and give me solice the fact that i can have 100% private inference, but as the main driver during the day? shoot me

New comment by _davide_ in "Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?"

_davide_ — Mon, 15 Jun 2026 16:55:54 +0000

i used to mix remote and local minimax 2.7(q3) on my strix halo, it run at 30 tg and 220 tokens pp... it was a bit painful slow, but it was a good feeling i could stay offline. unfortunately m3 which is at opus .8 levels is 460b parameters and doesn't even fit in 128gb of memory, let alone a big context. strix halo feels like a toy for ai purposes. https://kyuz0.github.io/amd-strix-halo-toolboxes/

New comment by _davide_ in "Xiaomi MiMo-v2.5 Series API Permanent Price Reduction Up to 99%"

_davide_ — Tue, 09 Jun 2026 07:11:54 +0000

I did develop my own agent around MiniMax. I did see weird behavior when I messed up the loop, like omitting pieces of remove thinking; maybe it's an agent bug, some models/providers just ignore/normalize the broken input, some don't.

New comment by _davide_ in "MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second"

_davide_ — Mon, 08 Jun 2026 20:47:45 +0000

>It's such a weird "Gotcha" that seems to only assume that Chinese LLMs might censor something.

We are not assuming anything; it is illegal, and you will get prison time just for talking about it. Yeah, sure, everyone distorts reality, but there is a huge gap between hiding and enforcing. So yeah, having models respond accordingly is unexpected. There are probably multiple variants tuned differently.

New comment by _davide_ in "Artificial intelligence is not conscious"

_davide_ — Wed, 03 Jun 2026 20:23:18 +0000

Consciousness doesn't exist, it's a vanity concept, to boost human ego...

New comment by _davide_ in "Xiaomi MiMo-v2.5 Series API Permanent Price Reduction Up to 99%"

_davide_ — Wed, 27 May 2026 07:24:36 +0000

I had a subscription before the price was cut down; the model kept randomly looping the with same character (burning 30% of the budget in one shot), and the overall performance for agentic purposes is, simply put, terrible. It finds non-existing bugs and randomly removes chunks of code to fix them, then even presents it as an "extra fix". Maybe it's a good generalistic model; I haven't tested it in that regard.

MiniMax (currently 2.7) which is a ~270B model tuned exclusively for agentic purposes, performs so MUCH better; it's more reliable and cheaper. Both are still far away from Opus 4.7 that I'm using at work. IMO benchmarks are just a very rough estimation; everyone cheats as much as they can get away with. Test the model yourself; do not make any assumptions based on the benchmarks.

I would love to see specialized, cheaper, bleeding-edge models like MiniMax for other non-agentic purposes as well. Why pay $1 for a general model when, for example, you can pay $0.1 for a content-moderator model that you actually need?

New comment by _davide_ in "Xiaomi MiMo-v2.5 Series API Permanent Price Reduction Up to 99%"

_davide_ — Tue, 26 May 2026 19:43:32 +0000

They do want to see the American bubble burst, this is the quickest way

New comment by _davide_ in "Show HN: We made a cinematic heist trailer with 4 AI models for $60"

_davide_ — Tue, 26 May 2026 18:13:41 +0000

100% agree, unwatchable and cheap, it's the most effective way to make sure I'll never touch the product.

New comment by _davide_ in "The limits of Rust, or why you should probably not follow Amazon and Cloudflare"

_davide_ — Thu, 14 May 2026 06:41:51 +0000

Lol, use Gentoo

New comment by _davide_ in "The limits of Rust, or why you should probably not follow Amazon and Cloudflare"

_davide_ — Thu, 14 May 2026 06:19:27 +0000

Except rust is way more productive than any other language out there...

New comment by _davide_ in "I am building a cloud"

_davide_ — Thu, 23 Apr 2026 11:31:45 +0000

Thank you, but no thanks