I'm the founder / indie developer behind namesuppressed. I make Photoshop plug-ins & desktop apps (occasionally mobile apps), and sometimes do freelance work.
I also run IndieConference.com: a free curated email newsletter of conferences for indie developers, bootstrappers, indie musicians, digital nomads and other independent / DIY folks. It's been on hiatus since the pandemic though, it kinda killed off conferences.
Basically I love making products & being a solo developer.
I'm pro-AI but anti-slop, an active Claude Code Max user. I occasionally dabble with other models but keep coming back to Claude. Opus 4.5 is an inflection point.
I'm Australian & live in Perth. Pre-pandemic I used to travel between Sydney & Melbourne, and to Berlin & Malmo when I had the opportunity. In 2025 I got to spend a few months in upstate New York. I hope eventually I can travel again soon.
I don't use Hacker News much anymore. Maybe I'm too old for it now, I find myself rolling my eyes at many of the comments here.
If you've found this profile, feel free to email me. I'm happy to help HN people and I do try to reply to everyone when I can.
Email: syneryder AT namesuppressed DOT com
Personal Site: https://kohanikin.com
Company Site: https://www.namesuppressed.com/
Indie Conference: https://www.indieconference.com/
BlueSky: https://bsky.app/profile/syneryder.bsky.social
Twitter (rarely used): @syneryder
> ... make it a lot more expensive to use for multi-turn coding than many would assume from the $2/$6 headline numbers they led with.
There's a further sting in the tail, Grok 4.5 is only $2/$6 for the first 200k of context. Go above that, and the pricing is $6 / $12 - and you're still capped at only 500k context anyway.
Similar story here. They took my ~$100/yr Harvest time-tracking Solo plan, increased the price by 2.5x for a more restricted plan than I had... or I could get back the plan I had for $20,000/year.
So I downloaded my data, and had Claude vibecode a fully-featured clone in a single evening. Even if I was paying Anthropic API rates, it cost me less than a single year of my Solo plan.
People have already been using ChatGPT to design custom bespoke mRNA vaccines specifically for one patient, based on sequencing their specific cancer. It already works to reduce tumours. Sam and Dario know this, it's why they can make their claims - it's already done. The problem is the cost of the procedure (which is why only rich entrepreneurs are seeing their cancers treated this way so far) and government regulations preventing its use in wider human populations without a 10 year study first.
Wow, this was worth watching more than I expected it to be. Not because of anything Karp is saying - okay, so Palantir thinks they're going to make their own frontier model by fine tuning Nemotron, good luck with that.
Watch the body language. Hear the tone of voice. He's scared. He's not arguing from a position of strength.
I find the implications that follow from that fascinating. I'll let others draw their own conclusions though.
I did a quick look for 200k models on OpenRouter. There's a lot of previous-gen Minimax 2.5 & 2.7, GLM 5.1 that are around 200k.
But also on the list at 200k are "Free Models Router" and "Claude Haiku 4.5". I would not recommend making any judgment of AI based on free models. And coding with Haiku is a bad idea... I mean, that was my first code AI test too, but it's just not an accurate impression.
To be fair, Opus 4.1 & 4.5 are also listed as 200k. They did require context management for large & difficult tasks. But if you do have access to Opus, there's very little reason not to switch to 4.8 / Sonnet 1 Million now. I wouldn't recommend Sonnet, but I have used it to write a USB audio driver that got some hardware working on an obscure OS, so it can work.
>Problem 3: "you'll hit the 200k token limit..." ... Suggestion: use 1 million context window LLMs.
Yes, if the model someone is using only has 200k token limit, that would immediately suggest to me that it really isn't a sophisticated enough model.
Most of my coding sessions end up being about 350k tokens long when I finish, it wouldn't even fit in a 200k context. And that isn't counting the cache-reads by subagents, etc.
It's worth spending some time with the best Opus / GPT model, to at least get a sense of what the frontier is like.
Thank you, I haven't heard of Cortecs before. Might see if I can integrate this into my harness, or at least wire up Tensorix.
Also, I don't know how accurate that tokens/per/second measure for GLM 5.2 is, but if that is even remotely true, then I won't complain about the mild markup Tensorix have for GLM ;) Thank you for the heads-up!
It's because GLM 5.2 is offered on many inference providers, including providers in the US. Those companies only make their money by charging for inference, and yet they seem to be doing quite well while charging the exact same prices as Z.AI / GLM.
In fact, there's a price war where some of the US inference providers are undercutting the pricing of Z.AI's own GLM hosting. Novita & AtlasCloud are both offering 8% and 5% discounts on GLM 5.2 respectively. GMICloud is charging 30% less - but getting so hammered with demand that it only has 80% uptime & 7 tokens per second, so you get what you pay for.
You can find a list of providers & their pricing through OpenRouter here:
I do agree in cases where I'm using API and not the subscription, this would be very costly via API. Not sure why the tokens wouldn't be in the cache though? Seems everything should be cached as long as I'm within the 1 hour caching window? If I'm wrong about how token caching works, I'm eager to learn!
My other concern is, it isn't really a 1 Million context window if we can only use the first 500k, right? But now that I've found that I can re-enable it, I'm happy.
I've previously had sessions go to 700k tokens and still be okay, though it does start drifting at that 700k point. I'm regularly at 300k with no problem.
Not only that, but using Opus 4.8 [1m] right now outside the US, and suddenly I only have a 500k context window. I really hope this is just a strange Claude Code bug, but I had access to a 1 Million window before, and it wouldn't entirely surprise me if context window length becomes another US export restriction.
The Anthropic page here seems to say that Max users should have access to the full 1 Million window for 4.8:
I was already setting up my infra to experiment with GLM 5.2 and its 1 Million token window before this happened. I think I'm glad I did.
EDIT: Found a solution, seems Claude Code 2.1.193 (or an earlier version I didn't notice) changed default settings, so that if you have Autocompact turned on it occurs at 50% of the context window. If you turn off Autocompact, the full 1 Million context window is restored. Another example of Claude Code quietly changing default settings sigh
> There is probably a market for Deepseek/GLM served from non CCP available servers. I might even look into how hard that would be to setup here.
Please do. There is definitely a market for Deepseek / GLM hosted from non-China servers, there's over 20 providers for GLM 5.2 on OpenRouter alone... and they're all either Singapore (home of Z.AI / GLM), China, or US. There is nothing yet listed on OpenRouter from Europe (Inceptron still only has GLM 5.1). And of course, there is absolutely nothing hosted in Australia.
We're in a particularly dire situation in Australia. We're about to be cut off from Claude Fable and premium American models. The European Mistral models are garbage, at least in comparison to US models. Our only hope is going to be Chinese models (GLM 5.2 is good), and we're not even hosting them in Australia.
By the way, if you haven't tried an Anthropic model, it's worth spending at least $20 one month to give Opus 4.8 a try. I only got one night of access to Fable before I was cut off, but one single evening of Fable provided plans that I've been working through for about a week afterwards with Opus 4.8... and that was only Fable, not even Mythos. That's the kind of intelligence lead Australia is about to be cut off from.
(And kudos on the Containers For Change, that's something I do as well - mostly as an exercise incentive to walk to the local recycling machine, because the money certainly doesn't compensate for the time spent on the recycling.)
> The script ended up outputing code that uses variables outside of their scope, didn't utilize like 90% of the features of the language
Using variables outside of their scope sounds very unusual to me for Claude. You are using Claude Opus (4.5 or higher) and have set the thinking to High or above, right? Make sure you're not using Claude Haiku. Sonnet can be okay, but I'm sure the developers you've heard raving about it are all using Opus 4.8 or GPT 5.5, and all using it from within Claude Code or Codex (or OpenCode or Pi, tools like that anyway).
Claude should catch something like variables being outside of scope immediately when compiling, and fix it as soon as it notices the compiler bug.
> The script itself was also written in really weird way, utilizing recursion for pretty much everything when most of what it did could be done in simple loops...
That's actually a great opportunity to develop a new prompt to give to Claude. AI is really good at pattern matching. Take one of those weird recursion methods Claude came up with, then rewrite it as that simple loop that you would prefer, and show both to Claude. Then ask in the same turn: "This is how I prefer to write this code. Can you suggest a prompt to me that would encourage you to write this style of code instead in future?"
See if you can get Claude to reduce that down to a simple maxim or principal you can include in a startup prompt you provide at the start of each session, or into your global CLAUDE.md file that is loaded at the start of every Claude Code session. It might end up being a guideline like "Prefer simple loops over recursion whenever appropriate."
It's possible that the developers you've heard raving about AI have already developed startup prompts / CLAUDE.md files filled with similar maxims & principals, tailored specifically to how they like to code & work, evolved from months of working with AI.
I've had success with vision models & OCR, saved me many hours / days / weeks of typing work.
Last year I finally OCR'd many hundreds of pages of my father's old writings. I found that feeding it to Claude Sonnet 4.x via API gave me results that were perfect. No corrections required. So perfect, that Claude was reading along with the story, and actually pointed out a continuity error in the story where an incorrect character was reciting dialog. Claude asked if it should transcribe exactly as is or if I would like Claude to correct the continuity error.
Claude also correctly OCR'd some handwriting that was in the margins of the documents. Sonnet came very close to transcribing a Word Sleuth puzzle, but that was where I hit the limits of its capability at the time.
Mistral OCR was also good (and actually what I started with), but it wasn't quite as good as Claude. And when it was wrong, Mistral could be frighteningly wrong - one API call must have failed, the model must have been presented with a pure black / null image, and I got back a "transcription" that described neverending darkness. It read like something the Woodsman would have broadcast in Twin Peaks S3E8. That poor model.
Tables from electronics datasheets might be okay, I think I've had success with OCR of technical manuals with tables for 80s synthesizer hardware. But I admit my use cases don't crossover into transcriptions of equations or graphs.
Not behind Tor here, but I just got a "406 Not Acceptable" with "Your browser is not supported". I'm running Firefox here, but on an older machine with an ESR v115 release. Does your site use particular functionality not supported in older Firefox?
Aside from that - as for parent poster's story about needing to register a company, perhaps they are living in a particularly onerous jurisdiction. But more generally, many jurisdictions allow you to be a Sole Trader with fairly minimal registration. Filing taxes - well, hopefully you do that already, and adding your Sole Trader income is likely not that much work on top. (Selling overseas and dealing with overseas taxes? There's often companies that will handle all the overseas taxes on your behalf, and they might only take 10% or less of the sale with no upfront cost as payment.)
If you're not sure about this stuff, see if your city has a Small Business Development Center where you can ask their advice. This stuff is probably all online, and if not they might have leaflets & books on what you need to know. Places like that will often have open hours with someone from the Tax Office as well where you can ask your questions.
Especially, don't put up walls for yourself that weren't already there. This stuff really may not be as complicated as you think.
Upstate New York has a site for testing and reporting / tracking. Costs are $80 USD for a comprehensive test though. It looks like they'll test just for Lyme for $20, but if you found a tick on you I imagine you'll want to know all the diseases it has potentially given you. At least I did.
That's strange to me that you mention London as being similar to Glasgow. I've not had the chance to visit either, but my go-to on this topic has always been this faux news story on the Mash Report:
OpenRouter has a list of providers, looks like NovitaAI would meet those criteria. Though not for $50/mth for 80/M tokens, which I assume is the Z.ai subscription pricing.
I think it's out now - or do you mean as part of the Zen subscription?
The API GLM 5.2 launched last night with several providers on OpenRouter. I had a short conversation, didn't get to test much, but initial impressions "the vibes were good".
I also run IndieConference.com: a free curated email newsletter of conferences for indie developers, bootstrappers, indie musicians, digital nomads and other independent / DIY folks. It's been on hiatus since the pandemic though, it kinda killed off conferences.
Basically I love making products & being a solo developer.
I'm pro-AI but anti-slop, an active Claude Code Max user. I occasionally dabble with other models but keep coming back to Claude. Opus 4.5 is an inflection point.
I'm Australian & live in Perth. Pre-pandemic I used to travel between Sydney & Melbourne, and to Berlin & Malmo when I had the opportunity. In 2025 I got to spend a few months in upstate New York. I hope eventually I can travel again soon.
I don't use Hacker News much anymore. Maybe I'm too old for it now, I find myself rolling my eyes at many of the comments here.
If you've found this profile, feel free to email me. I'm happy to help HN people and I do try to reply to everyone when I can.
Email: syneryder AT namesuppressed DOT com
Personal Site: https://kohanikin.com Company Site: https://www.namesuppressed.com/ Indie Conference: https://www.indieconference.com/ BlueSky: https://bsky.app/profile/syneryder.bsky.social Twitter (rarely used): @syneryder