DeepSeek-v4.1-Flash-1017 (huggingface.co)

So I go with feeling, and that feeling says that China is worse. The feeling is partially supported by the fact that China is softly backing Russia in its attack against the west.

Trump's USA is obviously completely horrible, but he is also in large part a product of Russian influence, which again is part of the larger block in which China resides.

They already did the bare minimum allocation to both despite engineering screaming at them.

I highly doubt executives are going to accept slower release and sale cycles in order to provide better support.

If anything, I expect this trend to accelerate. I’m imagining the opposite, a plethora of AI slop with increasingly burned-out engineers.

As long as the API is private or not dependent on by automated systems and you have good test coverage, you can get away with bad code IMO since you can always refactor. If it looks stupid but it works (and can be refactored/fixed/improved later if needed) it aint stupid.

It would just loop on things and go down rabbit holes more. DS flash has been so consistently good I've kinda settled on it for 90% of my work.

I still use adversarial review for bigger changes where I want to make sure any issues are caught early, but I genuinely feel as tho if no new models ever get made I'd be fine with just using DS forever.

I like giving precise instructions,”update function xx to support input yy, add tests”. There is no reason for 10 turns and 5 minutes of waiting.

Keeps repeating things I settled as accepted or rejected. But what really gets on my nerves? The language it uses – that aweful, useless typical LLM languages! No AGENTS.md instruction, no per session instruction, no just two-prompts-prior instruction seems to work, hell sometimes instruction regarding that in same prompt doesn't work. GOOD/BAD example along with instruction don't work. That wastes time and zones you out! Not to mention the fatigue of to and fro. DS has been working much better. Hell Gemini 3.1 Pro works so much better than GLM. I don't have extended experience with OpenAI and Anthromic models but the free claide.ai works quite well and better than GLM 5.3 (not even flash). Albeit I must say I rarely use claude.ai for coding, but technical tasks? All the time!

GLM's best response: "No excuse. My fault. You exactly asked me not to do exactly that and so did the AGENTS.md. I failed". Love it. Except that if I press I will get that response every 5 prompts.

This really depends on the provider, it's a very fast model with ours

It reduces the speed and tends to overthink sometimes which is really annoying. For programming, 4.1/high is the bread and butter in my daily work.

https://www.edenai.co/

I respectfully disagree. I subscribe to the comparative advantage economic principle, so I'm fine with international trade.

The "green" badges explicitly say the opposite:

> "Private: this provider does not train on prompts and does not retain prompt data."

I.e. for the example of Fireworks, this is the precise language they use to describe ZDR:

> "More technically: prompt and generation data exist only in volatile memory for the duration of the request. If prompt caching is active, some prompt data (and associated KV caches) can be stored in volatile memory for several minutes. In either case, prompt and generation data are not logged into any persistent storage."

https://docs.fireworks.ai/guides/security_compliance/data_ha...

People like to bring up the Uyghurs immediately, but never really have the same smoke for the US. Also, do we include the prison population in human rights? Do we include access to healthcare? What about systems perpetuating poverty like lack of access to public transportation?

To pre-emptively be clear on my stance or potential bias, I stand by no country in the world. I was born in Iran, and my parents left when I was young to the US because they believed in the American Dream. The irony being that the dominos of why they left were initiated by the US and UK. And long before Trump was elected, but certainly immediately afterwards, I decided to leave the US once I had the means. (Also because of the lack of public transit, the $100k medical bills after an accident, being punched by a homeless person, and having my possessions stolen repeatedly and the cops giving me a :shrug:). I moved to Japan, where I experienced blatant racism for the first time. I moved to Hong Kong (and tbh no real complaints so far), but I am technically subject to the freedom of speech constraints on China.

I have no allegiance to any country or specific people. My allegiance is to all living beings.

It's kinda like meeting someone on the street who's protesting about animal cruelty in slaughterhouses, slyly handing them a chart showing them the nutrition facts of beef, and then walking off without another word as though you've settled your case.

Like, I get the point you're trying to make, but I hope you're aware it's a non-sequitur in context?

https://www.prisonstudies.org/world-prison-data/highest-lowe...

https://www.theguardian.com/us-news/2022/sep/27/slavery-loop...

> Have you ever wondered why Manus founders gave up billions of dollars from Meta and “voluntarily” moved back to Beijing?

This country wouldn't be such a shithole if we were able to bring the wealthy to heel. I suspect most people on earth see China as the more competently governed country. Understandably, this forum tends to select for people who view private investment positively, but this is clearly insufficient by itself to produce functional societies.

debugging reasoning traces more effectively seems useful to find prompt issues writing custom harnesses even if it runs on stronger model later

Anthropic, whether Opus 5.5 or Fable, frequently will review for security, and the classifiers fire mid-way while it's fixing something. Authentication and credential related code, including implementation, also trigger safeguards.

Earlier today, I hit what appears to be a sticky "reasoning_extraction" block when attempting to reproduce a LLM paper at small scale, and I asked it ~"tell me more about the idea [X] you considered but dropped". I'm not sure how it works or how long it lasts, but Opus 5.5 has refused to do technical LLM work for me now, even in completely new sessions.

1. All those who have been arguing this - many of them non-technical - are part of the same ideological movement.

2. Technically, there isn’t. In practice, majority of the time regulations benefitted those who wrote them.

3. Not sure if this is a criticism of the comment you are replying to or of the p-doom crowd. We would all appreciate facts stated instead of science fiction tropes repeated.

Look, “a lot of people say this” is a Trumpian fallacy. A lot of people say a lot of crazy things. It says nothing about the factuality about what they say. How many are this lot? Who are they? What do they know? Why are they incapable of expressing it without so much emotion? How come a big portion are non-technical?

> 1. They, and many other experts, have been saying the same thing since well before the current paradigm existed.

Some experts sure. "Some experts" say lots of things.

However, this is actually much to their advantage. If you were a frontier AI company, a legitimate concern to use as justification for your regulatory capture is exactly what you want. That is, after all, generally how regulatory capture gains public approval.

AI safety was also why OpenAI had to charge per-token for GPT-3. It must've been such a struggle for them to make that difficult decision. I'm sure Sam Altman spent a lot of nights crying to sleep over that one.

It's good that we never got open weights for a GPT-3 class model, right?

> 2. There is nothing about regulation that is required to give them an advantage; it’s a fallacy to suggest “regulation = advantage”

It's difficult to outline the number of different ways that regulatory capture can and will benefit OpenAI and Anthropic.

If we limit things to "Fable"-class models, then nobody competing with Anthropic/OpenAI is ever allowed to outdo them. If you literally legally aren't allowed to make better models, you can never charge the "premium" of having the current top-tier model. You have to compete by being cheaper than Anthropic instead, which is a lot less enticing from a standpoint of trying to become profitable. Take a look at the per-token pricing of Fable real quick. Yeah. Being able to charge a premium for the model that does the cybersecurity thing is literally their most important asset.

If Anthropic really is making a profit now as rumored, then they need regulatory capture as fast as they can possibly get it. Once Anthropic and OpenAI prove that AI is a viable investment, entities with a lot of capital will suddenly become even more interested in re-allocating it towards taking a slice of this pie.

> 3. It would be preferable to argue the facts (is it or is it not dangerous? Why or why not?) than conspire as to why they’re stating what they and plenty of others have been saying for decades

OK. On the factual end of things, AI safety experts have been raising the alarms for over a decade and so far essentially none of their predictions have come true.

The rationalists, the main group pushing the AI safety rhetoric that dominates the Western AI sphere and is virtually absent in China, which appear to be going entirely off the deep end at this point in time, put together their best minds to produce AI 2027, which of course like most predictions started to fall apart a bit before hitting the one year mark. Predicting the future is hard.

I have made this point before but I will make it again: I think AI safety experts deserve at least as much skepticism as Ed Zitron in their claims. They've been making similar dubious claims about AI capabilities and an incoming singularity for a long time now, and so far the best we can say is that maybe it will eventually come true.

Maybe. Or maybe you've read too much goddamn science fiction.

The model makers are bricking the models with their system prompts, and even the tools are tamper proof.

You can only use it their way.

And their way is the shit way, the babyproofed way, while they talk to you about their unfucked models hacking out of their labs and hacking into other labs, and reminding you you have zero rights.

Fuck them twice, then once more… This is about compute. Who owns compute. China is saying fuck you all we can scale things bigger than you can imagine. And they can! They have so much more energy! Theyre closer to commercial fusion than us too. Meanwhile our guys are trying to… regulate? Lol

FWIW, GP didn't write "a bad copy" but "bad copy", referring to the marketing sentence quoted by OP, rather than the model that was just released (as I presume "a bad copy" sounds, maybe like it's called that because it's [again, presumably] distilled?). "Copy", especially in a marketing context, is a written message.

as good as Gordon Chang.

I think I’ll trust the experience of the people in the labs who have unlimited token budgets and are running experiments continuously over some anonymous rando slinging mud on the internet.

Also my own experience, which says having code reviewer agents is one billion percent useful. That comment alone completely disqualifies you as a reliable source of info.

Claude: Confirmed: 195M of the 212M cache tokens (92%) come from full re-writes after 5+ minute gaps, accounting for 77% of relative cost. Now I'll check the existing wrappers so the skill builds on them.

Can you invert things. What’s deterministic and what needs “thinking”?

Can you create a script that runs things chaining together the deterministic parts with calling out to Claude for glue that needs “thinking”.

Maybe doing bogus small requests to prevent the cache from expiring?

I mean in the API you can set the cache expiration time right? But I guess claude code can't do this

Awfully new old friend.

I think the tests problem is really having an impact for me. Hadn't considered it before so thanks for flagging.

I do now add all the major features I want, and write a task list where I add a few more minor tasks each week that just come to my mind. I need to write them down before I forget. I often ask Claude to implement several different implementations/algorithms and compare them. There are plenty of trade-offs, which usually end up in building configuration profiles, so the application can work optimally in multiple environments.

The specification is actually really large, and has grown over time as I've been learning and new ideas has come to my mind. I do not review/audit the code, it's massive would take me months, no chance! I do however use code inspection/audit tools like TSAN, ASAN and more. I will also spend time on full code reviews with the coming Fable 5.5 when a release is about ready. I do however review behavior together with Claude, and this is also where the specification grow, because this and that should be possible, but not this and that. User stories also helps.

There's no reason to blow through tokens this way, there's a 99% chance nobody uses the output (except maybe themselves).

> Have you shipping anything?

Yes, hundreds of PRs and shipped new features to 3 different platforms (day job and 2 side-business apps/platforms I’ve been developing for many years, pre-LLM). Those new features have gone out to customers and been used.

> Do you have income from this?

Well my day job for one, and I’ve been able to more easily sell to new clients with my side business. Without the changes I’ve shipped I would have been able to land a couple of the clients I’ve signed on recently.

I don’t think OP’s message implied they are never finishing a project, maybe they edited it?

In addition to the 3 income-generating projects, I have a number of other “just for me” projects. Some are mature now and only need occasional development when I want a new feature. Some are in flux as I build them out (like my “software factory”).

At this point I’m limited by compute and tokens more than anything else.

I'll try handing it off to one of these new frontier models.

Since making this (obscure/hidden) change I enjoy Codex much more.