HN user

johndough

1,714 karma
Posts0
Comments504
View on HN
No posts found.
Are AI Labs Pelicanmaxxing? 2 hours ago

Thanks for pointing that out. I haven't noticed any adds in years with Firefox and Ublock Origin extension.

I'll look for a better image host in the future. I guess the economic incentives makes them all turn bad after a while.

0ThreadHN
The Kimi K3 Moment 5 hours ago

I would not put any trust into that AI-generated "research". It does not control for how OpenAI, Anthropic and Moonshot are doing tokenization and token healing, so the results are meaningless.

0ThreadHN
The Kimi K3 Moment 2 days ago

I am not arguing that Kimi did not distill Opus or Sonnet (which they almost certainly have, as opposed to Fable or Sol). I am arguing that even if they did not distill, the model could still identify itself as Opus or Sonnet.

That being said, I'd like to point out a few things:

- The second link (to claude-sonnet-4-2025051) had 17k matches, not just 3k.

- grep.app does not index the entirety of GitHub, so the real number of occurrences of model identifiers is even higher. SourceGraph has a larger index, but the number is so high that it exceeds their result limit of 10k: https://sourcegraph.com/search?q=claude-opus-4-5-20251101&pa...

- 1000 occurrences are already plenty for memorization. Here is a paper that shows over 80% "extractability" with 1000 occurrences for a 6B model. It also shows that extractability scales with model size: https://arxiv.org/pdf/2202.07646

- LLMs have a "mosaic memory", which means that they can combine information from different parts of the training data. https://arxiv.org/pdf/2405.15523 For example, one piece of training data might mention "I am Opus", another might mention "Opus (claude-opus-4-5-20251101)" and another 10000 "claude-opus-4-5-20251101", where the later occurrences strengthen the generation probability of "I am Opus".

- RL can change the model identity easily, so all of the above may not matter at all.

0ThreadHN
Kimi Work 2 days ago

Implementing your own agent is very easy. Here is a minimal agent in 60 lines of Python without dependencies:

https://github.com/99991/MinimalAgent

You only need a single tool to start with. All recent LLMs know how to use bash for reading/writing/editing/executing.

0ThreadHN
Show HN: 18 Words 13 days ago

If an uneducated acquaintance of yours was about to name their newborn child "Adolf", would you interject that this name might not be such a great idea?

0ThreadHN
Qwen 3.6 27B is the sweet spot for local development 23 days ago
    > GLM-5.2 class models already need 1TB+ of RAM.
If you quantize GLM-5.2 to 4 bit, you can do it in less than 500GB: https://huggingface.co/unsloth/GLM-5.2-GGUF (table on the right)

If you find three finds that also have a 128GB MacBook, you can chain them together (the MacBooks, not your friends) and make it work.

You could also run GLM-5.2 on a single MacBook if you stream the active parameters from disk, but even with speculative decoding, you'd probably only get in the order of 1 token per second, so this is not really practical for most applications.

0ThreadHN
GLM-5.2 is a step change for open agents 28 days ago
    > What provider do you use.
OpenRouter with pinned DeepSeek provider or OpenCode Go
    > Why do you trust it with serving full quality?
Quality seems good so far.
    > What harness do you use? Why do you trust it not to have malware (most harnessed are TS apps).
I wrote my own. A minimal harness without dependencies is only 65 lines of Python.
0ThreadHN
Founding a company in Germany: €9600, 152 days and I still can't send an invoice 28 days ago

Its not an issue to adhere with your private money if your product isn't causing damages.

Might happen really easily though. E.g. you install some package which has been compromised, infecting your software product and suddenly all your customer's systems are cryptolocked and you are on the hock for millions of €€€.

Or your db crashes in new and creative ways and your backups don't work for some reason and now your customer lost an expensive contract because critical data that was in your db is gone.

Of course, you can try to foresee every eventuality, but you will indubitably overlook something and probably never make it to market.

0ThreadHN
There is minimal downside to switching to open models 1 month ago

It’s unclear to me what the advantages of openrouter are but it seems to be a default I see many people talking about here.

The advantage of OpenRouter compared to using API providers directly is that you can switch between API providers without binding your money to a single provider.

The advantage of OpenRouter compared to OpenCode Go is that the price for DeepSeek-V4-Pro and MiMo-V2.5-Pro is better on OpenRouter.

For example, DeepSeek costs $0.435/0.87/0.003625 for 1M in/out/cached tokens (https://openrouter.ai/deepseek/deepseek-v4-pro), compared to an equivalent of $1.74/3.48/0.0145 under the OpenCode Go plan (https://opencode.ai/docs/go/#usage-limits), almost exactly 4x.

But since you get a monthly usage limit of $60 with the OpenCode Go plan for $10 (i.e. 6x), you might still come out ahead if you use it a lot (or use other models, where the pricing difference is smaller or non-existent).

0ThreadHN
There is minimal downside to switching to open models 1 month ago

I had a look at eurouter.ai and it seems like an extremely bad offer.

- The prices are ridiculous (15 % markup for free account).

- They have a rate limit of 1000 requests per month, unless you pay 40€ per month for ... what exactly is their value proposition?

- They have a single provider (TensorX) for DeepSeek-V4-Pro, with a cache read cost that is over 100 times higher than DeepSeek ($0.44 vs $0.003625). Notably, I had to look at the TensorX website for that information, since I could not find any information about cached token cost on eurorouter.ai.

0ThreadHN
NSA director: 'Mythos "broke into almost all of our classified systems in hours" 1 month ago

Mythos and other models are not brute-forcing passwords (and with this analogy passwords, ie. systems are the same).

I am not talking about literally bruteforcing passwords (although LLMs are being used for that, too), but bruteforcing passwords and solving verifiable domain tasks have quite a few similarities, especially when considering rule-based and probabilistic bruteforce methods.

We're not talking about dogs, but LLM systems.

Well, clearly dogs are not LLM systems. It is an analogy. If there is an important point on your mind that makes the analogy break down, feel free to spell it out.

Mythos is not exploring entire solution space either.

Yes, but weaker models do not find the solution right away, so they need to try more often. But if they only try the same thing every time, they will never succeed, so we need some kind of guarantee that they try something different every time.

Usually looping is solved by repetition/frequency/presence/n-gram penalties/DRY/min-p sampling, not temperature but we're not talking about small models that have those classes of issues here.

Those might help to reduce looping (at the cost of biasing the generation), but to guarantee that a model can generate all possible generations, we need non-zero probabilities for all tokens, not lower probabilities for likely tokens.

0ThreadHN
NSA director: 'Mythos "broke into almost all of our classified systems in hours" 1 month ago

I don't think that is necessarily true.

- With a weaker model, the time to break into the system might grow so larger that it becomes infeasible, similar to how password hashes can be bruteforced, but if the password is long enough, that is not going to happen in our lifetime.

- There might be problems which are inherently unsolvable with a lower level of intelligence. For example, your dog won't derive calculus from scratch, even if it lived forever.

- LLMs might be biased in such a way that they never explore the entire solution space, no matter how many attempts are made. Some models are notorious for getting stuck in a loop, trying small variations of the same approach every time, even though it is doomed to fail. This can be counteracted somewhat with higher sampling temperature, but that hurts reasoning capabilities.

0ThreadHN
Running local models is good now 1 month ago

I see that OVH offers Qwen3.5-397B-A17B, which is a bit surprising to me. I thought that EU providers had to comply with the AI act where you have to provide opt-out and information about the training data once the model is sufficiently large (over 10^23 FLOPs, likely the case here), but providing information is not possible since people who train those models only give vague information at best.

Does anyone know if OVH is ignoring the law here, or whether it does not apply for some reason?

0ThreadHN
Free SQL→ER diagram tool, runs in the browser, nothing uploaded 1 month ago

Probably not that important in practice. Firefox allows 2^20 - 4 and Chrome allows 2100000 characters. Also, 8000 characters already allows for an unreasonable amount of SQL and could be extended even further with compression. And if that should not be enough, the website already supports JSON exports. All in all, this seems like a worthwhile tradeoff for not having to store anything.

0ThreadHN