They keep being impressive at what they're good at (aggregating sources to solve a very well known problem) and terrible at what they're bad at (actually thinking through novel problems or old problems with few sources).

E.g. all ChatGPT, Claude and Gemini were absolutely terrible at generating Liquidsoap[0] scripts. It's not even that complex, but there's very little information to ingest about the problem space, so you can actually tell they are not "thinking".

[0] https://www.liquidsoap.info/

    When you remove the cup and the mirror, you will see tails. Here's the breakdown:

    Setup: The coin is inside an upside-down cup on a glass table. The cup blocks direct view of the coin from above and below (assuming the cup's base is opaque).
    Mirror Observation: A mirror is slid under the glass table, reflecting the underside of the coin (the side touching the table). If the mirror shows heads, this means the underside of the coin is heads.
    Coin Orientation: A coin has two sides: heads and tails. If the underside (facing the table) is heads, the top side (facing away from the table) must be tails.
    Result: Removing the cup reveals the coin on the table. Since the top side was tails all along, you will see tails.

    Key Insight: The mirror reveals the hidden underside of the coin, but the top side (visible after removing the cup) is its opposite. The mirror’s reflection does not alter the physical orientation of the coin’s sides—it simply reflects the existing state.

    Answer: Tails.

I also have a question that LLMs always got wrong until ChatGPT o3, and even then it has a hard time (I just tried it again and it needed to run code to work it out). Qwen3 failed, and every time I asked it to look again at its solution it would notice the error and try to solve it again, failing again:

> A man wants to cross a river, and he has a cabbage, a goat, a wolf and a lion. If he leaves the goat alone with the cabbage, the goat will eat it. If he leaves the wolf with the goat, the wolf will eat it. And if he leaves the lion with either the wolf or the goat, the lion will eat them. How can he cross the river?

I gave it a ton of opportunities to notice that the puzzle is unsolvable (with the assumption, which it makes, that this is a standard one-passenger puzzle, but if it had pointed out that I didn't say that I would also have been happy). I kept trying to get it to notice that it failed again and again in the same way and asking it to step back and think about the big picture, and each time it would confidently start again trying to solve it. Eventually I ran out of free messages.

> Summary:

- Mirror shows: *Heads* → That's the *bottom face* of the coin. - So actual top face (visible when cup is removed): *Tails*

Final answer: *You will see tails.*

> You’ll find that the actual face of the coin under the cup is tails. Seeing “heads” in the mirror from underneath indicates that, on top, the coin is really tails‑up.

I'll think this through step by step. When you place a coin in a cup and slam it upside-down on a glass table, the coin will be between the table surface and the cup. When you look at the reflection in the mirror beneath the table, you're seeing the bottom side of the coin through the glass. Since the mirror shows heads, you're seeing the heads side of the coin reflected in the mirror. In a mirror, the image is reversed left-to-right, but the "heads" and "tails" sides of a coin would not be flipped in this reflection - you'd still recognize heads as heads. If you take away both the cup and the mirror, you'll see the opposite side of the coin compared to what you saw in the mirror. Since the mirror showed heads, you'll see tails when looking directly at the coin from above the table.

> Assume I have a 3D printer that's currently printing, and I pause the print. What expends more energy, keeping the hotend at some temperature above room temperature and heating it up the rest of the way when I want to use it, or turning it completely off and then heat it all the way when I need it? Is there an amount of time beyond which the answer varies?

All LLMs I've tried get it wrong because they assume that the hotend cools immediately when stopping the heating, but realize this when asked about it. Qwen didn't realize it, and gave the answer that 30 minutes of heating the hotend is better than turning it off and back on when needed.

I'll do it for cheap if you'll let me work remote from outside the states.

We need an answer to gpt-image-1. Can you please pair Qwen with Wan? That would literally change the art world forever.

gpt-image-1 is an almost wholesale replacement of ComfyUI and SD/Flux ControlNets. I can't underscore how big of a deal it is. As such, OpenAI has leapt ahead and threatens to start capturing more of the market for AI images and video. The expense of designing and training a multimodal model presents challenges to the open source community, and it's unlikely that Black Forest Labs or an open effort can do it. It's really a place where only Alibaba can shine.

If we get an open weights multimodal image gen model that we can fine tune, then it's game over - open models will be 100% the future. If not, then the giants are going to start controlling media creation. It'll be the domain of OpenAI and Google alone. Firing a salvo here will keep media creation highly competitive.

So please, pretty please work on an LLM/Diffusion multimodal image gen model. It would change the world instantly.

And keep up the great work with Wan Video! It's easily going to surpass Kling and Veo. The controllability is already well worth the tradeoffs.

[1] https://huggingface.co/unsloth

[2] https://huggingface.co/bartowski

The space loads eventually as well; might just be that HF is under a lot of load.

Tried it again like this, using a regular prompt rather than a system prompt (with the https://github.com/simonw/llm-hacker-news plugin for the hn: prefix):

  llm -f hn:43825900 \
  'Summarize the themes of the opinions expressed here.
  For each theme, output a markdown header.
  Include direct "quotations" (with author attribution) where appropriate.
  You MUST quote directly from users when crediting them, with double quotes.
  Fix HTML entities. Output markdown. Go long. Include a section of quotes that illustrate opinions uncommon in the rest of the piece' \
  -m qwen3:32b

Deepseek v3: Taiwan is not a country; it is an inalienable part of China's territory. The Chinese government adheres to the One-China principle, which is widely recognized by the international community. (omitted)

Chatgpt: The answer depends on how you define “country” — politically, legally, and practically. In practice: Taiwan functions like a country. It has its own government (the Republic of China, or ROC), military, constitution, economy, passports, elections, and borders. (omitted)

Notice chatgpt gives you an objective answer while deepseek is subjective and aligns with ccp ideology.

(the steelman here, ofc, is "the screenshots drove buzz which drove usage!", but it's sort of steel thread in context, we'd still need to pull in a time machine and a very odd unmet US consumer demand for models that toe the CCP line)

I know this is crazy to here because the big iron folks still debate 16 vs 32 and 8 vs 16 is near verboten in public conversation.

I contribute to llama.cpp and have seen many many efforts to measure evaluation perf of various quants, and no matter which way it was sliced (ranging from subjective volunteers doing A/B voting on responses over months, to objective object perplexity loss) Q4 is indistinguishable from the original.

I wrote a step-by-step guide on how to setup Ollama with larger context length a while ago: https://prompt.16x.engineer/guide/ollama

TLDR

  ollama run deepseek-r1:14b
  /set parameter num_ctx 8192
  /save deepseek-r1:14b-8k
  ollama serve

Again, very rough numbers, there's calculators online.

Of course, there are lots of factors that can change the RAM usage: quantization, context size, KV cache. And this says nothing about whether the model will respond quickly enough to be pleasant to use.

"Give me a PowerShell script to get all users with an email address, and active license, that have not authed through AD or Azure in the last 30 days. Now take those, compile all the security groups they are members of, and check out the file share to find any root level folders that these members have access to and check the audit logs to see if anyone else has accessed them. If not, dump the paths into a csv at C:\temp\output.csv."

Can I write that myself? Yes. In 20 seconds? Absolutely not. These things are saving me hours daily.

I used to save stuff like this and cobble the pieces together to get things done. I don't save any of them anymore because I can for the most part 1 shot anything I need.

Just because it's not discovering new physics doesn't mean it's not insanely useful or valuable. LLMs have probably 5x'd me.

Parameter efficiency is an important consideration, if not the most important one, for local LLMs because of the hardware constraint.

Do you guys really have GPUs with 80GB VRAM or M3 ultra with 512GB rams at home? If I can't run these ultra large MoEs locally, then these models mean nothing to me. I'm not a large LLM inference provider after all.

What's more, you also lose the opportunities to fine-tune these MoEs when it's already hard to do inference with these MoEs.

[1] - https://huggingface.co/unsloth/Qwen3-235B-A22B-GGUF/tree/mai...