you are viewing a single comment's thread
view the rest of the comments
[–] 71 points 11 hours ago* (39 children)

If LLMs can't be made more power efficient, then the technology isn't ready yet for general use. There may have to be fundamental engineering breakthroughs before what these systems do can be more than a very expensive and inefficient worldwide proof of concept.

Of course, the military and the surveillance industry will still want to keep it, even if no one else can afford it, and we'll be the ones paying for it.

  • source
  • parent
  • hideshow 39 child comments
  • [–] 44 points 10 hours ago (21 children)

    They CAN be made more efficient. Hell, AMD just bought a company that translated LLMs to direct silicon... which should enable scalability if it wasn't for one of the key players owning the tech thus limiting its use.

    It's also estimated that some 70% of Claude tokens gets spent on recursive self-correction so the output is higher quality. Instead of bettering the model, Anthropic just keeps throwing money at it to make the problem go away.

    Meanwhile Chinese models - as small as 36-40-80b params - are outdoing these fancy frontier models if the right harness is used.

  • source
  • parent
  • hideshow 21 child comments
  • [–] 28 points 10 hours ago (16 children)

    I've spent the last month or so using nothing but a local 27B Qwen model as my coding assistant and it's working fine. The big American AI companies could all collapse in ruins tomorrow and it's not going to slow things down all that much, anyone who wants to use AI will be able to continue using it. Might even be better in the long run if that happens - the people who are scared of ASI will get their much-demanded temporary slowdown at the frontier while everyone else catches up with open-weight models that everyone can use without central control.

    Pity about the economy in the meantime, I guess.

  • source
  • parent
  • hideshow 16 child comments
  • [–] 22 points 9 hours ago (7 children)

    anyone who wants to use AI will be able to continue using it

    Anyone who's privileged enough to have the hardware.

  • source
  • parent
  • hideshow 7 child comments
  • [–] 9 points 6 hours ago (1 child)

    The kind of specs that would enable local LLM usage were available on laptops since 2020. The floor for acceptable performance for LLMs stopped literally just before 24+gb of VRAM would have become pretty common in consumer applications. The reason this technology isn’t more ubiquitously available is because ‘they’ thought it would be more profitable to hoover up literally every byte of RAM and GPU in the world rather than let the technology continue to naturally evolve to a place where any consumer could have run useful models on their home computers. In other words, your anger is misplaced.

  • source
  • parent
  • hideshow 1 child comment
  • [–] 11 points 9 hours ago

    Open models will still be available via API from third-party hosts. The bigger ones like Kimi K3 or GLM 5.3 don't fit on conventional desktop computers to begin with, most non-institutional users of those would already be doing that (eg via OpenRouter).

  • source
  • parent
  • [–] 4 points 9 hours ago (3 children)

    Anyone who lacks the skill to to it themselves…

  • source
  • parent
  • hideshow 3 child comments
  • [–] 2 points 8 hours ago (2 children)

    There's not much skill to be had there - It is literally just downloading an app nowadays if you do not want to do anything special, especially on Linux (Newelle is great stuff!). But I am sure there are similar packages available for Windows too.

  • source
  • parent
  • hideshow 2 child comments
  • [–] 2 points 4 hours ago (1 child)

    Excuse my ignorance - I don't have much experience with AI to this point - but what does Newelle have that something like Unsloth or LMStudio does not? What makes it great stuff?

  • source
  • parent
  • hideshow 1 child comment
  • [–] 1 point 3 hours ago*

    honestly? ease of use. I like Unsloth too, but Newelle is really an easy solution if you just want to use LLMs on you own hardware (or use inference providers) that requires practically no knowledge at all - it is focused on providing something to use LLMs without anything else interfering.

    Unsloth does well too, but if i hadn't learnt as much as i already did when i started using it, i would probably have been overwhelmed (outside of it crashing pathetically when following symlinks for local model selection - you can define these directories, but the quick selection then just makes it crash)

  • source
  • parent
  • [–] 1 point 4 hours ago (3 children)

    What kind of hardware do you need to run a model like that? And what do you use :-) ?

  • source
  • parent
  • hideshow 3 child comments
  • [–] 5 points 4 hours ago (2 children)

    I run a 5 bit quantized Qwen 3.8 27b at home on a gaming PC with an RX 7900 XTX and RAG memory using Gemma MoE (i forget what one)running on an old 1080 ti on my Valheim server.

    It takes 3-15 minutes to run depending on how many tool calls the model makes and that's mostly memory or web scrapes since that runs on the slower hardware. I mostly just use it as a discord bot to look stuff up for me and to fetch the news.

  • source
  • parent
  • hideshow 2 child comments
  • [–] 2 points 3 hours ago (1 child)

    Sabata, goddess of computing, can I run it on a 32GB system with a 4GB nVidia GPU?

  • source
  • parent
  • hideshow 1 child comment
  • [–] 4 points 2 hours ago

    Probably not, or if it runs it may take hours or days to get a full output. VRAM on the GPU really decides what will run reasonably. Try an 8 billion parameter phone sized model and see if its faster than sending a letter, then keep moving up until your setup can't handle it.

    8B models are a bit too dumb to use any tools reliably but should handle a basic conversation.
    llama cpp will allow you to manually load a model and tweak settings.

    unsloth will give you a basic setup with some tools, manage model downloads, and settings.

  • source
  • parent
  • [–] 2 points 10 hours ago (2 children)

    I'm always running into context limit problems

    Wanted to refactor a too large and hectic hacked together state machine into separate functions and reduce redundancy and increase code readability

    Every model I've tried failed.

    And that should be an easy task an actual AI should be able to handle. Logic is done, just translate to a different structure.
    That should be exactly what they are able to do at least.

    None worked, because the project is just to big and interlinked.

  • source
  • parent
  • hideshow 2 child comments
  • [–] 5 points 8 hours ago* (last edited 4 hours ago)

    More Ram, and break stuff up into smaller pieces. I Have 12Gb of VRAM and 64 Gig System Ram, which - with CPU offloading - allows pretty large models to be used at acceptable speed (although probably not fast enough for someone who wants to make his living with it. But these also will invest in dedicated hardware). And i let a larger model sit there to coordinate, and let it use subagents for the rest. That keeps the Context for the main model a lot more manageable and keeps it on track for a pretty long time.

    How you structure the Task is more important than what the task is at all. For example, i have a huge list of games to be catalogued, and just telling the model to search the web and fill in the blanks in the database makes it crap out pretty soon. But I tell it to let subagents handle everything regarding web search and data extraction and just let them hand back the resulting data. the main model then calls another subagent to sanity check the data and update the database. Each of these subagents do not run for long, and therefor never run out of context, while the main model can keep context size manageable because it does not have to work with "messy" data at all.

  • source
  • parent
  • [–] 11 points 10 hours ago

    I've got 24GB of VRAM, which helps a lot. I'm using the Q4_K_M version of this model, with the KV cache quantized to Q8, and that's able to get me to 128000 tokens of context. I'm using the Qwen Code harness in VS Code.

    If 128000 tokens still isn't enough, break the task down into smaller chunks and help the harness out with MCP tools - I installed Codebase Memory to help it navigate large codebases more efficiently, for example. Ask the coding agent what's causing problems and it may be able to help identify solutions too, I've had it troubleshoot itself several times now and it's been quite good at inspecting its own settings and finding where the problems are with them. I even installed Firecrawl for it so it can do its own web searches.

  • source
  • parent
  • [–] 6 points 9 hours ago* (2 children)

    Is anyone trying to make LLMs with analog computing + memristors? That would make them absurdly efficient

  • source
  • parent
  • hideshow 2 child comments
  • [–] 2 points 10 hours ago

    If you’re talking about the company I think you are, that acquisition by AMD is interesting news.

    The company was the one with a demo AI in their page that was super quick??

    I always figured that was the future of AI when I saw it. Where you’d buy processors with n number of “AI cores” that’d have work/prompts scheduled as needed in the same way we now CPUs and RAM.

  • source
  • parent
  • [–] 10 points 10 hours ago (3 children)

    There may have to be fundamental engineering breakthroughs before what these systems do can be more than a very expensive and inefficient worldwide proof of concept.

    Controversial thought after reading this sentence: It's cryptocoins all over again.

  • source
  • parent
  • hideshow 3 child comments
  • [–] 3 points 10 hours ago (1 child)

    That'd be fine. Cryptocurrency as a whole is still going strong (total market cap is around 3 trillion dollars) and most of the major ones have switched over to energy-free proof-of-stake validation.

  • source
  • parent
  • hideshow 1 child comment
  • [–] 3 points 11 hours ago (4 children)

    If LLMs can’t be made more power efficient, then the technology isn’t ready yet for general use.

    Hm, I don't see the harm in powering local models with solar.

  • source
  • parent
  • hideshow 4 child comments
  • [–] 2 points 6 hours ago

    Well that is an alternative. But I bet each query to a local 27b model takes less energy anyway than the same query to Claude Opus or Fable in some data centre. So it is also a case of improving energy efficiency by running smaller models.

  • source
  • parent
  • [–] 2 points 10 hours ago (2 children)

    Depends. Is it solar energy that started production to power these models? Great! If not, then you're still consuming power and the difference will have to be made somewhere, likely by burning more fossil fuels.

  • source
  • parent
  • hideshow 2 child comments
  • [–] 3 points 9 hours ago (1 child)

    Oh yeah, I mean my own personal solar modules in my backyard. I agree it's not that easy to say "solar exists, checkmate doubters", that would be silly.

  • source
  • parent
  • hideshow 1 child comment
  • [+] -15 points 11 hours ago (7 children)

    But without widespread usage there won't be any breakthroughs... Anti-LLM folk could redirect their attention to the core problem (energy source, wind and solar shouldn't raise any concerns) but they prefer to attack the LLMs themselves. Early implementations of every technology were crazy energy ineffective at the moment when becoming practically useful.

  • source
  • parent
  • hideshow 7 child comments
  • [–] 19 points 11 hours ago (1 child)

    Anti-LLM folk don't just have an issue with energy consumption. There's also the issue of intellectual theft, studies that correlate worsened education with LLM usage, and the tech leadership silencing those issues by corrupting politicians. But I'm sure if they get past that they'll understand how great LLMs are.

  • source
  • parent
  • hideshow 1 child comment
  • [–] 2 points 8 hours ago*

    We understand LLM is great at something but we can never get passed the facts that you've stated and it also isn't great in all thing like we're being sold to and forced to look at everyday. If the tech stay with the professional and not given to the general public, if there's no cunts telling everyone to adapt or get thrown out, if there's no mass disruption toward people's living, i'm sure it would be much more acceptable. The biggest issue with the tech is the cunt parading it.

  • source
  • parent
  • [–] 2 points 11 hours ago* (2 children)

    No one should be arguing if LLMs are useful or worth investing into, they are and it can be a really useful tool, but the rich (seemingly spinless) lizards have managed to skyrocket the price of RAM, pushed global warming to new extrimes and jacked up electricity prices. Oh and while making an AI bubble so big and fradgile, that when (not if) popped will send us back to the great depression! All in the percute of "the next big thing".

    to;dr LLMs are a cool tech but in the percute of it have managed to fuck up a whole bunch

  • source
  • parent
  • hideshow 2 child comments