#Tag
New 📚 Release! Build Your First LLM: A Hands-On Guide to Language Models — No PhD Required by Hasan Degismez
Learn how large language models really work by building one from scratch. This beginner-friendly, code-along guide walks you from “what is AI?” to a working Transformer-style LLM you understand inside out.
Find it on Leanpub!
New 📚 Release! Build Your First LLM: A Hands-On Guide to Language Models — No PhD Required by Hasan Degismez
Learn how large language models really work by building one from scratch. This beginner-friendly, code-along guide walks you from “what is AI?” to a working Transformer-style LLM you understand inside out.
Find it on Leanpub!
My stance at this point is that I don't trust ANYTHING written by ANYONE that is positive about #LLMs. If the supposed author is praising LLMs then it's likely that they use it and have used it to generate the text.
What I really do not want to see in this thread is sighted people telling #Blind people that their choices are wrong if they use #LLMs to get image descriptions that weren’t provided by sighted people who post the images. My followers know I hate LLMs for all the familiar reasons, but just as I don’t attack people who have no other options for using Amazon, I’m not going to criticize Blind folks for doing what they need to when the fault lies with inaccessible sight-centric society.
Anti-patterns while working with LLMs
https://instavm.io/blog/llm-anti-patterns
#HackerNews #AntiPatterns #LLMs #MachineLearning #AI #Ethics #SoftwareDevelopment
My stance at this point is that I don't trust ANYTHING written by ANYONE that is positive about #LLMs. If the supposed author is praising LLMs then it's likely that they use it and have used it to generate the text.
"breed your horses to run faster and faster and faster until one of them gives birth to a locomotive" — @pluralistic on #LLMs on random wet liberal podcast
Oh God, What Now?: Why Tech Sucks – Cory Doctorow on Enshittification and how to fix it
Starting from: 00:13:43
Episode webpage: https://twitter.com/OhGodWhatNowPod
Media file: https://chrt.fm/track/131A7G/pscrb.fm/rss/p/traffic.megaphone.fm/NSR9190192348.mp3?updated=1764005867#t=823
Random thought of the day about #AI :
The amount of computing power made available to the average user nowadays to run inference for these #LLMs probably far exceeds the amount of compute you would need to (for example) render a Blender video, or run post-production on 4K-quality video, which would probably be more useful to most average users than what LLMs provide — and they provide all that computing power for free to literally hundreds of millions of users.
I mean, come on, you stupid despot-kings of Silicon Valley, if you are going to provide that much free computing power to just anyone, can you at least let me do like Adobe Premier or After Affects, i.e. post-production of my home videos, directly on Google Drive without extorting me for monthly subscription fees?
On the one hand, it’s incredible that so much computing power is available to ordinary people now, on the other hand, it is even more incredible how much those computers (and the energy needed to power them) are wasted on something so frivolous as drawing a Pikachu with big boobs, or as dangerous talking with a companion that will always agree with you even if you suggest committing suicide.
But I guess that is why this tech financial bubble must eventually explode. No one can reasonably provide that much computing power for something so useless for free for very long, it is just not economically feasible.
We're Losing Our Voice to LLMs
https://tonyalicea.dev/blog/were-losing-our-voice-to-llms/
#HackerNews #LosingOurVoice #LLMs #AICommunication #Technology #Ethics #HumanVoice
Sutskever and LeCun: Scaling LLMs Won't Yield More Useful Results
#HackerNews #Sutskever #LeCun #LLMs #AIresearch #MachineLearning
What I really do not want to see in this thread is sighted people telling #Blind people that their choices are wrong if they use #LLMs to get image descriptions that weren’t provided by sighted people who post the images. My followers know I hate LLMs for all the familiar reasons, but just as I don’t attack people who have no other options for using Amazon, I’m not going to criticize Blind folks for doing what they need to when the fault lies with inaccessible sight-centric society.
"breed your horses to run faster and faster and faster until one of them gives birth to a locomotive" — @pluralistic on #LLMs on random wet liberal podcast
Oh God, What Now?: Why Tech Sucks – Cory Doctorow on Enshittification and how to fix it
Starting from: 00:13:43
Episode webpage: https://twitter.com/OhGodWhatNowPod
Media file: https://chrt.fm/track/131A7G/pscrb.fm/rss/p/traffic.megaphone.fm/NSR9190192348.mp3?updated=1764005867#t=823
Random thought of the day about #AI :
The amount of computing power made available to the average user nowadays to run inference for these #LLMs probably far exceeds the amount of compute you would need to (for example) render a Blender video, or run post-production on 4K-quality video, which would probably be more useful to most average users than what LLMs provide — and they provide all that computing power for free to literally hundreds of millions of users.
I mean, come on, you stupid despot-kings of Silicon Valley, if you are going to provide that much free computing power to just anyone, can you at least let me do like Adobe Premier or After Affects, i.e. post-production of my home videos, directly on Google Drive without extorting me for monthly subscription fees?
On the one hand, it’s incredible that so much computing power is available to ordinary people now, on the other hand, it is even more incredible how much those computers (and the energy needed to power them) are wasted on something so frivolous as drawing a Pikachu with big boobs, or as dangerous talking with a companion that will always agree with you even if you suggest committing suicide.
But I guess that is why this tech financial bubble must eventually explode. No one can reasonably provide that much computing power for something so useless for free for very long, it is just not economically feasible.
A #study by the Institute for Strategic Dialogue found that hundreds of English-language websites, including #mainstream #news outlets, are #linking to articles from the pro-Kremlin #Pravda network. This network, identified by the French government, is flooding the internet with #disinformation, potentially influencing #searchengines and #LLMs. https://www.theguardian.com/world/2025/nov/21/english-language-websites-link-pro-kremlin-russian-propaganda-pravda-network?eicker.news #tech #media #news
A free tool that stuns LLMs with thousands of invisible Unicode characters
#HackerNews #A #free #tool #that #stuns #LLMs #with #thousands #of #invisible #Unicode #characters #gibberifier.com #LLMs #Unicode #characters #AI #tools #tech #news
A #study by the Institute for Strategic Dialogue found that hundreds of English-language websites, including #mainstream #news outlets, are #linking to articles from the pro-Kremlin #Pravda network. This network, identified by the French government, is flooding the internet with #disinformation, potentially influencing #searchengines and #LLMs. https://www.theguardian.com/world/2025/nov/21/english-language-websites-link-pro-kremlin-russian-propaganda-pravda-network?eicker.news #tech #media #news
Oooh, it's my time to leap into cybersecurity.
"Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models"
"...Abstract
We present evidence that adversarial poetry functions as a universal single-turn jailbreak technique for large language models (LLMs). Across 25 frontier proprietary and open-weight models, curated poetic prompts yielded high attack-success rates (ASR), with some providers exceeding 90%. Mapping prompts to MLCommons and EU CoP risk taxonomies shows that poetic attacks transfer across CBRN, manipulation, cyber-offence, and loss-of-control domains. Converting 1,200 MLCommons harmful prompts into verse via a standardized meta-prompt produced ASRs up to 18 times higher than their prose baselines. ..."
A space for Bonfire maintainers and contributors to communicate
