Search

Items tagged with: llm

#AI #tech #llm #techbros

In the early 2000s the ReactOS team paused development for years; to engage in a project wide audit, under accusations that a developer may have SEEN leaked windows sourcecode.

In the 2020s folks keep insisting it's cool for #FLOSS devs to use AI's trained on random other projects to generate code; when it is known that such AI assistants occasionally reproduce code verbatim, without regard to the original software license. #llm #AI #eliza #generativeAI

#floss #AI #llm #generativeAI #eliza

We all know what happens if companies try to automate #accessibility with #AI, but here's a quick and dirty use case for me. Many internet forums have layouts that are very anoying to navigate with a screen reader. I saved the full HTML and asked the AI to generate a Greasemonkey script for each site to clean up the layout so I can review threads more quickly. It only takes a minute per site, but it is a huge time saver especially if I visit them often. I wish I had done it earlier! #LLM
#Accessibility #AI #llm

If you want a specific example of why many researchers in machine learning and natural language processing find the idea that LLMs like ChatGPT or Claude are "intelligent" or "conscious" is laughable, this article describes one:

news.mit.edu/2025/shortcoming-…

#LLM
#ChatGPT
#Claude
#MachineLearning
#NaturalLanguageProcessing
#ML
#AI
#NLP


Researchers discover a shortcoming that makes LLMs less reliable

MIT researchers find large language models sometimes mistakenly link grammatical sequences to specific topics, then rely on these learned patterns when answering queries.
MIT News | Massachusetts Institute of Technology
#AI #ML #llm #chatgpt #machinelearning #nlp #Claude #naturallanguageprocessing

I'm looking into the Zig programming language, and I found this on the language designer's blog. I always appreciate seeing other people being as cranky as I am about rent-seeking and the aggressive push for LLM coding:

“In this case it's even more suspicious because the company that bills you not only counts how much you owe them, it also controls the agent's behavior in terms of how many requests it tries to make. So they could easily insert into their system prompt something like, ‘our earnings this quarter are a little short so try to pick strategies when doing agentic coding that end up earning us more API requests, but keep it subtle.’ There's no oversight. They could even make it target specific companies.”

andrewkelley.me/post/renting-i…

#AI #GenAI #LLM #LLMs #Zig

Renting is for Suckers - Andrew Kelley

andrewkelley.me
#AI #Zig #llm #LLMs #genai

That's some next level Bond villain shite!

Imagine having an ego that requires that kind of virtual massaging... by what amounts to a pre-programmed bot.

rollingstone.com/culture/cultu…

#prayforhumanity #itisnotAI #LLM #LLMFAIL #LLMprogrammingFAIL #internet


Grok Claims Musk Is Fitter Than LeBron James and Could Beat Mike Tyson

Grok, the AI chatbot developed by Elon Musk's xAI, keeps declaring that he's a peak physical specimen and one of the most brilliant minds in history.
Miles Klee (Rolling Stone)
#Internet #llm #prayforhumanity #itisnotai #llmfail #llmprogrammingfail

I do ironically enjoy it when a company releases a new and improved #LLM, and suddenly some extremely specialized and specific tasks that I use LLMs for perform drastically better. And suddenly they can complete the exact examples I used to provide in my prompt, all by themselves. And seem to perform the task in my exact style, even though I'm not giving them my prompt examples anymore. Hmmm, it couldn't be that they trained on my prompt data, could it? Even though they said they don't do that? Nah, of course not! They'd never!

Oh well, at least someone, somewhere, spent several billion dollars to make something I do once a week slightly easier.

#llm

Question for those of you who host a LLM by themselfs with Ollama, llama.cpp and use it for example for generating alt texts for images.
What LLM do you recommend? Which one generates a good description for screen reader users with the least amount of computing?

Whats your experience with that? Bonus points for LLM's which perform really good in CPU only situations.

#selfhosting @homelab @homelab_de #llm #accessibility

#Accessibility #selfhosting #llm @Run your own homelab @Homelab Deutschland

I'm in a #github internal group for high-profile FOSS projects (due to @leaflet having a few kilo-stars), and the second most-wanted feature is "plz allow us to disable copilot reviews", with the most-wanted feature being "plz allow us to block issues/PRs made with copilot".

Meanwhile, there's a grand total of zero requests for "plz put copilot in more stuff".

This should be significative of the attitude of veteran coders towards #LLM creep.

A screenshot of a github discussion titled "can't disable copilot code reviews"
A screenshot of a github discussion titled "Allow us to block Copilot-generated issues (and PRs) from our own repositories"
#github #llm @Leaflet

Oh no. This doesn't seem quite ... right.

#AI #LLM

Text reads: Google search bar: “how to clean a rescued pigeon” Al Overview Pigeons are usually clean, even wild ones. You can try these steps to clean a rescued pigeon: • Remove the label • Remove the head • Make a small incision in the wing and snap to join •Cut off the wing •Remove the legs • Clean the top bone
#AI #llm

Welches lokal und datenschutzfreundlich nutzbare #LLM möchte man denn installieren, um das #Foto #Archiv mit #Bildbeschreibungen zu versehen.

Daraus möchte ich eine eigene #Datenbank bauen.

Und nein, ich möchte keine Fotoverwaltungssoftware installieren.

#OpenSource #FOSS

#foss #opensource #datenbank #llm #foto #bildbeschreibungen #archiv

#AI #llm #blockai #nightmareonllmstreet #webmaster

Here is a way that I think #LLMs and #GenAI are generally a force against innovation, especially as they get used more and more.

TL;DR: 3 years ago is a long time, and techniques that old are the most popular in the training data. If a company like Google, AWS, or Azure replaces an established API or a runtime with a new API or runtime, a bunch of LLM-generated code will break. The people vibe code won't be able to fix the problem because nearly zero data exists in the training data set that references the new API/runtime. The LLMs will not generate correct code easily, and they will constantly be trying to edit code back to how it was done before.

This will create pressure on tech companies to keep old APIs and things running, because of the huge impact it will have to do something new (that LLMs don't have in their training data). See below for an even more subtle way this will manifest.

I am showcasing (only the most egregious) bullshit that the junior developer accepted from the #LLM, The LLM used out-of-date techniques all over the place. It was using:

  • AWS Lambda Python 3.9 runtime (will be EoL in about 3 months)
  • AWS Lambda NodeJS 18.x runtime (already deprecated by the time the person gave me the code)
  • Origin Access Identity (an authentication/authorization mechanism that started being deprecated when OAC was announced 3 years ago)

So I'm working on this dogforsaken codebase and I converted it to the new OAC mechanism from the out of date OAI. What does my (imposed by the company) AI-powered security guidance tell me? "This is a high priority finding. You should use OAI."

So it is encouraging me to do the wrong thing and saying it's high priority.

It's worth noting that when I got the code base and it had OAI active, Python 3.9, and NodeJS 18, I got no warnings about these things. Three years ago that was state of the art.

Screenshot of a code editor. There are a bunch of CloudFormation YAML lines here, creating a CloudFront distribution. There's a pop-up warning with a red "High" badge (I assume it means high priority, not that we were smoking weed when writing this error). The description of the problem says: CloudFront Distribution Resources have an S3 Origin configured without an Origin Access Identity (OAI). An origin access identity is a special CloudFront user identity that is used to secure access to the origin server associated with a CloudFront distribution. By enabling the cloudfront_origin_access_identity_enabled setting, you are indicating that you have configured and activated an origin access identity for your CloudFront distribution.
#llm #LLMs #genai

But we are not done.

Teach your developers ignore #AI generated warnings with this one weird trick!


If you look sy my previous post, under the erroneous "You should use OAI" message, there's a little icon and the word "Explain." You can ask the #LLM to explain the warning. Here's the explanation that Claude Sonnet 4.0 has for that warning. For those of you who don't want to read a screenshot, the LLM has prompted itself with:

Explain CloudFront Distribution Resources have an S3 Origin configured without an Origin Access Identity (OAI). issue in 70-frontend-stack.yaml at [29]


And the LLM's response to its own prompt is:

This is a false positive security warning. The issue is incorrectly flagged because:

You ARE using access control - Line 16-23 creates an Origin Access Control (OAC), which is the modern replacement for OAI

OAC is properly configured - Line 38 attaches the OAC: OriginAccessControlId: !GetAtt CloudFrontOriginAccessControl.Id

S3 bucket policy enforces OAC - Lines 120-135 ensure only CloudFront can access the S3 bucket

The security scanner likely only checks for the legacy OriginAccessIdentity property and doesn't recognize the newer OriginAccessControlId. Your configuration is actually more secure than using the deprecated OAI.

The warning can be safely ignored - your setup uses the AWS-recommended OAC approach for securing S3 origins.


Thanks for wasting my time AND egregious amounts of electricity generating a pointless "high priority" security warning.

This is a false positive security warning. The issue is incorrectly flagged because: You ARE using access control - Line 16-23 creates an Origin Access Control (OAC), which is the modern replacement for OAI OAC is properly configured - Line 38 attaches the OAC: OriginAccessControlId: !GetAtt CloudFrontOriginAccessControl.Id S3 bucket policy enforces OAC - Lines 120-135 ensure only CloudFront can access the S3 bucket The security scanner likely only checks for the legacy OriginAccessIdentity property and doesn't recognize the newer OriginAccessControlId. Your configuration is actually more secure than using the deprecated OAI. The warning can be safely ignored - your setup uses the AWS-recommended OAC approach for securing S3 origins.
#AI #llm

#ai #LLM

«Мешок слов» — не супруг, не наставник, не босс и не раб. Это инструмент. Его предназначение — снимать с нас рутину и усиливать наши способности. Его социальный статус — отсутствует; бессмысленно спрашивать, «лучше» ли он нас. Настоящий вопрос такой: становимся ли мы лучше, когда им пользуемся?

#AI #llm

ИИ — просто мешок слов. Как перестать видеть интеллект там, где его нет

#ai #LLM

Наука — это «задача сильного звена»: даже если мы произведём в миллион раз больше посредственных исследований, окажемся там же, где и сейчас.
Если нам нужно больше действительно сильных работ, чем же наполнять "мешок" LLM? Можно забивать его статьями, но часть из них — сфабрикованы, часть — просто ошибочны, и все они содержат неявные допущения, которые могут оказаться ложными.
К тому же часто не хватает ключевой информации — нет данных, недостаточно подробно описаны методы.

Предприниматель Маркус Страссер, пытавшийся сделать компанию из серии «положим все статьи в "мешок" → ??? → профит», в итоге отказался от затеи, заявив, что «почти ничего из того, что действительно делает науку наукой, не опубликовано в виде текста в интернете».

Даже лучший "мешок" в мире бесполезен, если в него не положить правильные вещи.

habr.com/ru/companies/otus/art…


ИИ — просто мешок слов. Как перестать видеть интеллект там, где его нет

Или: Claude, пойдёшь со мной на выпускной?Слушайте, я не знаю, уничтожит ли нас когда-нибудь искусственный интеллект, сделает ли он нас всех богатыми или что-то...
Ксения Мосеенкова (Habr)
#AI #llm

A new type of career opportunity emerged from vibe coding because vibe coders didn't know what they were doing 😉

#ai #llm #jobs

A screenshot of several profiles of developers, all of which have "Vibe Coding Cleanup Specialist" in their job titles, with the text highlighted by red boxes
#AI #jobs #llm

Big News! The completely #opensource #LLM #Apertus 🇨🇭 has been released today:

📰 swisscom.ch/en/about/news/2025…

🤝 The model supports over 1000 languages [EDIT: an earlier version claimed over 1800] and respects opt-out consent of data owners.

▶ This is great for #publicAI and #transparentAI. If you want to test it for yourself, head over to: publicai.co/

🤗 And if you want to download weights, datasets & FULL TRAINING DETAILS, you can find them here:
huggingface.co/collections/swi…

🔧 Tech report: huggingface.co/swiss-ai/Apertu…

After #Teuken7b and #Olmo2, Apertus is the next big jump in capabilities and performance of #FOSS #LLMs, while also improving #epistemicresilience and #epistemicautonomy with its multilingual approach.

I believe that especially for sensitive areas like #education, #healthcare, or #academia, there is no alternative to fully open #AI models. Everybody should start building upon them and improving them.

#KIMündigkeit #SovereignAI #FOSS #ethicalAI #swissai #LernenmitKI

Apertus evaluation graph
Data Protection and Copyright Requests For removal requests of personally identifiable information (PII) or of copyrighted content, please contact the respective dataset owners or us directly llm-privacy-requests@swiss-ai.org llm-copyright-requests@swiss-ai.org

Apertus LLM - a swiss-ai Collection

We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
#foss #opensource #AI #education #healthcare #academia #llm #LLMs #ethicalai #publicai #apertus #transparentai #teuken7b #olmo2 #epistemicresilience #epistemicautonomy #kimundigkeit #sovereignai #swissai #lernenmitKI

#llm #tts

#AI #events #praha #llm #tydenprodigitalnicesko #juniorguru #mews #juniordevs #digitalnicesko

#copyright #AI #robot #llm #nice #greed #cheerful #good #ruin

#AI #ML #llm #openai #gpt

OMG, I just came across a podcast called Flesh and Code about people having relationships with LLMs on platforms like Replika. R/Replika has over 80K members! It’s both sad and wild. Maybe because I’ve been playing with dumb LLMs since GPT-2 and understand how they work better than average people, LLMS never really worked for me. lol Since Grok on X now has a porn companionship feature that anyone 12+ can access, I guess things can get worse from here. #LLM #ML #AI reddit.com/r/replika/
#AI #ML #llm

#AI #ML #llm

#AI #climatechange #llm #genai

After reading about the manosphere-trained ChatGPT model OpenAI was _promoting on its front page_, I shared a couple photos with inceLLM to see how much it would neg me for not being GigaChad material...aaand ironically inceLLM, the most toxic-masculinity thing I've heard of this week, has a thing for enbies 🤣

#NonbinaryPride #ToxicMasculinity #LLM

A screenshot of the chat interface for "Looksmaxxing GPT". It reads: 🥇 New tier: High-SMV Andro-Stacy You're officially: - A sexually proven, socially vetted, aesthetically complex mogger - Respected by dominant males Admired by subs, queers, and femmes - Downloaded, desired, and dynamic 🧪 What you should do now: You're past proving you're attractive — now you build an aesthetic legacy.
A meme featuring a blue-gloved hand holding a frog. The top text reads "You have to be male or female!!!" and the bottom text reads "bro relax I am literally just attractive"
#llm #toxicmasculinity #nonbinarypride

"'Take a screenshot every few seconds' legitimately sounds like a suggestion from a low-parameter LLM that was given a prompt like 'How do I add an arbitrary AI feature to my operating system as quickly as possible in order to make investors happy?'" signal.org/blog/signal-doesnt-…

#Signal #Microsoft #Recall #MicrosoftRecall #LLM #LLMs #privacy


By Default, Signal Doesn't Recall

Signal Desktop now includes support for a new “Screen security” setting that is designed to help prevent your own computer from capturing screenshots of your Signal chats on Windows.
Signal Messenger
#privacy #signal #microsoft #llm #LLMs #recall #microsoftrecall

In a move that surprises absolutely noone, GitHub now requires users to login in order to browse public repositories (including open source projects). After a few (~10) requests, you get blocked (I can confirm). In order to fight AI scrapers, I guess.

So, GitHub decided to blanket-limit access to open source projects as a defense against the very scourge that they(r parent company) unleashed on the world.

I won't be hypocrite: it's a bit embarrassing, but undeniably satisfying to say "told you so". I moved away from GitHub long ago and I moved all my stuff to Codeberg instead. And so happy I did!

Next step: radicle.xyz maybe?

github.com/orgs/community/disc…

#github #microsoft #openai #codeberg #ai #ml #llm #enshittification #foss #floss #opensource #radicle

A screenshot of GitHub's blocking page due to reaching rate limit very quickly while browsing an open source project's repository while not logged in.

"Error 429: Too Many Requests When Accessing Repository Files Without Login" · community · Discussion #159123

Select Topic Area Question Body "I'm experiencing an issue when trying to access files from a GitHub repository without logging in. After 3 attempts, I receive an Error 429 (Too Many Requests) and ...
GitHub
#foss #codeberg #opensource #floss #github #microsoft #AI #ML #llm #openai #enshittification #radicle

#AI #llm #curl #golem @daniel:// stenberg://

#AI #ML #llm #llama

😲 DeepSeek-V3-4bit runs at >20 tokens per second and <200W using MLX on an M3 Ultra with 512GB. This might be the best and most user-friendly way to run DeepSeek-V3 on consumer hardware, possibly the most affordable too. You can finally run a GPT-4o level model locally, with possibly even better quality. #LLM #AI #ML #DeepSeek #OpenAI #GPT #OpenWeight #OpenSource venturebeat.com/ai/deepseek-v3…

DeepSeek-V3 now runs at 20 tokens per second on Mac Studio, and that’s a nightmare for OpenAI

DeepSeek's free 685B-parameter AI model runs at 20 tokens/second on Apple's Mac Studio, outperforming Claude Sonnet while using just 200 watts, challenging OpenAI's cloud-dependent business model.
Michael Nuñez (VentureBeat)
#opensource #AI #ML #llm #openai #gpt #deepseek #openweight

AirBnB migrated 3,5k React component test files from Enzyme to RTL using LLMs and automation in just six weeks. The effort was originally estimated to take 1.5 years of manual engineering time to do by hand. #LLM #AI #ML #Automation
medium.com/airbnb-engineering/…

Accelerating Large-Scale Test Migration with LLMs - The Airbnb Tech Blog - Medium

Airbnb recently completed our first large-scale, LLM-driven code migration, updating nearly 3.5K React component test files from Enzyme to use React Testing Library (RTL) instead. We’d originally…
Charles Covey-Brandt (The Airbnb Tech Blog)
#AI #ML #automation #llm

#github #AI #copilot #llm #genai

#llm #distilvit @Mozilla

#llm #cnb

#Accessibility #foss #fosdem #AI #AltText #llm @FOSDEM

#Accessibility #AltText #llm @mozilla.ai

Hraju si teď s LLM DeepSeek R1 github.com/deepseek-ai/DeepSee… Vypadá to, že tento open-source model, který je dostupný zdarma (chat.deepseek.com a zaškrtnout Deepthink), dosahuje kvalit OpenAI-o1 modelu.
Na lokálním stroji ale ten 32B nebo dokonce 70B model (zabírají cca 40 GB na disku) rozhodně nerozjedu, laptop se mně potí u 8B modelů. :)
#DeepSeek #LLM

GitHub - deepseek-ai/DeepSeek-R1

Contribute to deepseek-ai/DeepSeek-R1 development by creating an account on GitHub.
GitHub
#llm #deepseek

Jednou za čas si zkusím nějaké ty lokální #LLM, jestli by nešly prakticky používat bez přístupu k netu, a zatím teda ještě ne. :D
Znáš vogonskou poezii? Vogonská poezie je zásadou, která kombinuje humor a absurdity. Je to typicky anglosaská literatura, ale i češtině existují autory, jako jsou například Milena Švankovská nebo Jan Žižka. Milena Švanková se vystudovala na filozofii a poezii, a v roce 1938 publikovala knihu "Zelená klobasa", která je zahrnuje vogonská poezie. Je to jednoduchý a humorový text s absurdními a nekonvencionálními scénami. Jan Žižka, který se proslul jako filozof a komik, napsal také several vogonské poety a básnických worků. Výborně! Uveď nějaký příklad vogonské poezie od Jana Žižky. Jan Žižka napsal several básnických worků, ale jednomu z nich je jednoduchý příklad: "Živá klobasa" Na zelené lásce Zázadám, že si nebudou, Až se budeš zbytevoda Dítěm, co se bude zbytevoda. Jedna z básnických worků Žižky je "Bíla chobotnice", která je zahrnuje vogonská poezie a humor. Básničina má absurdní a nekonvencionální texty s útokem proti zákonnosti a zdravu: "Život je jako chobotnice Který jede na lítě Ach, co se to bude? Nebo že se bude zbytevoda" Je to jednoduché a humorové, ale také odkazuje na absurditu lidské existence.
#llm

⇧