«This code does not call #curl. This is not a ‹POC› of anything than suggesting you did this with an AI and that you do not understand what you're doing here.» 🍿🍿🍿
## Summary I discovered a critical stack-based buffer overflow vulnerability in cURL's cookie parsing mechanism that can lead to remote code execution. The vulnerability occurs when processing...HackerOne
I have finally moved over to Linux as my primary platform. In many ways it is like coming home, as I loved working on UNIX machines in the past. Of course, I have been using Linux as a secondary OS for a long time, but I finally made the switch. Microsoft cancelling Windows 10 and the direction Windows 11 is going was just too much for me.
@ruario helped the transition, by making it easy for me to work with multiple concurrent @Vivaldi installs.
That is a must for me as I test a lot of builds at the same time.
Nedavno jsem tu nadaval na kulturu faktur v US. Dneska jsem narazil na borce, co nadaval ze za sluzbu vytezovani faktur chteji 5Kc/kus a ze on to radsi da do Gemini a ma to zadarmo.
O hodinu pozdeji psal, ze mu to na fakturach z US davalo celkovou cenu 0Kc ... firma "uplatnila predplaceny kredit jako slevu".
Jsem si vzpomel, jak nam kdysi ucetni nadavala, at to nedelame.
AI revoluce je obcas parodie sama na sebe.
The number one reason for (at least) weekly changes to my site is to update the AI crawler/siphon blockers ... it never stops : there are 97 of them right now 😤
› github.com/ai-robots-txt/ai.ro…
#BlockAI #AI #LLM #NightmareOnLLMStreet #Webmaster
A list of AI agents and robots to block. Contribute to ai-robots-txt/ai.robots.txt development by creating an account on GitHub.GitHub
But we are not done.
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
OriginAccessIdentityproperty and doesn't recognize the newerOriginAccessControlId. 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.
Nvidia’s Rally Faces a Reality Check
Citi’s price cut and rising competition test Nvidia’s dominance. While NVDA still leads AI infrastructure with soaring revenues and strong demand for Blackwell chips, challenges from Broadcom, hyperscalers, and China are real. Long-term strength remains, but it’s no longer a “buy at any cost” stock.
Read full article here:techi.com/nvidia-stock-faces-r…
#Nvidia #NVDA #Stocks #AI #Investing #TechStocks #StockMarket
Nvidia stock faces turbulence after strong earnings, with Citi cutting its target price. Is NVDA still a buy, or has the AI chipmaker’s rally run out of steam? Get the latest analysis.Fatimah Misbah Hussain (TECHi)
K AI pristupuju hodne kriticky a tak jsem rad, ze si muzu do sbirky anekdot pridat success story s AI a vyrobou hodne narocneho kusu kodu.
V nedeli v noci jsme se domluvili, ze Single od Quin spustime v nove podobe UI s custom SnapDrawerem™
Naflakal jsem verzi s AI za 6 hodin cisteho casu (3 hodiny pred deadlinem) a dnes 4 hodiny cistil.
Ve finale jsem spokojeny i s vystupem i s kodem.
Single tu:
unreleased.art/zip
Do SnapDraweru pribude i cool sticky music player!
«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?
ИИ — просто мешок слов. Как перестать видеть интеллект там, где его нет
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…
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)
Canada's National Observor: Whistleblower exposes how AI fuels Big Oil growth
nationalobserver.com/2025/09/0…
#AI #climateemergency #microsoft
"We realized we were basically working for an oil company," said Holly Alpine, a former Microsoft employee who quit her dream job on the company's sustainability team when she realized the company, like most tech companies, is helping fossil fuel com…Canada's National Observer
Well, that was a "productive" Saturday evening! I needed to combine some smart home data and made a mistake by asking the #AI to suggest some approaches. After two hours of going down blind alleys and being misled by the AI with things like old or completely made-up API endpoints, I finally studied the documentation and realised it was not the right path. I then did some old-school thinking and searching, found an open-source library on GitHub that did exactly what I needed, and solved the problem in 20 minutes.
Open source vs AI: 1–0
pri prebirani tour jednoho umelce jsme posilali sms listkodrzicim se zmenou data koncertu
43k lidi
neslo importovat URL
support odpovedel vyhalucinovanou featurou, kterou ten produkt nema
pisu, ze ta featura neexistuje
napise mi Chief Product Officer te firmy popis stejne vyhalucinovane featury s odkazem na video navod
dvakrat overuju, ze ta featura opravdu neexistuje
video navod je o necem jinem
proc? proboha proc? kde jsme jako lidstvo udelali chybu?
Therapists are secretly using ChatGPT. Clients are triggered.
Some therapists are using #AI during therapy sessions. They’re risking their clients’ trust and privacy in the process.
technologyreview.com/2025/09/0…
Some therapists are using AI during therapy sessions. They’re risking their clients’ trust and privacy in the process.Laurie Clarke (MIT Technology Review)
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
We’re on a journey to advance and democratize artificial intelligence through open source and open science.huggingface.co
As promised (warned), here is part 2.
#scrum #scrumteam #AI #aicodingtools #aicoding #stockbuyback #stockbuybacks #executives #leadership #layoffs #memes #Meme #Humor #humour
"AI advocates have warned that if every author in the class action filed a claim, it would "financially ruin" the entire industry."
Win win.
I just registered my name & book details with the appropriate law firm.
Check if your book/article/paper is on the list here:
theatlantic.com/technology/arc…
If it is, go here:
lieffcabraser.com/anthropic-au…
arstechnica.com/tech-policy/20…
Millions of books and scientific papers are captured in the collection’s current iteration.Alex Reisner (The Atlantic)
"#Anthropic Settles Major AI Copyright Suit Brought by Authors"
Precedent set?
Both of my #Scarfolk books were downloaded and pirated from the LibGen 'shadow library'.
Compensation would be nice.
Anyone aware of other class-action lawsuits I can join, or have any other legal pointers?
news.bloomberglaw.com/class-ac…
#AI
Anthropic PBC told a pair of courts in July that a judge’s order approving class-action status for authors’ copyright lawsuit over millions of pirated books put “inordinate pressure” on the company to settle a case that could kill the company.Annelise Levy (news.bloomberglaw.com)
→ We Are Still Unable to Secure LLMs from #Malicious Inputs
schneier.com/blog/archives/202…
“This kind of thing should make everybody stop and really think before deploying any AI agents. We simply don’t know to defend against these attacks. We have zero agentic AI systems that are secure against these attacks.”
“It’s an existential problem that, near as I can tell, most people developing these technologies are just pretending isn’t there.”
#AI #LLMs #stop #agents #secure #attacks #problem
Nice indirect prompt injection attack: Bargury’s attack starts with a poisoned document, which is shared to a potential victim’s Google Drive. (Bargury says a victim could have also uploaded a compromised file to their own account.Bruce Schneier (Schneier on Security)
"Zázraky" a "magie" technologií, kterým nerozumíme. Rizika #AI ve videu od Tony@segment, jako obvykle s kontextem.
Získejte zpět kontrolu nad svými osobními údaji s Incogni! Použijte kód SEGMENT na tomhle odkazu a získejte 60% slevu na roční plán: https://incogni.com/segm...YouTube
Let's start a campaign about replacing all CEOs and politicians with AI,
let's see how far we can go 😏
We do not aim for #deltachat to be another social media app. No #ai summaries or suggestions. No public directory of contacts. No discovery via outside identifiers (mobile phone or email). Just you and your contacts privately messaging, in a solid simple user interface on all platforms. End-to-End encryption enforced on two layers. #chatmail relays know and retain nothing, no content or metadata. #webxdc apps allow for custom interactions on top of chats.
Contributors and donations welcome!
Mastodon z Lumy nenačítá náhledový og:image obrázek, ale já jsem se s ním půl dne maloval v Inkscape, takže vás o něj rozhodně nehodlám ochudit 😀
#juniorguru #mews #ai #llm #juniordevs #praha #events #tydenprodigitalnicesko #digitalnicesko
Bude ofiko živá junior.guru akce! AI a junioři: pomocník, nebo riziko?
Panelovka o situaci a metodických přístupech, potom praktická přednáška o nástrojích.
Naplánovali jsme to společně v klubu. Akce je ve spolupráci s Mews a koná se v rámci vládního Týdne pro digitální Česko.
10.9. v kancelářích Mews na I.P.Pavlova v Praze (pro přespolní: nedaleko hlavního nádraží).
Zdarma, ale je nutné se registrovat, kapacita je omezená! Sdílejte, přijďte!
#juniorguru #mews #ai
Nezmeškejte akci pořádanou junior.guru společně s Mews na téma AI a junioři: pomocník, nebo riziko? Programátoři mají nového parťáka: umělou inteligenci.luma.com
Apple: spaceship 🛸
Microsoft: glass tower 🏢
Linux: basement... still runs the internet 🐧😎
Root access > real estate.
Pic source: reddit.com/r/linuxmemes/commen…
📸👇
#Linux #Desktop #FOSS #Privacy #Security #OpenSource #Microsoft #Windows #TechNews #CyberSecurity #UserFreedom #Freedom #Tech #Technology #AI #OS #MacOS #Meme #TechMeme
NVIDIA posted 69% revenue growth to $44B, eyeing $45B next quarter. But sky-high expectations, chip export bans to China, and AI market uncertainty keep shares volatile despite 1300% gains in 5 years.
#NVIDIA #NVDA #AI #TechStocks #StockMarket #Semiconductors #TECHi
Read Full Article Here : - techi.com/nvidia-stock-could-c…
NVIDIA's 70% revenue growth is impressive, but with high expectations and geopolitical risks, its stock is at risk of a sharp drop. Will the AI hype continue?Warisha Rashid (TECHi)
What's the 2025 digital trend for you: #AI or digital #sovereignty?
If it's the latter, check out these European alternatives 👉 tuta.com/blog/boycott-us-choos…
And, yes, Tuta is proudly #European! 💪 🇪🇺
With the growing movement to boycott US products and services, more people are choosing European alternatives. Let’s take a look at the best European products you can use.Tuta
Microsoft has added COPILOT AI to Excel — but give it a miss if you use the spreadsheet software for numerical calculations or in scenarios with legal regulatory and compliance implications because COPILOT "can give incorrect responses," the company warns. Here's more from @theverge.
#AI #ArtificialIntelligence #Copilot #Microsoft #Tech #Technology
Microsoft Excel is testing a new “COPILOT” function that lets you use AI to generate summaries, tables, tags, and more based on a group of cells you specify.Emma Roth (The Verge)
I was wondering what vibe coding reminds me of. And today I figured it out. It really reminds me of my experience brewing beer from Coopers brew kits: it was quick and I ended up with drinkable beer. But I knew nothing about the brewing process, the result was suboptimal, and most importantly, I didn't really have control over it.
#AI #vibecoding
Plasticine Action is a group of like-minded artists and concerned citizens, who want to be vocal against the rise in AI generated animation and art, and raise awareness of how AI is being used in an increasingly authoritarian manner.
“Plasticine Action” t-shirts fundraiser plasticineaction.com/
Medical Aid for Palestinians
map.org.uk/
Police Arrest “Plasticine Action” t-shirt wearing protester
theguardian.com/world/2025/aug…
#Ai #Gaza #PalestineAction #PlasticineAction #Solidarity
Miles Pickering says crowd at protest over Palestine Action ban was laughing at ‘silliness’ of scene as he was detainedRobyn Vinter (The Guardian)
