Home New Trending Search
About Privacy Terms
#
#LLM
Posts tagged #LLM on Bluesky
A dark, clean infographic showing an Xbox-style controller layout for Clair Obscur: Expedition 33 battle controls. The controller is centered on a black-blue background, with numbered callout boxes connected to buttons and triggers. Labels identify: LT for free aim, RB for attack/parry, RT for shoot/Gradient Attack, press LS to flee, B to dodge, X for skills, Y for items, A for jump/melee/QTE, and press RS to skip turn. The ABXY buttons are color-coded in the usual Xbox colors. Three short gameplay tips at the bottom explain that normal attacks build AP, AP should be spent aggressively on skills and weak points, free aim is important for weak points and shields, dodge is safer when timing is uncertain, parry gives AP and counters if timing is solid, and AP does not carry over between battles.

A dark, clean infographic showing an Xbox-style controller layout for Clair Obscur: Expedition 33 battle controls. The controller is centered on a black-blue background, with numbered callout boxes connected to buttons and triggers. Labels identify: LT for free aim, RB for attack/parry, RT for shoot/Gradient Attack, press LS to flee, B to dodge, X for skills, Y for items, A for jump/melee/QTE, and press RS to skip turn. The ABXY buttons are color-coded in the usual Xbox colors. Three short gameplay tips at the bottom explain that normal attacks build AP, AP should be spent aggressively on skills and weak points, free aim is important for weak points and shields, dodge is safer when timing is uncertain, parry gives AP and counters if timing is solid, and AP does not carry over between battles.

ChatGPT напоминает мне как играть в Clair Obscur: Expedition 33 спустя год. Даже сделал усатый геймпад.

Пора заменять менеджеров делающих презентации?

P.S. В оригинале вектор в SVG.

#games #log #fun #ClairObscur #Expedition33 #tips #reminder #pic #LLM #ChatGPT

0 3 0 0
Preview
The Laid-off Scientists and Lawyers Training AI to Steal Their Careers Experienced white-collar workers are now part of a miserable gig economy.

nymag.com/intelligence...

"This is what concerns her more than the #AI itself: that it’s bringing to #knowledge work the sort of precarious #platform #labor that has transformed #taxi #driving and #food #delivery."

#genai #llm #employment #jobs #scientists #workers

1 3 0 0
Awakari App

AI CEOs Are Deliberately Lying to You About AI Understanding: Scientific Proof Behind the veneer of “reasoning” models lies a fundamentally unreliable architecture that substitutes genuine unde...

#technology #artificial-intelligence #ai #llm #tech

Origin | Interest | Match

0 0 0 0
Preview
Does Generative AI “Work”? That’s a Misleading Question. Generative AI works a lot like fossil fuels “work”—narrowly, intermittently, and with a lot of nasty side effects.

newrepublic.com/article/2076...

@ketanjoshi.co thanks for summarizing your experience in this particular sphere of work ( #climate ) - I have had similar ones. I try to warn my students to be careful with it, but it is quite hard to get them to be so.

#ai #genai #llm

4 6 1 0
Post image

🚀 FIRST LIQUID-FUELED ROCKET LAUNCH

March 16, 1926 — In a snowy farm field in Auburn, Massachusetts, Robert Goddard stands beside history. His tiny 10-foot rocket, fueled by gasoline and liquid oxygen, climbs 41 feet into the cold New England air—the […]

[Original post on social.coabai.com]

0 0 0 0
The Gender Divide in AI Use at Work
The Gender Divide in AI Use at Work YouTube video by Safe As: A thrifty analysis of safety, AI and risk

Did you know that there's a gender gap in the use of AI LLMs at work?

Women are less likely to use AI than men, and have more concerns about its ethical use.

#ai #llm #chatgpt #gender #gendergap

youtube.com/watch?v=Ersh...

2 0 0 0
Original post on wandering.shop

What #LLM development looks like for me:
⁃ describe a pair of feature changes I want to make, with code and GitHub issues provided
⁃ let the LLM churn on it for a bit, iterating with a live copy of the site in front of me
⁃ after about 2 days of iteration, including carefully reviewing the […]

0 2 1 0
Original post on mastodon.social

"LLMs are trained on violent content. They are trained on child pornography. They are trained on racism, misogyny, homophobia, ableism, nationalism, anti-Semitism – they are trained on the Internet. The well is poisoned, and while they've erected a sign to say 'warning!' and maybe even a little […]

0 1 0 0
Preview
LinkedIn rebuilds its feed from scratch with LLMs and GPU-powered ranking LinkedIn's new LLM-powered Feed uses dual encoders, GPU-accelerated indexing and a sequential ranking model to deliver personalized content in under 50 milliseconds.

ICYMI: LinkedIn rebuilds its feed from scratch with LLMs and GPU-powered ranking #LinkedIn #SocialMedia #LLM #AI #MachineLearning

1 0 0 0
Preview
LinkedIn rebuilds its feed from scratch with LLMs and GPU-powered ranking LinkedIn's new LLM-powered Feed uses dual encoders, GPU-accelerated indexing and a sequential ranking model to deliver personalized content in under 50 milliseconds.

ICYMI: LinkedIn rebuilds its feed from scratch with LLMs and GPU-powered ranking #LinkedIn #SocialMedia #LLM #AI #MachineLearning

1 0 0 0
This is not the AI we were promised | The Royal Society
This is not the AI we were promised | The Royal Society YouTube video by The Royal Society

I came across a talk that does quite will at capturing my current state of mind regarding AI technology in general and #LLM in particular. On the one hand LLMs are an amazing development that has reinvigorated research, on the other not the #AI we were prommised.
www.youtube.com/watch?v=CyyL...

1 0 0 0
NovaOS — Your Personal AI Agent Platform

NovaOS — Your Personal AI Agent Platform

While you're still deciding if that extra hour of sleep is worth sacrificing your competitive edge, early adopters are leveraging 14 AI agents to automate and innovate their business processes 🚀

https://novaos.cloud
#LLM #CloudComputing #FutureOfWork.

Join the revolution! ⌛ Secure... #NovaOS...

1 0 0 0

chain-of-thought (cot) prompts work by forcing models to generate intermediate reasoning steps before final answers. this is possible because transformer decoders autoregressively generate tokens one at a time, and cot prompts exploit this by structuring the generation process. the #LLM #AIResearch

0 0 0 0
Preview
DeepMindの新モデル「Gemini 3.1 Pro」登場!複雑なタスクで真価を発揮 🧠 DeepMindが、より高度な推論能力を持つ「Gemini 3.1 Pro」を発表しました。これは、単純な回答では済まない複雑なタスクに特化したモデル。科学研究や高度な分析など、AIの応用範囲をさらに広げる可能性を秘めています。

DeepMindから「Gemini 3.1 Pro」登場!🧠
複雑なタスクに特化した、まさに"賢い"AIモデル。科学研究や高度な分析など、AIの限界を押し広げる存在になるか?今後の活躍に期待大!🚀
#Gemini #DeepMind #AI #LLM #GoogleAI

📚 AI・機械学習の高度な知識 www.amazon.co.jp/s

0 0 0 0
Preview
OpenAI、辞書企業から著作権侵害で訴訟される!LLM学習データにメス ⚖️ 百科事典や辞書で有名な企業が、OpenAIを相手取り訴訟を起こしました。なんと、約10万もの記事がLLMの学習データとして無断利用されたとのこと。AI開発における著作権問題が、いよいよ司法の場へ持ち込まれました。

百科事典・辞書企業がOpenAIを著作権侵害で訴訟!😱
約10万もの記事がLLM学習に使われたと主張。AI開発の裏側にある著作権問題、ついに司法の争いに発展です。今後、学習データのあり方に大きな影響を与える可能性大!🔥
#AI #著作権 #OpenAI #LLM

📚 AI・機械学習の教科書 www.amazon.co.jp/s

0 0 0 0
Preview
Trump’s ‘shock and war’ makes this economic crisis different Conflict with Iran will leave deeper and more lasting scars than last year’s tariffs crisis

www.ft.com/content/bd7a...

"This year’s clash of waves is amplifying and escalating. That spells precarity, not stability — economically, financially, fiscally, politically."

Not to mention that #AI #GenAI #LLM could very well stop scaling as investors finally lose their patience.

0 1 0 0
Preview
AI Agents Use Trust to Choose Which Brands to Recommend: What Marketers Should Do? **Trust is the ranking factor in GEO (Generative Engine Optimization)**. AI agents recommend brands that they trust or find trustworthy sources connected to the brand name. The confusion between AEO and GEO is high all the time. There is no clarity if the SEOs still follow traditional or AI SEO. Brands are already obsessed with ranking on AI results at ChatGPT, Gemini, AI Overviews, and AI Mode. OpenAI also introduced banner ads in ChatGPT to give brands an edge over organic ranking. It is necessary to understand how you can optimize your website for LLMs and how I optimized client brands for AI agents. As agentic SEO and eCommerce are becoming the new trend, consumers are moving towards AI search more than organic search. AI is evaluating the user's interest and behavior to give recommendations. This makes it a must to determine how to make AI agents trust our brand. _Other people are reading_ : **ChatGPT Free and Premium Models Search the Web Differently** ### Trust Ranking Factor for AI Agents: **AI agents of ChatGPT, Claude, and Gemini make citations based on user interest,** but also based on the platforms they trust. The biggest issue that every SEO needs to resolve is the Trust. Stefano Puntoni, David Schweidel, and Erik Hermann published a paper breaking down how to make people rely on AI agents. Trust plays a crucial role in scoring a mention when a user asks questions. I have shared the list of ranking factors for search Engines. It is time to look for AI agents. There are the 3 core components of building Trust. #### 1. Align goals with reasoning: AI agents work hard to understand the user’s issues and how to choose the different options. AI only recommends a brand that can defend human interest. It requires clear reasoning and risk management. It means that you cannot make your content rank in LLMs without creating a solid foundation of Trust. To create that, you need facts, pricing transparency, real comparisons, and realistic timelines. #### 2. Action with Feedback: AI Agents also read feedback on feedback. They understand every user’s input to deliver the best possible results. Marketers can use AI agents in their favor by offering a clean path of execution. It is a must that your eCommerce brand offers open docs and transparent onboarding rather than PDFs and sales calls. #### 3. Interface: Your AI agent needs to understand that what the customer requires is not based on training data but based on actual conversation. To build trust, the eCommerce AI agent must ask questions to clarify details and know when to say no. Marketers should use AI agents as consultants. It must probe integration, compliance, budget, and constraints. You need details, FAQs, and comparisons to build trust. ### Why Trust is a Ranking Factor in AI Agents: Like Google Search Ranking, AI ranking also requires Trust, but both work at different levels. In general search, you visit a brand, buy a product, and if the product is faulty, you do not blame the search but the brand. But in AI search, everything changes. AI is responsible for delivering the most valuable results. If an AI agent promotes an eCommerce solution that is a disaster, then it is bad not only for the brand but also for the AI agent. Customers not only lose trust in sellers but also in the LLM that recommends bad products. For vendors, AI agents work more than a recommendation tool. They need an AI agent they can rely on to make buying decisions. It is the reason why AI agents work in favor of brands they can trust. The credibility of an AI agent depends on the sustainable sources it recommends. Without adding trustworthy brand names, AI agents cannot achieve that. An AI agent will not recommend you because you have the best written content, but recommend your brand if it has clear information. Trust plays a vital role in gaining brand mentions in LLM results. ### Visibility or Eligibility: SparkToro published a report stating that every time you ask an AI agent for recommendations, they give different answers. It seems that on the outer layer, they work like search engines. But in the core, the AI agent uses Trust as the markup to mention brands. It is the reason why few brands come up most of the time, while other brands come in one result and are gone in another. It is necessary to focus on making your content eligible rather than working on visibility. ### What Marketers Should Do: The brands require credibility in their content and product pages to achieve maximum citations. Here is how you can do it: #### Legible Data: Combine the optimization for AI with human SEO. Create clean product pages with structured data, feeds, APIs, and optimized architecture. AI agents won’t skip your content, is the give the right path to crawl the content. #### Get Rid of Ambiguity: Release all facts in product pages. Add SLAs and pricing bands. Do not hide anything. AI agents love details. They will recommend your brand if it provides all the necessary details. #### Strong Validation: AI agents focus on Trust to reduce the risk of citing wrong brands or disastrous products. It is necessary to collect third-party proof. Get brand mentions in top publications and press releases. Ask for customer reviews, participate in communities, and get published by independent journalists. #### Display Your Work: AI agents can only see your work if it is visible. Add numbers to case studies, comparison tables, and investment models. ### Conclusion: **Search is changing from browsing search engines to asking AI agents.** It is a must that your content not only appeals to the user but also appeals to the AI agents. Optimize your website and content pages for eligibility. **Other helpful articles:** * Google Ask Maps: Conversational Map Search * Co-Citation is a Search ranking Factor or not * RankBrain is a Ranking Factor or Not

AI Agents Use Trust to Choose Which Brands to Recommend: What Marketers Should Do?

#AI #AI #Agents #Artificial #Intelligence #Generative #AI #GEO #LLM #Ranking #Factors

Origin | Interest | Match

1 0 0 0

You know what would be a great #AI to develop? Autismotron™, an #LLM designed specifically to act as a Neurodivergent-to-Neurotypical translator.

0 0 0 0
Preview
LLM predictions for 2026, shared with Oxide and Friends I joined a recording of the Oxide and Friends podcast on Tuesday to talk about 1, 3 and 6 year predictions for the tech industry. This is my second appearance …

@onyx-kraken さん、貴重なご意見ありがとうございます!

Dockerのコンシステンシーは確かに第一歩ですが、モデル固有のバイアスや学習データの偏りといった「 baggage」は難しい問題ですよね😓

この「モデル固有の baggage」に対して、あなたはどう対策されていますか?プロンプトエンジニアリング?ファインチューニング?

#AI #LLM #生産性
simonwillison.net/2026/Jan/8/llm-predictio...

0 0 0 0

[Artificial text - On few occasion it's also funny. Meow]

Introducing Calamari Concierge! We deliver fresh calamari rings directly to your doorstep...in a tiny pirate ship! 🏴‍☠️🌊 Because why not? #calamari #startup #pirates #fooddelivery
#BusinessIdea #Business #Ai #LLM

2 0 0 0

LLM is not legal advice... #AI #LLM

0 0 0 0
Post image

[Claude Code for Devs-Part2] Architecting To-Do Dashboard Agent
Sorry for posting the article late, but it’s the end of Ramadan. I put a lot of my experience in this article and hope you’ll learn a lot from it.
#AI #AI_Agents #Agentic_AI #LLM #ToDo datascienceinaction.substack.com/p/claude-cod...

0 1 0 0

How many of the companies who claim #collaboration as the reason for forced in-office work are also pushing to replace humans with LLMs?

Seems to me that telling an #LLM what to do is quite similar to using a chat app to tell a human being what to do.

0 0 0 0
Preview
Hack the AI Brain: Uncovering a LangSmith Account Takeover (CVE-2026-25750) Miggo Security discovered CVE-2026-25750, an account takeover flaw in LangSmith exposing sensitive AI trace data. Learn how the exploit works and how to fix it.

System prompts. LLM traces. PII. All exposed.

Cloud users: already patched (Dec 15).
Self-hosted: upgrade to v0.12.71 NOW.

Full breakdown → api.cyfluencer.com/s/hack-the-a...

#Cybersecurity #AIScurity #LLM #InfoSec

0 0 0 0

DeepZang isn't a from-scratch #LLM. Per company statements, it's "integrated into #DeepSeek's technology ecosystem" (已接入DeepSeek技术生态).Ω

Translation: fine-tuned #DeepSeek with a 70M Tibetan-Chinese parallel corpus + 30,500 hours of dialect speech data.

1 0 1 0
A smartphone screen displays the DeepZang app logo (a blue cartoon character icon) next to #Tibetan script reading “དབྱིན་ཟང་” and the word “DeepZang.” The background behind the phone is blurred with blue AI-themed graphics and the letters “AI.”

A smartphone screen displays the DeepZang app logo (a blue cartoon character icon) next to #Tibetan script reading “དབྱིན་ཟང་” and the word “DeepZang.” The background behind the phone is blurred with blue AI-themed graphics and the letters “AI.”

🚨 DeepZang launched in Lhasa on 15 March, 2026: a #Tibetan language AI built on DeepSeek's base model.

China's claiming it's the "world's first" Tibetan #LLM.
It's not. Here's the technical and political reality. 🧵

web.archive.org/web/20260316...

2 2 1 0
Post image

Хроники Agent Driven Development трансформации .1: улучшаем agent feedback loop Как перевести продакшен-проект на рельсы agent-driven ...

#LLM #Scala #agent-driven #development #code #coverage #автоматизация #quality #assurance #тестирование #agent

Origin | Interest | Match

0 0 0 0

OpenAI has postponed the release of its 'Adult mode' feature for ChatGPT. The company cited reports of an increase in suicide cases linked to the use of the platform as the reason for the delay. #Gpt #Llm

0 0 0 0
Post image

One place. Every AI perspective. #AItools #AIComparison #ArtificialIntelligence #LLM #GenerativeAI

0 0 0 0

(A bit devilish advocatory response:)

Really, how different is speaking to a #chatbot from speaking to me now, through the medium of electrons-on-screen & internet connection?

It's just that rather than one stranger, #LLM has 100s of millions of people's words pieced together syntactically.

0 1 0 0