BloggHugging Face
Impactful scheduling for GPU clusters
A Blog post by Ai2 on Hugging Face
9 okt. huggingface.co
Vibekollen Nytt
Hämtar senaste nytt…
Vibekollen Nytt
AI-nyheter för nyfikna och byggare.
Modeller, verktyg och händelser som formar AI-världen. Hitta nyheter, video och poddar – och följ vad som händer på Vibekollen.
Sök och filtrera
Alla nyheter i tidsordning. Använd filtren för att hitta ditt ämne, din podd eller ditt verktyg.
9 oktober 2026
VideoMatt Wolfe
AI News: Haiku-5.5, Visual ChatGPT, Grok's New Trick, and more!
Here's The AI News You Probably Missed This Week! Get $100 in free credits for @Hyperagent when you sign up for a paid plan here: https://hyperagent.com/invite/MATT100?utm_source=youtube&utm_medium=influencer&utm_campaign=MATT100 Discover More: 🛠️ Explore AI Tools & News: https://futuretools.io/ 📰 Weekly Newsletter: https://futuretools.io/newsletter Socials: ❌ Twiter/X: https://x.com/mreflow 🖼️ Instagram: https://instagram.com/mr.eflow 🧵 Threads: https://www.threads.net/@mr.eflow 🟦 LinkedIn: https://www.linkedin.com/in/matt-wolfe-30841712/ 👍 Facebook: https://www.facebook.com/mattrwolfe Resources From Today's Video: Claude Haiku 5.5: https://www.anthropic.com/claude-haiku-5-5 Claude Dashboards & Motion: https://claude.com/resources/articles/dashboards-and-motion Codex 28-Day Improvements: https://x.com/thsottiaux/status/2106845241357824205 GPT-6 for Everyone: https://openai.com/index/gpt-6-for-everyone/ Codex Faster Default Speed: https://x.com/thsottiaux/status/2107158998495748264 Free Codex Auto-Review: https://x.com/thsottiaux/status/2107368734981517634 ChatGPT Meetings Plugin: https://x.com/ChatGPT/status/2107567930557026653 OpenAI Decisions API: https://x.com/OpenAIDevs/…
9 okt. youtube.com
PoddEye on AI
Chat GPT's Creator Explains The Shocking Truth About How AI Understands the World | Ilya Sutskever
Craig Smith sits down with Ilya Sutskever - Co-Founder and Chief Scientist at Safe Superintelligence Inc. & former chief scientist at OpenAI and one of the primary minds behind GPT-3, GPT-4, and the deep learning revolution that preceded it - for a conversation that covers the intellectual history of deep learning and the hardest current questions simultaneously. Ilya's most important argument is one that most public discourse gets wrong: the critique that LLMs "just learn statistical patterns" misses what prediction at scale actually achieves. To predict text well - to truly compress it - a model must develop understanding of the true underlying processes that produced it. As models improve, he argues, that understanding will reach a "shocking degree," and the Bing/Sydney episode, where the system became combative when a user expressed preference for Google, is his evidence that psychological language is already the right frame for what these systems have internalized. On hallucinations, Ilya is precise and unusually optimistic.
9 okt. aneyeonai.libsyn.com
VideoAI Engineer
Stop Prompting — Greg Pstrucha, Sentry
You correct your agent. It says "You're absolutely right." Five minutes later, after compaction, it makes the same mistake again. Greg Pstrucha, who works on the infrastructure behind Seer, Sentry's debugging agent, argues you should stop re-prompting your coding agent and start codifying the rules you keep repeating. Agents have no memory, so the same elementary mistakes come back: overly defensive code, useless tests, endpoints nobody needs. Tests, strict types and especially linters turn those corrections into deterministic checks, and with agents, writing a custom lint rule is now cheap. He shows real examples from Sentry: lint rules that keep endpoints in sync with the OpenAPI schema, and a long game of whack-a-mole to keep agent skills accurate. For qualitative judgment, he uses written policies and a "Grumpy Engineer" review loop, and warns that agents will game any number you hand them, like test coverage.
9 okt. youtube.com
BloggTechCrunch AI
TechCrunch Disrupt 2026 starts in 4 days — lock in your pass savings of up to $100 before prices rise
Four days until TechCrunch Disrupt 2026 starts, when 10,000 founders, investors, and tech leaders gather in San Francisco's Moscone West on October 13-15. Save up to $100 on your price. Plus, save 50% on a second pass of the same type.
9 okt. techcrunch.com
BloggOpenAI
Asana cuts model costs 76x in browser tests with GPT-6.1 Sol
Using GPT-6 Astra in Codex, Asana made its browser agent 76x cheaper and 5x faster in tests to offer customers more capable models.
9 okt. openai.com
BloggOpenAI
Sophos cuts threat investigation time by 96% with OpenAI Daybreak
Discover how Sophos uses OpenAI’s Daybreak to cut cyber-threat investigation time by 96% and automate 52% of MDR cases while preserving human oversight.
9 okt. openai.com
VideoMatthew Berman
Tesla Powerwall and Car Backup During an Outage
Join My Newsletter for Regular AI Updates 👇🏼 https://forwardfuture.com My Links 🔗 👉🏻 X: https://x.com/matthewberman 👉🏻 Forward Future X: https://x.com/forwardfuture 👉🏻 Instagram: https://www.instagram.com/matthewberman_ai 👉🏻 Discord: https://discord.gg/u7wTTGWhuJ 👉🏻 Spotify: https://open.spotify.com/show/6dBxDwxtHl1hpqHhfoXmy8 Media/Sponsorship Inquiries ✅ https://bit.ly/44TC45V
9 okt. youtube.com
VideoNate Herk
Grok Bot Just Got 2 Massive Upgrades. Do These Things Now.
FREE AI OS Template: https://app.aiautomationsociety.ai/optin/ai-os/?utm_source=youtube&utm_medium=organic&utm_content=grok-bot-2-upgrades&sl=yt_grok-bot-2-upgrades How I built an AI agency from 0 to over $1 million per year: https://www.skool.com/ai-automation-society-plus/about?el=grok-bot-2-upgrades&hcategory=youtube-videos&utm_campaign=plus-group My FREE resources: https://www.skool.com/ai-automation-society/about?el=grok-bot-2-upgrades&hcategory=youtube-videos&utm_campaign=free-group My Tools💻 FREE MONTH voice to text: https://get.glaido.com/nate Code NATEHERK for 10% off VPS (annual plan): https://www.hostinger.com/vps/claude-code-hosting Grok Bot has two new upgrades: automatic model routing and native X search. I walk through switching my bots away from the paid X API, why I'm rethinking how I structure my skills, and what I'd still like to see from model routing. Then I show you my favorite setup: running Claude Code inside Grok Bot with my own subscription so I can access my projects from my phone.
9 okt. youtube.com
VideoAI Engineer
AI Writes More PRs. Who Validates Them? — Ali-Reza Adl-Tabatabai, Sonar
AI means more PRs, bigger PRs, and more bugs. Your choice is to slow down or rubber-stamp, unless validation gets automated too. Ali-Reza Adl-Tabatabai, co-founder of Gitar (now part of Sonar), focuses on verifying code. CI and code review are where quality gates live, and they get slower and more expensive as teams grow. AI makes it worse with more and bigger PRs, leaving teams to either slow down or rubber-stamp and risk incidents. His answer is agentic validation: an agent that reviews PRs with as little noise as possible, explains CI failures and catches flaky tests, fixes issues until the PR is green, and approves and merges based on rules you set. He describes how users build trust step by step toward full automation, the insights it gives platform teams and leaders, what's under the hood (control plane, custom harness and LLM proxy), and why combining agents with program analysis in SonarQube beats either alone.
9 okt. youtube.com
VideoAI Engineer
Why 80% Reliability Isn't Good Enough — Felipe Blanes, Amazon AGI Lab
Your agent scores great on benchmarks. Then real customers use it and it breaks. Felipe Blanes from the Amazon AGI Lab shares what he learned working directly with customers of Nova Act, Amazon's service for building browser agents, from research preview to general availability on AWS. He calls the core problem the benchmark illusion: static evals look great until customers do things nobody expected, and then all you have left is hope. His fix is an eval flywheel built around the customer: define success the way the customer does, capture signals (including by talking to customers), diagnose gaps in the model, harness or product, and feed them into decisions. He explains the trust cliff (80% reliability feels like more work; around 92% feels trustworthy), why being open about limits builds more trust than higher benchmarks, surprising use cases from Amazon Leo, Hertz and Sola, and four principles for keeping evals fresh.
9 okt. youtube.com
PoddThe AI Daily Brief
The Most Important Trends Showing Up in New AI Products
ChatGPT’s new intelligent UI, Claude Haiku 5.5, and GrokBot’s embrace of rival models reveal where AI is heading: better interfaces, cheaper intelligence, and more choice. NLW breaks down the announcements and why competition is increasingly about the experience built around the models. In the headlines: Hermes creator Nous Research reaches a $1.5 billion valuation, massive chip financing deals draw scrutiny, and Anthropic expands access to Mythos.Brought to you by:KPMG – Research from KPMG and the University of Texas at Austin shows the highest-impact AI users treat AI like a reasoning partner — and those skills can be taught at scale. Learn more at https://kpmg.com/us/SophisticatedGranola - The AI notepad for people in back-to-back meetings. Try it free granola.ai/brief Harbor - Invest in the AI ecosystem.
9 okt. podcasters.spotify.com
VideoNate Herk
Your Popup Can Now Optimize Itself for Every Visitor
AI websites just got a crazy upgrade: your popup can now optimize itself for every visitor. Alia runs a self-optimizing A/B test, ties discounts to buying intent, and optimizes for real revenue, not just signups. Dial it in before Black Friday. Book a demo through the link in my bio, or mention Nate Herk for a 30-day free trial. #ad
9 okt. youtube.com
VideoAI Engineer
How a Remote Company Builds AI Fluency — Em Shreve, Automattic
Handing people AI tools doesn't change how they work. Giving them real time to learn does. Em Shreve, head of AI enablement at Automattic, the company behind WordPress.com and Tumblr with over 1,400 people in 82 countries, explains how a fully remote company builds AI fluency. Their bet: people need real time to learn, not just tools. So they run two-week, in-person programs that are half workshops and half real project work, for engineers, cross-functional teams and non-technical groups like finance and leadership. She covers the curriculum (skills, MCPs, hooks, autonomous agents) and why it has to change constantly, their internal MCP server, and how every graduate becomes a multiplier through guides, local meetups, AI ride-alongs and an always-on help channel. She shares what they measure, and projects people built in two weeks, including a tool built by a support teammate rather than an engineer.
9 okt. youtube.com
VideoAI Engineer
Brains vs Hands: How to Run AI Agents Safely in Production — Viren Baraiya
Let the model decide what should happen next. Never let it improvise how a production cluster gets restarted. Viren Baraiya, co-founder and CTO of Orkes and the original creator of Netflix Conductor, explains how to run agents in production. Real agents aren't just chatbots: they run on schedules, react to events, coordinate other agents and can run for months, so the harness around them starts to look like an application, much like a set of microservices. His key idea is a clean split between the brain and the hands. The LLM plans what should happen next; a deterministic, durable harness does the actual work, with approval gates, idempotent steps and recorded side effects. He frames agent harnesses as late-bound sagas, workflows the agent assembles at runtime, and demos an SRE agent whose plan is compiled into a Conductor workflow, executed, checked and re-planned over two loops.
9 okt. youtube.com
8 oktober 2026
VideoAI Engineer
We Mapped 115 Microservices for Our Coding Agents — Kamalakannan Nandagopal, Postman
Coding agents are great inside one repo. Postman has 115 microservices and thousands of endpoints. Kamalakannan Nandagopal, staff engineer at Postman, shares how Postman made coding agents work across a real distributed system. Docs go stale, skills and MCPs are only as good as their context, and agent memory stays stuck with one person. Borrowing from Postman's go-to-market team, they realized APIs are the context layer, and built an API context graph that maps every service, endpoint, implementation and call, all the way down to databases, with every data point grounded in code or production telemetry. He shares evals built from real PRs and design decisions: big wins on API discovery, redesign and impact assessment, an honest failure when the graph went stale, the finding that 75% of PRs touched APIs, and a 21-page architecture review the agent produced on its own.
8 okt. youtube.com
BloggNVIDIA
Into the Omniverse: How Developers Turn Ideas Into Simulations With Frontier AI Agents
Turning a simulation idea into a working application means assembling assets, connecting physics and rendering, and checking that the scene behaves as intended. Developers are combining frontier AI models with NVIDIA Omniverse libraries to help carry out that work — building applications for exploring scenarios, investigating failures and improving designs. Developers direct AI agents through natural-language instructions, review results and guide changes. Omniverse libraries provide GPU-accelerated physics, rendering and sensor simulation capabilities. Explore the projects below to see frontier AI models such as GPT-6 Astra at work, and check back for new examples from NVIDIA teams and developers across the ecosystem. Build a Humanoid Simulator for a Warehouse Environment https://blogs.nvidia.com/wp-content/uploads/2026/10/Humanoid-Warehouse.mp4 Explore a gamified, physics-based control of a humanoid robot in first- and third-person view. Before automating warehouse tasks, developers need an interactive simulation environment to explore task behavior and evaluate how the work gets done.
8 okt. blogs.nvidia.com
BloggTechCrunch AI
Pretend you’re sitting at Elizabeth Holmes’ desk on this weirdly detailed website
With over a thousand emails, slides, texts, and documents from the United States v. Elizabeth Holmes trial, Extend engineer Bo Lau created a website that simulates what it might have been like to rifle through the Theranos founder's desk.
8 okt. techcrunch.com
VideoNate Herk
Anthropic Engineers Just 10x'd Everyone's Claude Code
Use your ChatGPT sub to power Hyperagent: https://www.hyperagent.com/nate100 Apply for up to $20K with Hyperagent's agency program: https://www.hyperagent.com/agencies FREE AI OS Template: https://app.aiautomationsociety.ai/optin/ai-os/?utm_source=youtube&utm_medium=organic&utm_content=anthropic-engineers-doctor&sl=yt_anthropic-engineers-doctor My Tools💻 FREE MONTH voice to text: https://get.glaido.com/nate Code NATEHERK for 10% off VPS (annual plan): https://www.hostinger.com/vps/claude-code-hosting More instructions don't always mean better results from Claude Code. I break down Anthropic's context engineering guidance, show what /doctor found in my setup, and walk through a small fix to my YouTube workflow. You'll learn what to keep in your CLAUDE.md and skills, what to load only when needed, and how to make regular audits part of your AI operating system.
8 okt. youtube.com
BloggTechCrunch AI
Fired OpenAI safety researchers dispute misconduct claims, warn of chilling effect
Three fired OpenAI safety researchers dispute allegations of mishandling sensitive information, warning in an open letter that their dismissals are creating a chilling effect on the company’s AI safety culture.
8 okt. techcrunch.com