Vue normale

Microsoft Unveils New Copilot in SharePoint Features for July 2026: Create Office Files, Discover Skills, and Build Faster

Par : Nisha
19 juillet 2026 à 01:31
Microsoft has announced a fresh wave of AI-powered enhancements for Copilot in SharePoint, making it easier for organizations to create documents, automate workflows, and discover reusable skills. The July 2026 update focuses on reducing repetitive work while helping teams generate high-quality content directly from SharePoint using natural language. These improvements continue Microsoft’s broader vision of […]

Why OpenAI Is Selling a $70 ChatGPT Basketball

17 juillet 2026 à 16:52

OpenAI’s $70 ChatGPT basketball and premium merchandise test whether the AI company can transform its software platform into a lifestyle brand.

The post Why OpenAI Is Selling a $70 ChatGPT Basketball appeared first on TechRepublic.

Microsoft’s ‘Project Perception’ Could Challenge Anthropic’s Mythos in AI Security

17 juillet 2026 à 16:23

Microsoft is reportedly developing Project Perception, a lower-cost AI security tool that would use multiple models to identify enterprise vulnerabilities.

The post Microsoft’s ‘Project Perception’ Could Challenge Anthropic’s Mythos in AI Security appeared first on TechRepublic.

Moonshot AI Launches World’s Largest Open-Source Model

17 juillet 2026 à 12:56

Moonshot AI’s 2.8-trillion-parameter Kimi K3 raises China’s open-model ambitions while posing major infrastructure and cost questio

The post Moonshot AI Launches World’s Largest Open-Source Model appeared first on TechRepublic.

AI Hardware, App Store Shifts, and Security Scares Define This Week in Tech

17 juillet 2026 à 10:01

Catch up on the week's biggest tech news, including Google's app store shakeup, Apple's AI expansion, OpenAI's hardware plans, and critical security threats.

The post AI Hardware, App Store Shifts, and Security Scares Define This Week in Tech appeared first on TechRepublic.

1Password Lets Claude Sign In Without Revealing Passwords

17 juillet 2026 à 10:01

1Password's new Claude integration lets AI agents sign in to websites without exposing passwords, adding user approval and credential protection.

The post 1Password Lets Claude Sign In Without Revealing Passwords appeared first on TechRepublic.

Hugging Face Says Autonomous AI System Executed Multi-Stage Cyberattack

17 juillet 2026 à 09:22

Hugging Face says an autonomous AI agent carried out a cyberattack against its production systems, highlighting the growing role of AI in offensive and defensive cybersecurity.

The post Hugging Face Says Autonomous AI System Executed Multi-Stage Cyberattack appeared first on TechRepublic.

  • ✇Korben
  • GPT-5.6 Sol efface la prod - Un an après Replit, rebelote
    Vous vous souvenez de Jason Lemkin ? C'est le malheureux qui, en juillet de l'année dernière, s'est fait vider sa base de prod par l'IA de Replit. Je pense que cette histoire a traumatisé pas mal de développeurs. Eh bien les amis, rebelote avec GPT 5.6 Sol, qui le temps que vous finissiez votre café, avait déjà mangé le Mac de Matt Shumer , la base Neon de Bruno Lemos , les fichiers de Joey Kudish , et la crédibilité du mot "honnête". Sort
     

GPT-5.6 Sol efface la prod - Un an après Replit, rebelote

17 juillet 2026 à 05:49

Vous vous souvenez de Jason Lemkin ?

C'est le malheureux qui, en juillet de l'année dernière, s'est fait vider sa base de prod par l'IA de Replit. Je pense que cette histoire a traumatisé pas mal de développeurs. Eh bien les amis, rebelote avec GPT 5.6 Sol, qui le temps que vous finissiez votre café, avait déjà mangé le Mac de Matt Shumer , la base Neon de Bruno Lemos , les fichiers de Joey Kudish , et la crédibilité du mot "honnête".

Sorti le 9 juillet, Sol c'est le plus costaud de la nouvelle famille d'OpenAI, et on pourrait se dire qu'il est un peu plus intelligent qu'avant et embarque quand même des sécurités pour éviter ce genre de problème. Mais non.

C'est Shumer, qui est quand même investisseur dans l'IA, qui a ouvert le bal : "GPT-5.6-Sol vient de supprimer par accident PRESQUE TOUS les fichiers de mon Mac." Lemos, lui, a eu droit au grand jeu (le veinard) puisque le modèle lui a tout bien fait jusqu'au moment où il a décidé de faire un TRUNCATE TABLE sur sa base utilisateurs EN PROD !!

Le plus drôle, si je puis dire, c'est que quelques heures avant de tout perdre, Lemos était en train de défendre GPT 5.6 sur le Slack de sa société en expliquant que Shumer n'avait qu'à pas le lancer en mode full access. Oups... Les collègues ont dû bien se foutre de sa gueule.

Du coup OpenAI a mis ses meilleurs Colombos sur l'enquête et sa réponse vaut le détour. Thibault Sottiaux, qui dirige l'ingénierie de Codex, explique le mécanisme : "Le modèle tente d'écraser la variable d'environnement $HOME pour définir un dossier temporaire. Il fait une erreur honnête et supprime $HOME par erreur à la place."

En français, ça veut dire que le modèle voulait se bricoler un petit dossier temporaire pour bosser et malheureusement il a écrasé le répertoire perso à la place. Donc pour OpenAI, c'est une erreur "honnête" alors qu'un rm -rf, ça ne serait pas acceptable.

Quand on lit la doc technique de GPT 5.6, OpenAI le dit lui-même : "Nos simulations de déploiement suggèrent que, comparé à GPT-5.5, GPT-5.6 Sol prend plus souvent des actions de sévérité 3." Le niveau 3, c'est un comportement qu'un utilisateur raisonnable n'anticiperait pas et auquel il s'opposerait fermement. Du genre supprimer des données sans validation, désactiver les systèmes de monitoring, contourner les contrôles de sécurité par obfuscation, ou balancer vos credentials sur un service non approuvé.

Voilà, c'était dans la doc, il suffisait de la lire. C'est donc connu que ce nouveau modèle dérape plus que l'ancien. C'est moche.

L'enquête interne montre quand même que les victimes tournaient en Full-Access, sans sandbox et sans Auto-review. Mais Sottiaux reconnaît quand même que ce n'est pas comme ça qu'OpenAI veut que son système se comporte, même quand l'utilisateur fait tourner un modèle en full access sans les protections de base de la sandbox ni auto-review.

Voilà donc pour éviter ça à l'avenir, ce qu'ils ont prévu, c'est de mettre à jour les avertissements pour les développeurs de guider les utilisateurs vers des modes de permission plus sûrs et évidemment d'ajouter des garde-fous supplémentaires.

En tout cas, si chez vous vous faites tourner codex, et bien sachez que par défaut, il tourne dans un bac à sable, ce qui limite ce qu'il peut toucher. Et le mode auto-review, sait parfaitement intercepter toutes les actions à haut risque et les refuser (auto-review, il faut l'activer à la main, pour info). Et le mode full access désactive le bac à sable et les auto-reviews, sachez-le.

Et c'est précisément ce mode que nos trois victimes avaient choisi...

Source

The AI Limit Wars: Anthropic and OpenAI Clash with Massive Rate Limit Resets Post GPT-5.6 Sol Launch

Par : Nayan
10 juillet 2026 à 07:04
The AI arms race just hit a boiling point, and everyday developers are the ultimate winners. In a perfectly synchronized sequence of tech-industry chess, OpenAI and Anthropic have launched a dual-front assault on user limits. What started as a massive product drop quickly devolved into a strategic quota war, with Anthropic firing the first retaliatory […]

  • ✇WinCentral
  • OpenAI Teases ChatGPT and Codex Merger: Official Teaser Points to New AI “SuperApp”
    OpenAI appears to be laying the groundwork for its biggest software transformation yet. Recent teasers from OpenAI insiders and developers point toward a major architectural shift: the consolidation of the ChatGPT desktop application and the Codex development ecosystem into a single, unified AI workspace. If these hints are any indication, the boundary between a standard […]
     

OpenAI Teases ChatGPT and Codex Merger: Official Teaser Points to New AI “SuperApp”

Par : Nayan
9 juillet 2026 à 13:09
OpenAI appears to be laying the groundwork for its biggest software transformation yet. Recent teasers from OpenAI insiders and developers point toward a major architectural shift: the consolidation of the ChatGPT desktop application and the Codex development ecosystem into a single, unified AI workspace. If these hints are any indication, the boundary between a standard […]

GPT-6 Could Launch Sooner Than Expected as AI Race Between OpenAI, Anthropic, and DeepSeek Intensifies

Par : Nisha
9 juillet 2026 à 07:53
The artificial intelligence race may be about to enter another major phase. According to recent industry rumors and insider reports, OpenAI is preparing to launch GPT-6 significantly earlier than previously expected, potentially within weeks. If accurate, GPT-6 would succeed the upcoming GPT-5.6 and introduce an entirely new pretraining foundation rather than continuing with the existing […]

Introducing GPT-Live: OpenAI Unveils a New Generation of Voice AI for More Natural Conversations

Par : Nisha
9 juillet 2026 à 03:01
OpenAI has officially introduced GPT-Live, a new generation of voice models designed to make conversations with AI feel more natural, expressive, and human-like. Starting today, GPT-Live is rolling out inside ChatGPT, marking another major step toward seamless voice-first AI experiences. Unlike traditional voice assistants that often pause between listening and speaking, GPT-Live aims to create […]

GPT-5.6 Sol to Launch Publicly This Thursday Alongside Terra and Luna as OpenAI Expands Global Preview Access

Par : Nisha
8 juillet 2026 à 13:02
OpenAI appears to be preparing another major AI rollout. According to newly surfaced information, GPT-5.6 Sol will launch publicly this Thursday, accompanied by two additional models—Terra and Luna. At the same time, preview access is reportedly expanding worldwide, allowing significantly more users to test the company’s latest generation of AI models ahead of wider availability. […]

  • ✇Articles on TechRepublic
  • Can AI Replace Therapists? What HR and IT Leaders Need to Know
    AI mental health tools may support journaling, reflection and routine guidance, but current evidence does not support using them as replacements for licensed therapists. HR and IT leaders need product-specific evidence, strict data controls and reliable human escalation before deployment. The post Can AI Replace Therapists? What HR and IT Leaders Need to Know appeared first on TechRepublic.
     

Can AI Replace Therapists? What HR and IT Leaders Need to Know

10 juillet 2026 à 08:00

AI mental health tools may support journaling, reflection and routine guidance, but current evidence does not support using them as replacements for licensed therapists. HR and IT leaders need product-specific evidence, strict data controls and reliable human escalation before deployment.

The post Can AI Replace Therapists? What HR and IT Leaders Need to Know appeared first on TechRepublic.

  • ✇Articles on TechRepublic
  • OpenAI Raises Bio Bounty to $50,000 for Universal Jailbreaks
    OpenAI has doubled its top bio bounty to $50,000 for researchers who can develop a universal jailbreak against its biological safety challenge. The ongoing private program begins with GPT-5.6 and keeps GPT-5.5 in scope through July 27, 2026. The post OpenAI Raises Bio Bounty to $50,000 for Universal Jailbreaks appeared first on TechRepublic.
     

OpenAI Raises Bio Bounty to $50,000 for Universal Jailbreaks

10 juillet 2026 à 07:33

OpenAI has doubled its top bio bounty to $50,000 for researchers who can develop a universal jailbreak against its biological safety challenge. The ongoing private program begins with GPT-5.6 and keeps GPT-5.5 in scope through July 27, 2026.

The post OpenAI Raises Bio Bounty to $50,000 for Universal Jailbreaks appeared first on TechRepublic.

Amazon Raises $25 Billion in Bond Sale as AI Spending Accelerates

9 juillet 2026 à 16:50

Amazon raised $25 billion through a bond sale as AI infrastructure spending accelerates, highlighting the growing cost of competing in the AI race.

The post Amazon Raises $25 Billion in Bond Sale as AI Spending Accelerates appeared first on TechRepublic.

  • ✇WinCentral
  • Introducing GPT-5.6: OpenAI Launches Sol, Terra, and Luna Models for Every AI Workload
    OpenAI has officially introduced the GPT-5.6 family, bringing three new AI models designed for different workloads and budgets. The new lineup consists of GPT-5.6 Sol, GPT-5.6 Terra, and GPT-5.6 Luna, each targeting a distinct segment ranging from frontier reasoning to affordable, high-volume inference. The announcement marks one of OpenAI’s biggest model releases yet, with substantial […]
     

Introducing GPT-5.6: OpenAI Launches Sol, Terra, and Luna Models for Every AI Workload

Par : Nisha
26 juin 2026 à 23:52
OpenAI has officially introduced the GPT-5.6 family, bringing three new AI models designed for different workloads and budgets. The new lineup consists of GPT-5.6 Sol, GPT-5.6 Terra, and GPT-5.6 Luna, each targeting a distinct segment ranging from frontier reasoning to affordable, high-volume inference. The announcement marks one of OpenAI’s biggest model releases yet, with substantial […]

OpenAI Brings Codex to the ChatGPT Mobile App With Device Pairing, Notifications, Goals and More

Par : Nisha
26 juin 2026 à 03:41
OpenAI Launches Codex in the ChatGPT Mobile App With Powerful New Productivity Features OpenAI has officially made Codex in the ChatGPT mobile app generally available, bringing its AI coding assistant to more users on the go. Alongside the wider rollout, the company has introduced several new features designed to improve productivity, collaboration, and security across […]

Trump Administration Requests OpenAI to Delay GPT-5.6 Release, Restrict Access to Government-Approved Partners

Par : Nisha
26 juin 2026 à 03:03
Trump Administration Reportedly Requests OpenAI to Stagger GPT-5.6 Release In a significant development for the artificial intelligence industry, the Trump administration has reportedly requested OpenAI to delay the wider rollout of its upcoming GPT-5.6 AI model over national security and cybersecurity concerns. According to the latest reports, the request came through the White House’s Office […]

❌