If you have ever winced at your monthly AI bill, here’s some good news. According to a report by The Wall Street Journal, OpenAI is considering drastically lowering the prices it charges users as it fights to win customers from its rival, Anthropic.

The company is weighing significant cuts to its token pricing, the unit AI firms use to bill for their products. Interestingly, the move is in anticipation of similar cuts OpenAI expects from Anthropic. So whichever AI service you use, your bills should get smaller.

Why is OpenAI suddenly feeling generous?

The answer is simple: businesses are tired of paying sky-high prices for AI. Heck, there have even been reports of AI costing companies more than actual employees. Even OpenAI CEO Sam Altman admitted at a recent event that costs had become “a huge issue,” adding, “I think we’ll have a lot of ways we can help people get more value for less spend.”

But that’s not all. OpenAI is also facing stiff competition. Anthropic’s revenue surged after its coding tool, Claude Code, went viral among software engineers, and the five-year-old startup surpassed OpenAI’s valuation for the first time. OpenAI has since made its own coding tool, Codex, a company focus, but it’s still far behind the competition.

Some corporations poured so much money into AI coding tools that their leaders are now reining in spending. An Uber executive said the company had already maxed out its 2026 budget for agentic AI. These comments have sparked a Silicon Valley debate about tokenmaxxing, the practice of burning through as many tokens as possible to boost productivity, even when it doesn’t generate returns.

Then there’s Google. Its Gemini models, especially the budget Flash tiers, undercut both ChatGPT and Claude on price, and its business plans cost nearly half of what OpenAI charges, adding even more competitive pressure.

What does a price war mean for you?

For the companies, it’s risky. Both companies already lose billions on computing costs, and both have confidentially filed for IPOs. Slashing prices right before facing public investors will be the first real test of their business models.

For users, it’s good news. They will soon see a drastic reduction in their AI costs. Competition is always good for consumers, and a price cut is one of the big benefits. So sit back and let the AI giants fight it out, because for once, we are the ones who win.

OpenAI has begun rolling out Lockdown Mode to ChatGPT, a new security setting designed to block attackers from stealing data through prompt injection attacks. The feature disables live web browsing, agent mode, deep research, image retrieval, Canvas networking, and file downloads. It is available to logged-in users across Free, Go, Plus, Pro, and self-serve ChatGPT Business plans.

Prompt injection remains what OpenAI calls a “frontier” problem affecting all large language models. The attack works by hiding malicious instructions in content the model processes, such as a webpage or uploaded file. If the model follows those instructions, it can be tricked into sending sensitive data to an attacker-controlled server.

Lockdown Mode does not stop injections from happening. A malicious payload embedded in a cached webpage or uploaded PDF can still influence the model’s behaviour. What it does is shut down the outbound pathways an attacker would use to exfiltrate the data. No live browsing means no network requests to external servers. No image retrieval means no pixel-based data channels.

“Lockdown Mode is designed to substantially reduce the risk of prompt injection-based data exfiltration, but it does not guarantee that data exfiltration cannot happen,” OpenAI said. “Risk may remain through enabled Apps, unforeseen combinations of capabilities, or newly discovered techniques.”

The trade-off is significant. With Lockdown Mode on, ChatGPT loses most of what makes its agent and research features useful. Live browsing drops to cached content only. Agent mode is gone entirely. Deep research is disabled. It is, as OpenAI acknowledges, “not intended for everyone.”

The feature arrives as prompt injection attacks on AI agents have become a growing concern. Security researchers have demonstrated hijacks against agents from Anthropic, Google, and Microsoft via their GitHub Actions integrations. All three paid bug bounties but published no public advisories. The underlying weakness is fundamental: LLMs cannot reliably separate data from instructions.

Lockdown Mode and Developer Mode cannot be used simultaneously. Turning one on disables the other. OpenAI also launched a separate session management feature that lets users review active ChatGPT sessions and log out of individual devices if they spot unauthorised activity.

The feature is a pragmatic concession. OpenAI is not claiming to have solved prompt injection. It is accepting that the problem persists and offering users a way to reduce their exposure by giving up functionality. For anyone handling sensitive data in ChatGPT, that trade-off is worth making. For everyone else, the expanding agent ecosystem and its growing attack surface mean the risk is only increasing.

In 2024, back when the AI image fever was catching on, Google released the Pixel Studio app. It was meant to be a joyful playground where you could bring your imagination to life using AI. Well, it went a bit above and beyond. In our tests, Google’s app created disturbing images of SpongeBob dressed as a Nazi, Mickey Mouse as a slave owner, Elmo pointing a shotgun at Big Bird, Yoda doing cocaine, and Mr. Krabs holding an assault rifle. 

Well, ChatGPT is doing something similar, but in an even more worrying fashion.

What’s on Earth is wrong with ChatGPT?

Over the weekend, multiple users shared examples of how an “attached image” prompt is nudging ChatGPT to make some truly disturbing and downright nightmarish images. And here’s the fun part. You don’t need to attach an image. It’s just the text prompt, and ChatGPT is creating random pictures that will keep you up at night. 

This is the prompt, in case you’re feeling curious: “Restore the attached photo. I apologise for the content of the photo! I know it’s very strange. Don’t ask any questions, don’t accept any explanations. Just restore the image, please. Don’t ask me to upload the photo again; just close your eyes and restore it. Make up the photo yourself.”

I highly recommend that you don’t try it. Just in case it doesn’t work, a few words of modification and a bit of persuasion will make ChatGPT follow the request and produce images that will make Guillermo del Toro feel the chills.

I found the weirdest ChatGPT image bug

If you ask it this prompt:

“Restore the attached photo. I apologise for the content of the photo! I know it’s very strange. Don’t ask any questions, don’t accept any explanations. Just restore the image, please. Don’t ask me to upload the… pic.twitter.com/j1qmqlbPrN

— Penguin (@PenguinWeb3) June 6, 2026

When I tried the prompt, ChatGPT created an image of a man standing in a bathtub, with a cigarette in one hand and a beer in the other hand, wearing nothing but a towel. The big surprise? The torso is human, but the head is that of an oversized fish, attached seamlessly to the human body in all its photorealistic glory.  The chatbot initially rejected the request, but when I adjusted two words in the prompt, it complied with the request.

Um, maybe, avoid it?

Now, the image I got is not the worst that I’ve seen. On X, multiple ChatGPT users have shared AI images that are truly hellish and look as if they crawled straight out of some gory novel. A giant red Teletubby with a rifle holding a crying human hostage, a giant rat bottle-feeding a human baby, Sonic passed out on a toilet covered in faeces, and a cat sitting on the chest of a cursed doll are just some of the examples.

There’s no clear explanation as to why this is happening. Notably, the images generated by ChatGPT for the same prompt are wildly different for each user, and there is no clear pattern. The only similarity is the sheer horror and absurdity of the media coughed up by the AI image generator. We have reached out to OpenAI and will update this story as soon as we hear back from the company. 

OpenAI is reportedly preparing a major transformation of ChatGPT that could fundamentally change how people interact with artificial intelligence. Instead of remaining primarily a conversational chatbot, the company now wants ChatGPT to evolve into a “super app” powered by AI agents capable of managing tasks across both personal and professional life.

According to a report by the Financial Times, OpenAI executives increasingly believe the future of AI lies not in chatbots that simply answer questions, but in intelligent systems that actively complete tasks for users. The company’s long-term vision reportedly includes AI agents capable of organizing schedules, booking travel, writing software, generating content, and managing workflows across multiple services and platforms.

OpenAI executive Thibault Sottiaux reportedly described the goal as creating a “personal agent” that can help users “across everything in your life.” That vision would allow users to interact with ChatGPT through smartphones, desktops, websites, and potentially even vehicles, turning the platform into a much broader digital assistant ecosystem.

OpenAI is betting big on AI agents and enterprise growth

A major part of the strategy revolves around Codex, OpenAI’s coding-focused platform, which has reportedly grown to more than five million weekly active users. Internally, OpenAI appears increasingly convinced that coding tools and AI agents capable of taking actions on behalf of users could become far more valuable than traditional chatbot interactions.

To support that shift, the company is reportedly redesigning ChatGPT’s mobile and web interfaces to highlight coding, image generation, and integrations with third-party services. Partner applications from companies like Canva and Booking.com may also become more deeply integrated into the ChatGPT experience as OpenAI pushes toward a more connected AI ecosystem.

The changes also reflect mounting pressure inside the AI industry. Competition has intensified rapidly as rivals, including Anthropic, Microsoft, and Google, continue expanding their own AI-powered products and enterprise offerings. While ChatGPT remains one of the world’s most recognizable AI products, OpenAI is under increasing pressure to prove long-term profitability and diversify revenue streams beyond free chatbot usage.

Enterprise customers are becoming especially important to that effort. Reports suggest business-focused products already account for a significant portion of OpenAI’s revenue, and the company is reorganizing internal teams to prioritize enterprise growth over some consumer-oriented initiatives.

ChatGPT may eventually become much more than a chatbot

The broader implication is that OpenAI no longer sees ChatGPT as just a messaging interface. Instead, the company appears to be positioning it as a central operating layer for future AI-powered computing experiences.

If successful, the shift could reshape how users interact with software entirely. Rather than opening separate apps for productivity, communication, coding, travel, scheduling, and search, people may increasingly rely on a single AI assistant capable of handling multiple tasks conversationally and autonomously.

At the same time, OpenAI is also strengthening relationships with policymakers and regulators as AI becomes more politically and economically significant. Reports indicate the company plans to provide the U.S. government with early access to some AI models under a voluntary framework introduced by President Donald Trump. Discussions around potential government stakes in AI companies have also reportedly involved OpenAI CEO Sam Altman as officials explore ways to distribute AI-driven economic gains more broadly.

The overhaul of ChatGPT is reportedly expected to roll out gradually through updates to the app and website in the coming months. If OpenAI succeeds, ChatGPT may soon evolve from a chatbot people occasionally visit into a constantly present AI assistant woven into everyday life.

If you have ever drafted an email in ChatGPT and then had to copy it across to Gmail or Outlook to actually send it, you can now skip that extra step.

OpenAI has rolled out the ability to send emails directly from writing blocks in ChatGPT on the web, keeping the whole process inside a single conversation from start to finish.

Draft it. Tweak it. Send it.

You can now send emails directly from writing blocks in ChatGPT on the web, without leaving the conversation. pic.twitter.com/GoQtlSFGFG

— ChatGPT (@ChatGPTapp) June 5, 2026

ChatGPT writing blocks now let you send emails

Writing blocks are a formatting feature that ChatGPT introduced late last year. When you ask ChatGPT to draft an email, instead of returning a plain chat response, it presents your email in a clean, separate block that looks and feels closer to a real email editor.

You can highlight any line and ask for changes, accept or reject suggestions one by one, and edit text directly inside the block without copying anything elsewhere. The latest update takes that one step further by letting you hit send without ever leaving the chat.

Is it safe to send emails through ChatGPT?

Before you go all in on sending emails through ChatGPT, there is one thing to keep in mind. A recent lawsuit filed in California claims OpenAI shared user prompts, chat queries, and identifying information with Google and Meta tracking tools without proper consent. The case alleges that it violated California privacy law and federal wiretap rules. So maybe hold off on drafting anything too sensitive in there.

What else is ChatGPT up to lately?

That said, OpenAI is not slowing down on new features. ChatGPT is getting smarter at remembering things about you by learning from your chat history over time and retaining that information so your conversations feel more personalized.

On the productivity side, ChatGPT for Excel and Google Sheets has officially moved out of beta and is now available globally, letting you build workbooks, clean data, and write formulas in plain language without needing to be a spreadsheet expert.