Connect with us

Technologies

7 Ways Microsoft Uses AI to Make You Actually Care About Bing

It isn’t just ChatGPT on the Bing website. Microsoft blends OpenAI’s language technology with its own Bing search engine.

Microsoft Bing faces a big problem: Google utterly eclipses search engine. But Bing has a chance to grab more attention for itself with the OpenAI‘s language technology, the artificial intelligence foundation that’s made the ChatGPT service a huge hit.

For the brainier Bing to work, though, Microsoft has to get the details right. ChatGPT can be useful, but it can be flaky, too, and nobody wants a search engine they can’t trust.

Microsoft has put a lot of thought and its own programming resources into the challenge. It’s wrestled with issues like how AI-powered Bing shows ads, reveals its data sources, and grounds the AI technology in reality so you get trustworthy results, not the digital hallucinations that can be hard to spot in machine-generated information.

I spoke to Jordi Ribas, leader of Bing search and AI, to dig more deeply into the overhauled Bing search engine. He’s a big enough fan that he used the technology to help him write his boss a memo about it. «It probably saved me two to three hours,» he said, and it improved the Spanish executive’s English, too.

When the technology expands beyond today’s very small test group, it’ll let millions of us dig for much more complicated information, like whether an Ikea loveseat will fit into your car. And we’ll all be able to see whether it truly gives Google a run for its money. But for now, are seven aspects of Bing AI that I learned.

Bing AI isn’t just a repackaged version of ChatGPT

Microsoft blends its Bing search engine with the large language model technology from OpenAI, the AI lab that built the ChatGPT tool that’s fired up excitement about AI and that Microsoft invested in. You can get ChatGPT-like results using Bing’s «chat» option — for example, «Write a short essay on the importance of Taoism.» But for other queries, Bing and OpenAI technology are blended through an orchestration system Microsoft calls Prometheus.

For instance, you can Bing, «I like the band Led Zeppelin. What other musicians should I listen to?» OpenAI first paraphrases that prompt to «bands similar to Led Zeppelin,» then repackages Bing search results in a bulleted list. Each suggestion, like Fleetwood Mac, Pink Floyd and the Rolling Stones, comes with a two-sentence description.

Bing AI cites its sources — sometimes

When you give ChatGPT a prompt, it’ll respond with text it generates, but it won’t tell you where it got that information. The AI system is trained on vast amounts of the information on the internet, but it’s hard to draw a direct line between that training data and ChatGPT’s output.

On Bing, though, factual information is often annotated, because Bing knows the source from its indexing of the web. For example, in the Led Zeppelin prompt above, Bing includes a link at the top of its answer to a Musicaroo post, 13 Bands That Sound Like Led Zeppelin, and includes that link and others from MusicalMum and Producer Hive.

That sourcing transparency helps address a big criticism of AI, making it easier to evaluate whether the response is accurate or a mere AI hallucination. But it doesn’t always appear. In the essay on Taoism above, for example, there aren’t any sources, footnotes or links at all.

Some source links are ads that make Microsoft money

The Bing AI’s elaborate answers provide a new way for Microsoft to generate money from ads. In traditional Bing searches, the «organic» search results that Bing judges to be most relevant are separate from items placed by advertisers. But with Bing AI searches, the two types of information can be blended.

For example, in its response to the query «plan me a one-week trip to Iceland without a rental car,» AI-powered Bing suggests several destinations. In one of them, several words are underlined: «You can visit places like Vík, Skógafoss, Seljalandsfoss, and Jökulsárlón glacier lagoon by joining a multi-day tour or taking a bus.» Hovering over that link shows three sources for that information and an ad from a tour company. The advertisement is the top item of the three and is labeled «ad.»

«When you look at those citations, sometimes they are ads,» Ribas said. «When it’s more of a purchasing intent query, you hover over it and you’ll see the list of the references and sometimes it’s an ad. Then sometimes in the conversation itself, you’re going to see product ads, like if you do a hotel query.»

Ad revenue is a big deal, since it takes weeks of work on an enormous cluster of computers for OpenAI to build a single update to its language model, and OpenAI CEO Sam Altman estimates it costs a few cents to process each ChatGPT prompt. Bing, even though it’s a distant second to Google in the search engine market, still handles millions of queries a day.

Google plans to open access to its Bard AI chatbot soon, but it won’t be including ads to begin with.

OpenAI-boosted results are more relevant than plain old Bing

The fundamental measure of a search engine’s usefulness is whether its results are relevant, and the OpenAI technology brings a huge boost in the measurement that Microsoft uses to score its search engine results’ relevance.

«My team, working super, super hard in a given year, might move that metric by one point,» Ribas said, but OpenAI’s technology boosted it three points in one fell swoop. «It’s just never happened before in the history of Bing,» Ribas said.

That relevance boost is just for ordinary search results, Ribas added. OpenAI’s technology can further improve Bing with its chat interface that offers more elaborate answers and a follow-up exchange.

OpenAI makes Bing better with languages besides English

One particular area where Bing has been weak is searches that aren’t in English, and Ribas said OpenAI helps there. A lot of Bing’s three-point gain in relevance scoring «came from international markets,» Ribas said.

OpenAI’s large language model, or LLM, is trained with text from 100 languages. «Catalan is my first language. I can have a dialogue in Catalan. It works really, really well,» Ribas said

Bing brings OpenAI’s results up to date

Large language models like OpenAI’s GPT-3.5, the foundation for ChatGPT, are slow to build and improve, which means they don’t move at the speed of the web or of conventional search engines. GPT-3.5, for example, was trained in 2021, so it doesn’t have any idea about Russia’s invasion of Ukraine, the effects of recent inflation on consumers, or Xi Jinping securing his third term as general secretary of the Chinese Communist Party.

Bing often does know this more recent information, though. «When you bring in the Bing results, then you will get fresh results on that complete answer,» Ribas said.

Bing ‘grounds’ OpenAI’s flights of fancy

Microsoft uses its Bing data to try to avoid situations where OpenAI’s more creative technology could lead people astray. The more factual a query and answer are, the more Bing’s technology is used in the answer, Ribas said. This «grounding» significantly reduces AI’s problems with making stuff up: «It will reduce hallucination, which is … an ongoing battle,» Ribas said.

But Microsoft doesn’t want its grounding system to squash all the magic out of the AI. There’s a reason ChatGPT has been so captivating. The Prometheus system decides on the priorities for each query.

«We had to find the sweet spot between over-grounding the model and keeping it interesting,» Ribas said. «We have a measurement of the interestingness of the results, and we have a measurement for the groundedness of the results. The more the query is looking for something very factual, the more we weight the grounded. The more the query is supposed to be creative, the less we weight the grounded. I kept telling my team, I want my cake and eat it too.»

Related Topics:

Technologies

Grammarly Pushes Beyond Proofreading With AI-Powered Writing Guidance

Grammarly dropped agents to spot plagiarism, cite sources and maybe even boost your GPA.

Grammarly is expanding beyond its grammar-checking roots. The company has announced the launch of several specialized AI «agents» and a new writing tool called Grammarly Docs, designed to help students and professionals with everything from drafting essays to polishing workplace emails.

It’s another example of generative AI expanding beyond general-purpose chatbots like ChatGPT and Gemini into more specialized domains. Other examples of gen AI in educational circles include Google’s NotebookLM and OpenAI’s new study mode for ChatGPT.

AI agents are digital helpers that go beyond traditional chatbots to understand context and assist in reaching your goals. Grammarly’s AI agents assist by offering feedback, predicting reactions, finding sources and more to increase efficiency in workflows. 

Read also: Grammarly AI: This Free AI Tool Will Easily Fix Your Grammar

What’s available now for Grammarly AI

The update introduces nine agents that move Grammarly into a more collaborative role. Instead of just correcting grammar or suggesting phrasing, the agents are intended to actively work alongside users. One predicts how a professor or manager might respond to a draft. Another offers an estimated grade based on an uploaded rubric. Others handle citation generation, proofreading, paraphrasing, plagiarism checks and AI detection. The tools are built directly into Docs, a «distraction-free» writing environment where all the agents can be summoned in context, according to the company.

As students head back to classrooms and colleges, Grammarly is looking to position itself as a study companion and writing coach rather than merely a browser extension. The company cites research showing that while only a small share of students feel confident using AI in professional settings (18%), most employers expect AI literacy from job candidates. By emphasizing skill-building and responsible use, Grammarly says it wants to bridge that gap rather than simply automate assignments.

«The launch of our new agents and AI writing surface marks a turning point in how we build products that anticipate user needs,» Luke Behnke, Grammarly’s vice president of product management, said in the company’s press release. «We’re moving beyond simple suggestions to intelligent agents that understand context and actively help users achieve their communication goals.» 

For professionals, Grammarly is marketing the tools as a way to tailor communication for different audiences. The Reader Reactions agent, for example, can highlight whether an email comes across as too vague or too blunt. And the Expert Review tool provides industry-specific feedback without requiring specialized prompts.

The launch also marks the debut of Docs as a standalone writing hub. Until now, Grammarly has functioned mostly as a browser extension layered on top of other apps, like Chrome or Google Docs. Grammarly Docs signals a push to keep users inside the platform’s own environment, though the company says it will expand agent functionality to the more than half a million apps and sites where its tools already appear.

The new features are rolling out immediately for free and premium subscribers, though plagiarism and AI detection remain locked behind the paid plan. Enterprise and education customers will also gain access later this year.

Early reactions to Grammarly’s AI agents 

Early reactions suggest strong interest from students and educators alike as the company shifts from a grammar checker to a productivity platform. Educators have noted the potential benefits and risks of tools like the AI Grader. Some users on social media welcomed the update as a way to cut through the anxiety of essay writing, while others questioned whether it might make students too dependent on machine feedback.

The launch comes just months after Grammarly raised $1 billion to fuel its AI pivot and acquired the email startup Superhuman. Together, those moves point to an ambitious strategy for the company: one that seeks to transform Grammarly from a background utility into a full-fledged productivity suite powered by AI. 

Continue Reading

Technologies

Today’s Wordle Hints, Answer and Help for Aug. 20, #1523

Here are hints and the answer for today’s Wordle No. 1,523 for Wednesday, Aug. 20.

Looking for the most recent Wordle answer? Click here for today’s Wordle hints, as well as our daily answers and hints for The New York Times Mini Crossword, Connections, Connections: Sports Edition and Strands puzzles.

Today’s Wordle puzzle is a fun word. Two letters repeat, so don’t forget once you find a correct letter, you can reuse it in another spot. If you need a new starter word, check out our list of which letters show up the most in English words. If you need hints and the answer, read on.

Today’s Wordle hints

Before we show you today’s Wordle answer, we’ll give you some hints. If you don’t want a spoiler, look away now.

Wordle hint No. 1: Repeats

Today’s Wordle answer has two separate repeated letters.

Wordle hint No. 2: Vowels

Today’s Wordle answer has one vowel, and it’s one of the repeated letters, so you’ll see it twice.

Wordle hint No. 3: Start letter.

Today’s Wordle answer begins with L.

Wordle hint No. 4: Animal kingdom

Today’s Wordle answer is an animal.

Wordle hint No. 5: Second meaning

Today’s Wordle answer is a domesticated pack animal of the camel family.

TODAY’S WORDLE ANSWER

Today’s Wordle answer is LLAMA.

Yesterday’s Wordle answer

Yesterday’s Wordle answer, No. 1,522 for Aug. 19, was ROWDY.

Recent Wordle answers

Aug. 15, No. 1,518: LEVEL

Aug. 16 No. 1,519: MATTE

Aug. 17, No. 1,520: LOUSY

Aug. 18, No. 1,521: ISSUE

Continue Reading

Technologies

Today’s NYT Connections Hints, Answers and Help for Aug. 20, #801

Here are some hints and the answers for the NYT Connections puzzle No. 801 for Wednesday, Aug. 20.

Looking for the most recent Connections answers? Click here for today’s Connections hints, as well as our daily answers and hints for The New York Times Mini Crossword, Wordle, Connections: Sports Edition and Strands puzzles.

Today’s NYT Connections puzzle is a real headache. The NYT puzzle writers are really pulling some obscure connections out of the air, and I did not do well today at all. Need some help? Read on for clues and today’s Connections answers.

The Times now has a Connections Bot, like the one for Wordle. Go there after you play to receive a numeric score and to have the program analyze your answers. Players who are registered with the Times Games section can now nerd out by following their progress, including number of puzzles completed, win rate, number of times they nabbed a perfect score and their win streak.

Read more: Hints, Tips and Strategies to Help You Win at NYT Connections Every Time

Hints for today’s Connections groups

Here are four hints for the groupings in today’s Connections puzzle, ranked from the easiest yellow group, to the tough (and sometimes bizarre) purple group.

Yellow group hint: Ebony and ivory.

Green group hint: They go together.

Blue group hint: Spinning.

Purple group hint: There’s a bend in these.

Answers for today’s Connections groups

Yellow group: Black-and-white things.

Green group: Pairs of rods.

Blue group: Things that rotate about a vertical axis.

Purple group: Rods that curve at one end.

Read more: Wordle Cheat Sheet: Here Are the Most Popular Letters Used in English Words

What are today’s Connections answers?

The yellow words in today’s Connections

The theme is black-and-white things. The four answers are domino, piano keys, yin-yang symbol and zebra.

The green words in today’s Connections

The theme is pairs of rods. The four answers are chopsticks, claves, knitting needles and ski poles.

The blue words in today’s Connections

The theme is things that rotate about a vertical axis. The four answers are barber pole, carousel, ceiling fan and lazy Susan.

The purple words in today’s Connections

The theme is rods that curve at one end. The four answers are candy cane, crochet hook, crook and crowbar.

Continue Reading

Trending

Copyright © Verum World Media