Aggregator

OpenAI's latest reasoning models, o3 and o4-mini, hallucinate more frequently than the company's previous AI systems, according to both internal testing and third-party research. On OpenAI's PersonQA benchmark, o3 hallucinated 33% of the time -- double the rate of older models o1 (16%) and o3-mini (14.8%). The o4-mini performed even worse, hallucinating 48% of the time. Nonprofit AI lab Transluce discovered o3 fabricating processes it claimed to use, including running code on a 2021 MacBook Pro "outside of ChatGPT." Stanford adjunct professor Kian Katanforoosh noted his team found o3 frequently generates broken website links. OpenAI says in its technical report that "more research is needed" to understand why hallucinations worsen as reasoning models scale up.

Read more of this story at Slashdot.

EDEN CONFIDENTIAL: When a house is bought by a former Tory minister, you might think a boost to its value would follow. However, these days, such ownership seems to reduce it.

"I woke up in the morning looking like I've just had a facial"

A quarter of Keir Starmer's ministers belong to the militant union behind the Birmingham bin strikes crisis, it can be revealed.

Victoria Beckham shared some more snaps from her birthday dinner on Friday night as her 51st birthday celebrations continued with her family and friends. 

Women's rights groups are now calling for organisers to take action to comply with this week's Supreme Court ruling, which said that women are defined by biological sex and not gender .

For an insight into the current state of the British penal system, the case of Denny De Silva is as instructive as it is worrying.

The duo have got plenty of tongues wagging thanks to their super close relationship, with fans previously left baffled after he called her his 'girlfriend'.

The list of genders includes 'pangender', ' transgender person' and bizarre, largely unknown terms like 'androgyne' and 'neutrois'.

Researchers at the University of California, Berkeley, say that by stimulating individual cells in the retina that the laser pushed their perception beyond its natural limits.

The Love Island star took to his Instagram Stories on Friday night to reveal that they have called time on their romance.

The woman was struck by a vehicle at Engineers Way at around 11.10pm last night near Wembley Arena after a concert by reggae artist Alkaline.

Locals in upmarket Jesmond, Newcastle, resorted to the extreme measures after looters started rifling through their waste, leaving a trail of litter in their wake.

The disgraced family of Captain Tom have been hit my another major blow - and this time it involves money.

US President Donald Trump blithely declared on Monday: 'I was told they made a mistake.' A mistake? Let's consider what happened in Sumy on Palm Sunday.

Butt is alleged to have attacked the guard during the event at Soho Farmhouse near Great Tew, Oxfordshire in January.

With macOS now 24 years old and Apple officially designating all Intel-based Mac minis as "vintage" or "obsolete," The Register takes a look at new internet tools that help keep vintage Macs online and surprisingly relevant: Cameron Kaiser of Floodgap Systems is a valuable ally. His retro computing interests are broad, and we've mentioned him a few times on The Register, such as his deep dive into the revolutionary Canon Cat computer, and his evaluation of RISC-V hardware performance. Back in 2020, he revived the native Classic Mac OS port of the Lynx web browser, MacLynx. Earlier this month, he came back to it and has updated it again, including adding native Mac OS dialog boxes. His account is -- as usual -- long and detailed but it's an interesting read. He also maintains some other web browsers for elderly Macs, including TenFourFox for Mac OS X 10.4 and Classilla for Mac OS 8.6 and 9.x. If you're not up to git pull commands and elderly Mac OS X build tools, then there is a fork of TenFourFox that may be worth a look, InterWebPPC. It's not current with the new batch of patches, but we can still hope for another build. In other "Classic on the internet" news, although it's not a huge amount of use on its own, there's also a newly released Classic Mac OS version of Mbed-TLS on GitHub. This ports the SSL library -- also used in the super-lightweight Dillo browser -- to the older C89/C90 standard, so that it can build in CodeWarrior and run with OpenTransport from Mac OS 9 right back to later versions of Mac OS 7. Modern macOS is UNIX certified and as such it's not all that dissimilar from other Unix-like OSes, such as Linux and the BSD family. Classic Mac OS is a profoundly different beast, which makes porting modern code to it a complex exercise -- but equally, it's a good learning exercise, and we're delighted to see 21st century programmers exploring this 1980s OS. That may be part of the motivation behind the newly announced and still incomplete SDL 2 "rough draft" that appeared a week ago. It builds on the existing SDL 1.2 port, but so far, it's less complete -- for instance, there's no sound support.

Read more of this story at Slashdot.

Lola Young proved that the show really must go on as she powered through her Coachella set last Friday. 

Sir Keir Starmer urged Donald Trump to drop his tariffs on British exports yesterday after the US President warned he could keep 'substantial' levies in place.

After the frenzied busyness of the past week, and the momentous ceremony of Easter Sunday yet to come, I shall count it a success if I manage not to set myself on fire.