3 place 0 fresh

16 OpenAI Announces Benchmarks for AI Life Sciences Research. Its Best Model Failed 63.9% of the Test

Slashdot
EditorDavid @ Slashdot 1 place · today 17:34 EDT

OpenAI Announces Benchmarks for AI Life Sciences Research. Its Best Model Failed 63.9% of the Test

This week OpenAI announced a 750-task test to to measure "whether AI systems can support realistic life science research tasks, not just answer biology questions."

But while OpenAI's top-performing GPT-Rosalind model led the rankings, Slashdot reader BrianFagioli notes that "it achieved a pass rate of just 36.1 percent, failing nearly two-thirds of benchmark tasks." Nerds.xyz points out that means "the best-performing model failed nearly two-thirds of the benchmark's tasks."




The benchmark also reveale

To see detailed statistics for the news please log in »

Read the original

Add your comment
You must be logged in with Facebook to read and write comments.

A newsletter a day!

You may get 10 most important news around midday in daily newsletter. Press the button and we will send you the most important news only, no spam attached.

or register

LIKE us on Facebook so you won't miss the most important news of the day!

News from the same source
Slashdot Slashdot
Silicon Valley
George Avalos @ Silicon Valley 1 place · 02/07/2106 01:28 EDT

Newark apartment complex bought for much less than prior value

An East Bay apartment complex has been bought at a price that's well below its prior value. Read more

0

🔮
20.06.2026 ♓︎ Dear Pisces, today promises many interesting events and opportunities for personal growth and harmony. In... Read more ›
Silicon Valley
George Avalos @ Silicon Valley 2 place · 02/07/2106 01:28 EDT

PG&E buys San Jose building to bolster South Bay operations

A PG&E Corp. unit has bought a San Jose building in a move to bolster the utility's South Bay operations. Read more

0

Habr
alexlptk (StudyAI) @ Habr 1 place · today 19:08 EDT

Как объединить два фото в одно нейросетью — Проверяем как ТОП-6 ИИ соединяют 2 картинки в 1

Вы в разных городах, любимого человека физически нет рядом, а общий снимок хочется так, что аж сводит. Или на групповом фото у тебя удачное лицо, но друг моргнул. Или ты ведешь блог и тебе нужен чистый кадр «До/После» по ремонту или фитнесу, а не кривой коллаж из двух картинок встык. Раньше это решалось Фотошопом и парой часов возни со слоями. В 2026 году хватает двух исходников, одного описания - и... Read more

0 fresh

TechRadar
TechRadar 1 place · today 19:00 EDT

NYT Strands hints and answers for Sunday, June 21 (game #840)

Looking for NYT Strands answers and hints? Here's all you need to know to solve today's game, including the spangram. Read more

0 fresh

TechRadar
TechRadar 2 place · today 19:00 EDT

Quordle hints and answers for Sunday, June 21 (game #1609)

Looking for Quordle clues? We can help. Plus get the answers to Quordle today and past solutions. Read more

0 fresh

TechRadar
TechRadar 3 place · today 19:00 EDT

NYT Connections hints and answers for Sunday, June 21 (game #1106)

Looking for NYT Connections answers and hints? Here's all you need to know to solve today's game, plus my commentary on the puzzles. Read more

0 fresh

Habr
ArgusXII @ Habr 2 place · today 18:47 EDT

Предметно-ориентированная СМК: как построить живую инженерную модель качества предприятия

Систему менеджмента качества на предприятии часто воспринимают слишком узко: как набор обязательных процедур, журналов, форм, регламентов, протоколов, подписей и документов для аудита. В такой логике СМК существует рядом с реальной деятельностью предприятия: производство работает, склад принимает, закупки закупают, сервис обслуживает, ERP фиксирует документы, а система качества как будто отдельно ведёт свои формы и подтверждения.Но у СМК есть гораздо более серьёзный потенциал. Она может быть не документальн Read more

0 fresh

SlashGear
SlashGear 1 place · today 18:45 EDT

There's A Good Reason Why Android Stopped Using Dessert Names For New Versions

Android's dessert-themed version names were once a defining part of the operating system, but Google eventually decided it was time for a change. Read more

0 fresh

Habr
appet1te @ Habr 3 place · today 18:38 EDT

Теория игр в обычной жизни. Своя игра

«Моя игра, моя игра, Она мне принадлежит и таким же, как и я. Моя игра, моя игра, Здесь правила одни, и цель одна.»Предаваясь размышлизмам на стыке впф, этологии, менеджмента, преподавания и теории игр, я пришел к выводу, что разные люди(или же агенты) играют в разные игры.В прошлой заметке по теории игр, я уже описывал ситуацию, когда один игрок играет в игру сотрудничество, а другой в игру «поесть другого» или «достигнуть... Read more

0 fresh

Inc42 Media
Team Inc42 @ Inc42 Media 1 place · today 18:18 EDT

Recykal Bags $23 Mn To Take Its Waste Management Solutions Global

Waste management startup Recykal has raised $23 Mn (nearly ₹217 Cr) as part of a bridge funding round, in a… Read more

0 fresh

GSMArena.com
GSMArena.com 1 place · today 18:11 EDT

Deals: Samsung Galaxy S25 FE price drops again, OnePlus 15 and 15R, Nothing phones are on sale

Reminder: Prime Day is next week. You will need an active Prime subscription to get the lower prices, though the free trial usually works – unless you have already used it recently. This week, you don’t need Prime to get these deals. The Samsung Galaxy S25 FE stayed at MSRP for a few weeks after the launch of the Galaxy A57. Now the FE model is back where it should... Read more

0 fresh

Digital Trends
Shikhar Mehrotra @ Digital Trends 1 place · today 17:59 EDT

The Sashimi robot is real and it doesn’t fumble at slicing and dicing

A Norwegian research team built a robot that can slice and serve salmon sashimi using three arms, AI training, and a tactile sensor that knows when the blade hits the board. Read more

0 fresh

Digital Trends
Sudhanshu Kumar Mangalam @ Digital Trends 2 place · today 17:49 EDT

Apple users are being targeted by a familiar tech support scam

After years of scammers posing as Microsoft support, reports suggest Apple users are now facing a similar wave of fake tech support warnings. Read more

0 fresh

SlashGear
SlashGear 2 place · today 17:45 EDT

Torque-To-Yield Bolts: What Are They, And Why Do Automakers Use Them?

Just about every vehicle is held together using a lot of small components, including bolts. What exactly is a torque-to-yield, also known as a TTY bolt? Read more

0 fresh

Habr
900k @ Habr · today 17:30 EDT

Знакомимся с Cruzo. Часть 1. RxBucket – контейнер состояний и конфигураций компонентов на фронте

Не так давно, я наконец выложил на github свой фреймворк cruzo – https://github.com/MaratBektemirov/cruzo. Сам фреймворк писался где-то с 2020г, в свободное от работы время. Причем большую часть времени я потратил на шаблонизатор с реактивными значениями.Я хотел сделать минималистичный, но в то же время мощный инструмент для создания простых и сложных веб-приложений. Попытался взять хорошие идеи от разных фреймворков и собрать их в одном месте. Одна из таких идей - это... Read more

0 fresh

Habr
OlegSivchenko @ Habr · today 17:01 EDT

Визит к Полигимнии: догадки о составе сверхплотного астероида

Мои постоянные читатели знают, что ранее я не раз затрагивал на Хабре тему скрытой массы и поиск гипотетических частиц или объектов, из которых может состоять тёмная материя. Базовый минимум о тёмной материи на русском языке изложен в отличной книге Йостейна Кристиансена «Невидимая Вселенная», вышедшей в 2022 году. Чаще всего рассматривается два основных варианта «скрытой массы»: либо предполагается, что она состоит из каких-то пока не известных частиц, не взаимодействующих с обычной... Read more

0 fresh

Habr
asakura201 @ Habr · today 16:43 EDT

Записная книжка, которой не было, или Почему простота — истинная добродетель

Я изучил записные книжки шести писателей-классиков и обнаружил, что ни один из них не вёл "систему управления знаниями". Их тетради были хаотичны, а сам подход не навязывал структуру. В результате исследования я сделал свою полноценную "тетрадь писателя" на Go в 3253 строки с нулём фреймворков и минимумом зависимостей. Под катом — пространное эссе о том, почему "удобно" и "просто" — разные вещи. Читать далее Read more

0 fresh

Digital Trends
Shikhar Mehrotra @ Digital Trends 3 place · today 16:40 EDT

iOS 27 puts a much better dictation experience on your iPhone, and you must enable it

iOS 27 quietly ships two dictation systems. The better one is off by default, requires 12GB of RAM, and most users will never know to enable it. Read more

0 fresh

The most popular news from the same source for the last week
Slashdot Slashdot
Slashdot
EditorDavid @ Slashdot · 06/13/2026 21:47 EDT

How Author Dave Eggers Avoids Smartphones, Internet Access, and Flock Cameras

A few weeks ago on a bike ride "inspiration struck" for Dave Eggers, reports SFGate... Without a pen and paper handy, he was stuck texting the idea to himself. The problem? Eggers doesn't own a smartphone. "It takes 20 minutes to write a sentence," Eggers said... It's a funny predicament for Eggers, given that he's arguably the city's biggest proponent of the written word... Now age 56, Eggers' latest book... Read more

0

Slashdot
EditorDavid @ Slashdot · 06/14/2026 00:34 EDT

UK Police Officer Accused of Using AI to Fake Evidence

The Sunday Times reports: A criminal investigation has begun after a police officer allegedly used AI to create evidential material in a "number of cases". Derbyshire Constabulary said an officer was being investigated over an allegation of suspected perverting the course of justice. The Crown Prosecution Service (CPS) confirmed it was engaging with defence lawyers and the courts over potentially affected cases... It is the first known allegation of AI... Read more

0

Slashdot
EditorDavid @ Slashdot · 06/14/2026 03:34 EDT

Four LTS Java Versions Get End-of-Support in a Three-Year Window (2029-2032)

Simon Ritter joined Sun Microsystems in 1996 and spent time working in both Java development and consultancy. He's now written an opinion piece for InfoWorld warning that "Between 2029 and 2032, every currently supported long-term support (LTS) version of Java will reach end-of-support within a single three-year window." That's Java 17 in 2029, Java 8 in 2030, Java 21 in 2031, and Java 11 in 2032... On paper, this looks... Read more

0

Slashdot
EditorDavid @ Slashdot · 06/14/2026 07:34 EDT

Bitcoin Has Lost Nearly Half Its Value in 11 Months

The price of bitcoin dropped 13% down to $64,394 just in June — but there's more bad news, reports CNBC." "Bitcoin has lost nearly half its value since reaching a record high above $123,000 in July 2025." While previous bitcoin selloffs were often followed by large rebounds in price, the latest decline may prompt some investors to revisit why they own bitcoin in the first place, [says Daniel Sotiroff, associate... Read more

0

Slashdot
EditorDavid @ Slashdot · 06/14/2026 10:34 EDT

Blizzard Sues To Take Down Another Private World of Warcraft Server, Project Ascension

"Blizzard Entertainment is continuing its crusade against private World of Warcraft servers," reports the gaming news site Aftermath: The company filed a new lawsuit on Friday in a California court against the makers of Project Ascension, alleging copyright infringement, Digital Millennium Copyright Act violations, and other claims. Blizzard Entertainment claims that Project Ascension is a "lucrative way to exploit and profit from the popularity of the WoW game experience," according... Read more

0

Slashdot
EditorDavid @ Slashdot · 06/14/2026 11:34 EDT

How America's Energy Department is Building a National Platform for Doing Science with AI

America's Energy Department "wants to build a single national platform for doing science with AI," reports Communications of the ACM: It is called the Genesis Mission, and the idea is to connect the country's 17 national laboratories, their supercomputers, scientific datasets, and a growing layer of AI models and agents into one system researchers can access. The DOE has taken to calling it 'a national operating system for science.' That... Read more

0

Slashdot
EditorDavid @ Slashdot · 06/14/2026 12:34 EDT

Vintage AMD R600 Graphics Driver Sees Code Cleanups Thanks To GitHub Copilot

Phoronix reports: The AMD R600 Gallium3D driver saw 59 commits [last] Sunday to Mesa 26.2. Making this code restructuring and code cleaning all the more notable is that the improvements to this old AMD Radeon graphics driver was done in part by GitHub Copilot. Gert Wollny has been among the few open-source developers left working on the AMD R600g driver that covers from the Radeon HD 2000 series through Radeon... Read more

0

Slashdot
EditorDavid @ Slashdot · 06/14/2026 14:43 EDT

Will Meta's $14 Billion Bet on AI Ever Pay Off?

"A year after spending over $14 billion to bring in Alexandr Wang and a group of his top Scale AI engineers to revamp its artificial intelligence efforts, Meta is at least back on the map in AI," reports CNBC, "though it's still far behind OpenAI, Anthropic and Google in the market." Wang's big accomplishment was the delivery of the Muse Spark AI model in April, marking Meta's first jump into... Read more

0

Slashdot
EditorDavid @ Slashdot · 06/14/2026 16:11 EDT

As 'Disclosure Day' Premieres, Steven Spielberg Says He Believes Aliens Really Have Visited Earth

Steven Spielberg grants that his 1977 UFO film Close Encounters was "speculative," writes the Associated Press, but "Disclosure Day, he insists, is the real deal." "It's my first film that will be considered science fiction that I do not consider to be science fiction," Spielberg said in a recent interview. "It's much more reflective of the world as it is evolving and discoveries that are being made as we speak."... Read more

0

Slashdot
EditorDavid @ Slashdot · 06/14/2026 17:35 EDT

UK Scientists See Little Evidence for Claims Smartphones Are Rewiring Kids' Brains

UK's Members of Parliament (MP) were "looking for proof that smartphones and social media are rotting children's brains," writes The Register — but they got "a less satisfying answer from neuroscientists on Wednesday: nobody can really prove it." Appearing before the Science, Innovation and Technology Committee this week, three researchers spent much of the session explaining that concern and evidence are not quite the same thing. Asked what evidence exists... Read more

0

Most popular sources

  • You see 363 news out of 363.
  • Sources 61 out of 61.
Startups News 0%
Financial Times 0%
ScienceDaily 0%
The Fintech Times 0%
Wired 0%
View sources »

LIKE us on Facebook so you won't miss the most important news of the day!

20.06.2026 19:30
Last update: 19:15 EDT.
News rating updated: 02:20.

What is Times42?

Times42 brings you the most popular news from tech news portals in real-time chart.
Read about us in FAQ section.


Times42 © 2026