Technology
The Movie Gen Meta model provides realistic video with sound, so we can finally have infinite Moo Deng

No one really knows yet what generative video models are good for, but that does not stop firms like Runway, OpenAI, and Meta from investing thousands and thousands of their development. The latest version of Meta is titled Movie Genand true to its name, it turns text prompts into relatively realistic video with sound… but luckily no voice yet. And it’s sensible that they do not post it publicly.
Movie Gen is definitely a set (or “cast” as they call it) of basic models, the most important of which is the text-to-video bit. Meta claims it outperforms the likes of Runway Gen3, the newest LumaLabs release, and Kling 1.5, although as all the time, this type of thing shows more that they are playing the identical game than Movie Gen winning. The specs can be present in Meta’s release article describing all components.
Sound is generated to match the content of the video, adding, for instance, engine sounds corresponding to the movements of the automotive, the sound of a waterfall within the background, or thunder mid-video when required. He’ll even add music if he thinks it is vital.
It was trained on “a combination of licensed and publicly available datasets” that they called “proprietary/commercially sensitive” and provided no further details about it. We can only guess, which means there are various videos on Instagram and Facebook, in addition to some partner materials and rather more, that usually are not properly shielded from scrapers – i.e. “publicly available”.
However, Meta is clearly aiming here not only to say the “state-of-the-art” crown for a month or two, but for a practical, soup-to-nuts approach during which a quite simple material can be changed into a solid end product, a natural language prompt. Things like “imagine me as a baker baking a shiny hippopotamus-shaped cake during a storm.”
For example, one in every of the sticking points with these video generators is how difficult they have an inclination to be to edit. If you request a video of an individual crossing the road and also you realize that you just want the person to walk from right to left, not left to right. There’s a very good probability the entire shot will look different when you repeat the prompt with additional instruction. The meta adds an easy, text-based editing method where you can just say “change the background to a busy intersection” or “change her clothes to a red dress” and she is going to attempt to make that change, nevertheless it’s a change.
Camera movements are also generally understood, and things like “tracking shot” and “panning left” are taken into consideration when generating video. It’s still quite clunky in comparison with actual camera controls, nevertheless it’s significantly better than nothing.
The model limitations are a bit strange. It generates video with a width of 768 pixels, a dimension familiar to most from the famous but outdated 1024×768 resolution, but which can be thrice the width of 256, so it plays well with other HD formats. The Movie Gen system upscales this resolution to 1080p, which is the source of the claim that it produces this resolution. Not entirely true, but we’ll leave them alone because upscaling is surprisingly effective.
Oddly enough, it generates as much as 16 seconds of video… at 16 frames per second, a frame rate that nobody in history has ever wanted or asked for. However, you can also record 10 seconds of video at 24 frames per second. Lead with it!
As for why it doesn’t play the voice… well, there are probably two reasons. First of all, it is extremely difficult. Generating speech is now easy, but matching it to lip movements and lip movements to faces is a rather more complicated proposition. I do not blame them for leaving it until later because it could have been a one-minute fail. Someone might say, “generate a clown delivering the Gettysburg address by riding around on a little bicycle” – nightmare fuel primed for popularity.
The second reason might be political: releasing a deepfake generator a month before the major elections is… not one of the best for optics. A practical preventive step is to barely limit its capabilities so that if malicious actors try to make use of it, it requires real work on their part. You can actually mix this generative model with a speech generator and an open mouth sync generator, but you can’t just generate a candidate making crazy claims.
“Movie Gen is currently purely an AI research concept, and even at this early stage, security is a top priority, as it is with all of our generative AI technologies,” a Meta representative said in response to TechCrunch’s questions.
Unlike, say, Llama’s large language models, Movie Gen is not going to be publicly available. You can replicate these techniques to some extent by following the research paper, however the code is not going to be published apart from the “baseline evaluation prompt dataset,” a record of the prompts used to generate the test videos.
Technology
Space Solar Startup Aetherflux collects USD 50 million for the introduction of the first version of the spatial demo in 2026

Aetherflux, a start-up with a cosmic sunny founded by Baiju Bhatt, billionaire co-founder Robinhood, collected $ 50 million in the A series round, because it really works on the first demonstration of low land orbit in 2026.
The startup from San (*50*) in California, which got here out of Stealth in October last yr, goals to finally start the constellation of low soil orbit satellites, which might collect and transfer solar energy on to “ground stations” on Earth. This is an concept that was initially attributable to telling Isimov’s telling “reason”. Bhatt focuses on the transformation of this inspired science fiction concept into reality.
But firstly, Aetherflux must persuade the satellite to orbit to prove technology, “show that we have made transformal progress from people who do not have power from place to, for the first time, for the first time there is power from the place for people for the first time,” said Bhatt, founder and general director of the startup.
At least that is the goal next yr, which shall be supported by Fresh Capital Aetherflux. The round brings total Aetherflux funds to $ 60 million after Bhatt has invested $ 10 million in its own funds in the company. The round A round was led by the Ventures and Interlagos indexes, with the participation of groundbreaking energy projects of Bill Gates, Andreessen Horowitz and Nea, in addition to several other interesting names equivalent to Jared Leto.
Bhatt, who joined us in the TechCrunch Equity podcast at the starting of this yr, told Techcrunch that Aetherflux would use funds to employ a bigger number of engineers and invest in technology and infrastructure needed for its first few missions.
“Our team is now focused primarily on building a load, which is located at the top of the bus … which has all the power generated by a satellite bus and turns it into laser energy,” said Bhatt.
Aetherflux uses Apex Space satellite bus. The satellite bus is the basic structure and satellite system that gives basic functions for its operation, equivalent to power, drive and communication. Most buses generate energy through solar panels, and Bhatt says that power – as much as a kilo of energy – shall be sent back to the ground.
After the receipt shall be “ground stations” Aetherflux, consisting of photovoltaic boards, which convert sunlight into energy stored in batteries for later use. Bhatt said that his team, which consists of engineers and researchers from NASA, Spacex, Lockheed Martin, Anduril and the American Navy, can be working on constructing the first Aetherflux ground station. The startup has no place for the station yet, but evaluates military sites where there may be more controlled airspace.
In the future, Bhatt claims that the goal is to construct small, portable ground stations – with a diameter of 5 to 10 meters – to introduce electricity to the most distant locations.
“We would like to demonstrate (with the first mission), it is to join the end,” said Bhatt. “We want to be able to show that we actually have electricity on Earth and use it to illuminate light installations or perform electronic items on Earth.”
Few achieved the feat of sending solar energy from space to earth. One of the only successful missions was in 2023, when scientists Caltech’s Space Solar Power Project The displayed wireless power transfer from low Earth’s orbit using microwave radiation. This has proved this idea, but it surely will not be in the state of Aetherflux for the scalable, industrial system.
Eetherflux increases falls at the back Prize From the Energy Health improvement fund of the Defense Department to develop cosmic solar energy for the US army.
(Tagstotransate) aetherflux
Technology
Spelman organizes the game Dżem to build a hbc gaming pipeline

The event took place from March 28 to 30 with Hackaton, workshops and network events.
Spelman College wants the game industry to be “E” for everybody. HBCU hosted the third annual game from games to encourage more black people to take part in creating video games.
When the world becomes much more digital, with an adult video game industry, Spelman wants black professionals to take places at the table. HBCU Jam hopes to encourage students with this lucrative profession path by constructing calls and supporting opportunities.
This yr the game It began completely by the team led by students by the senior computer science Major Major Denee Denee. Co -chairing older “Comp Sci”, Nia Brunson, an eight -person team used the Spelman innovation laborator as the seat of the conference.
“Innovation laboratory began so small and then it was an amazing space,” Brunson explained, “Now, with this new dedicated space, students have even more learning and creating opportunities. School and team deserve it, and I think they will do amazing things for Spelman and the entire HBCU community.”
Trope added: “I am a great supporter of jams and hackatons because they give you the opportunity to assess their skills and work on something you are really proud of.”
Event began From March 28 to 30, allowing many without experience as well as to the interest in games to proceed passion on this field. Game Jam began with the inaugural conference before the start of the 24-hour hackaton, wherein students met in teams to create their very own video games.
Brunson believes that this support could make everyone feel welcome in the gaming industry, no matter initial knowledge on this subject. The co -chairman also formatted the game to be sure that that the participants had enough time to work in Hackathon before workshops and network events.
“I love that playing jam welcomes people without the previous development of the game. Over 50% of our applicants are new in games,” said Brunson. “That is why we organize workshops on the creation of assets, the use of unity and ensuring mentoring – that everyone feels supported.”
Students from nine HBCu took part in evolution, and technological sponsors reminiscent of Zynga, Microsoft, Unity, Boeing and Codehouse are also joining the fun with prizes for participants. Although black professionals constitute only 5% of the workforce, which is confirmed by the International Association of Dewelopers, this initiative goals to solve this method gap without delay.
For Jaycee Holmes, a professor of interactive media and co -director Spelman Innovation Lab, Jam encourages enthusiasts of black games to know that these works are already waiting for them.
“We want them to realize what they are capable of and understand that there is a friendly game industry willing to their votes.”
Technology
Altman Foling Drama itself listed in the new book Fragment

Fragment of the upcoming book “Optimist: Sam Altman, Opeli and Race to Invent the Future” offers new details About why the Opeli board briefly slowed down the general director of Altman in 2023.
The book written by the Wall Street Journal reporter, Keach Hagey, claims that members of the Management Board of the Non -Profit organization were increasingly concerned after learning about problems akin to OpenAI Startup Fund, which was actually personally owned by Altman.
At the same time, the co -founder of Ilya Sutskever and Cto Mira Murati reportedly collected evidence of what they perceived as toxic and dishonest behavior of Altman, together with the screenshots of the Slack Channel screen. For example, Altman allegedly claimed that the company’s legal department said that the Turbo GPT-4 didn’t must be checked by a joint security committee, but the best lawyer of the company refused this.
After Sutskever provided this evidence to the board members, they moved to Altman and the appointment of Murati as a brief director. But this failed quickly, and Opeli employees (including Sutskever and Murati) signed a letter demanding the return of Altman – which he soon did, and Sutskever and Murati leave, after which go to their very own startups.
(Tagstotransate) ILYA SUTSKEVER (T) MIRA MURATI (T) OPENAI (T) Altman
-
Press Release12 months ago
U.S.-Africa Chamber of Commerce Appoints Robert Alexander of 360WiseMedia as Board Director
-
Press Release1 year ago
CEO of 360WiSE Launches Mentorship Program in Overtown Miami FL
-
Business and Finance10 months ago
The Importance of Owning Your Distribution Media Platform
-
Business and Finance1 year ago
360Wise Media and McDonald’s NY Tri-State Owner Operators Celebrate Success of “Faces of Black History” Campaign with Over 2 Million Event Visits
-
Ben Crump12 months ago
Another lawsuit accuses Google of bias against Black minority employees
-
Theater1 year ago
Telling the story of the Apollo Theater
-
Ben Crump1 year ago
Henrietta Lacks’ family members reach an agreement after her cells undergo advanced medical tests
-
Ben Crump1 year ago
The families of George Floyd and Daunte Wright hold an emotional press conference in Minneapolis
-
Theater1 year ago
Applications open for the 2020-2021 Soul Producing National Black Theater residency – Black Theater Matters
-
Theater10 months ago
Cultural icon Apollo Theater sets new goals on the occasion of its 85th anniversary