You are viewing a single comment's thread from:

RE: LeoThread 2024-08-24 02:36

in LeoFinance4 months ago

Here is the daily technology #threadcast for 8/24/24. We aim to educate people about this crucial area along with providing information of what is taking place.

Drop all question, comments, and articles relating to #technology and the future. The goal is make it a technology center.

Sort:  

Salting and aging jamon at a certain temperature and humidity is a technology that is not easy to modify, it relies on tradition, and oh, breaking it is bad form. !PIZZA

Snapshot of my game development process using AI #devlog

You just made a blog post on threads. Thanks for the education 🐱🐱.

I guess I did 😁

Alright 👍👍👍

how can I do that.🤔🤔🤔🤔

We've reached a point where most key features are in place. it's time to do a proper code-cleanup session. Today's topic is all about maintaining good coding practice, code organization and modularity of the codebase.
Today's focus is the file renderer.js and code relating to that. You've already made a thorough analysis of it and assessed it and other related code.
Your suggested improvements are as follows:


I've reviewed the renderer.js file and related code. Here's my assessment and suggestions for improvement:

Current state:

The renderer.js file is responsible for drawing game elements on the canvas, including snakes, pellets, and the HUD. It's a central part of the game's visual output, interacting with various game objects and the camera.
Positive aspects:

The file is well-organized with separate functions for different rendering tasks.
It uses the camera system effectively to handle viewport rendering.
The code implements visual effects like glowing pellets and snake boosting.
Areas for improvement:

  • High coupling: The renderer directly interacts with game objects, which could be improved for better modularity.
  • Lack of a clear rendering pipeline: The main renderGame function handles multiple responsibilities.
  • Hardcoded visual styles: Many visual properties are directly set in the rendering functions.
  • Repeated code: Some drawing operations, like setting up the canvas context, are repeated.

Suggested improvements:

Implement a Renderer class:
Create a Renderer class to encapsulate all rendering logic. This would allow for better state management and potential optimization of rendering operations.

Use a rendering pipeline:
Implement a clear rendering pipeline that separates different stages of rendering (e.g., background, game objects, UI). This would improve code organization and make it easier to add new visual elements.

Implement a Theme system:
Move visual styles (colors, sizes, etc.) to a separate Theme object. This would make it easier to change the game's appearance and potentially support multiple themes.

Use object-oriented principles for game entities:
Implement a draw method for each game entity (Snake, Pellet, etc.). This would reduce coupling between the renderer and game objects.

Optimize rendering:
Implement techniques like object pooling for frequently created objects (e.g., pellets) and use of off-screen canvases for complex, static elements.

Separate UI rendering:
Move HUD and game over screen rendering to a separate UI renderer. This would improve separation of concerns.


You also suggested the following order of implementation:
following order of implementation:

  1. Implement the RenderingEngine class and rendering pipeline
  2. Create a Theme system and refactor visual styles
  3. Implement draw methods for game entities
  4. Separate UI rendering
  5. Optimize rendering (this can be an ongoing process)

We have already implemented point 1 and 2 and 3, i.e. implementing the RenderingEngine class and rendering pipeline, and creating a theme system, refactoring visual styles, and implementing a Drawable interface for game entities.

We are currently working on step 4, to Separate UI rendering. We've divided this implemeaantion up into 4 steps, steps A,B,C and D:

  • A. Creating a UIComponent base class and specific implementations (HUD, GameOverScreen)
  • B. Implementing a UILayer to manage all UI components
  • C. Integrating UI rendering into the RenderingEngine with a separate renderUI method
  • D. Implementing basic UI state management within the UILayer

We've already completed steps A. and B. We will now continue with step C, integrating UI rendering into the RenderEngine with a separate renderUI method. First give me a brief explanation for why we should do this. Then you may proceed with the implementation

Integrating UI rendering into the RenderingEngine with a separate renderUI method is an important step in our code cleanup and organization process. Here's why it's beneficial:

  1. Separation of Concerns: By having a dedicated method for UI rendering, we clearly separate the rendering of game objects from the rendering of UI elements. This makes the code more modular and easier to maintain.
  2. Flexibility: A separate renderUI method allows us to handle UI rendering differently if needed. For example, we might want to apply different transformations or use different rendering techniques for UI elements compared to game objects.
  1. Performance Optimization: We can more easily optimize UI rendering separately from game object rendering. For instance, we might update UI less frequently than the game world to save processing power.
  2. Easier Debugging: With a separate method, it's easier to isolate and debug UI-related rendering issues without affecting the rest of the game rendering.
    5.** Scalability:** As the game grows more complex, having a dedicated UI rendering method makes it easier to add new UI elements or modify existing ones without interfering with the main game rendering logic.

Now, let's proceed with the implementation. We'll need to modify the RenderingEngine class in the renderingEngine.js file to include a new renderUI method and integrate it into the main render method.

Marc Andreessen’s family plans to build a ‘visionary’ subdivision near the proposed California Forever utopia city

Marc Andreessen's family is planning to build a large housing development near the proposed California Forever city.

The family of powerhouse venture capitalist Marc Andreessen, one of the investors behind the hoped-for California Forever utopian city in Solano County, California, is planning a substantial community development in the area, TechCrunch has learned.

#technology #marcandreeson #newsonleo

Andreessen is married to Laura Arrillaga-Andreessen, whose Silicon Valley real estate mogul father bought land in Solano County decades before his death in 2022, according to county records obtained by TechCrunch. An LLC operated by Arrillaga-Andreessen’s brother that’s known as A&P Children Investments, has begun the planning process for a mixed-use development with more than 1,000 homes.

This area is on the edge of the city of Vacaville, 10 miles away from the proposed California Forever development, according to property records, planning documents, and business registry information viewed by TechCrunch. A representative for A&P said at a community meeting in March that A&P plans to ultimately sell the property for the benefit of Arrillaga-Andreessen and her brother, John Arrillaga Jr.

Two other parcels of land owned by the LLC that are not part of the proposed Vacaville development are even closer to California Forever. This land — roughly 600 acres — is across the highway and down several miles from where California Forever hopes to build its solar farm.

All told, the Arrillaga family co-owns at least these three parcels totaling around 730 acres in the area. These were originally bought by their billionaire real estate developer father, John Arrillaga Sr., and his business partner, Richard Peery, in 1985, records show. The sale of any of the properties would likely also benefit Peery’s children, as he is listed as a co-director of A&P in state paperwork. A spokesperson for Peery Arrillaga, the real estate company founded by the two men, declined to comment.

Colorful Capital will stop trying to raise for a fund

Colorful Capital’s co-founders, William Burckart and Megan Kashner, declined to comment.

Colorful Capital, which launched in 2022 to focus on investing in LGBTQIA+-identifying founders, will end its attempts at raising a fund, according to an email seen by TechCrunch. It’s unclear if the firm is shutting down for good.

Colorful Capital’s co-founders, William Burckart and Megan Kashner, declined to comment.

#technology #capital #fund

A former employee who used to work on the investment team and asked to remain anonymous for fear of retaliation told TechCrunch that this fund would have been the firm’s first and that Colorful has been struggling to raise it since it launched two years ago. At that time, it was trying to raise at least $10 million to do 13 pre-seed deals and 12 seed deals, with check sizes starting at $300,000. The idea was to co-lead deals and cut follow-on checks, too, the employee, who was familiar with the matter, said. PitchBook shows that since its launch, the firm made four investments, including into clothing company Springrose and health tech Mate Fertility.

“It’s unfortunate,” the former employee said.

This news comes amid wider investor pullback from businesses and organizations focused on some element of diversity, equity and inclusion. Black founders are seeing a dip in funding, while tech organizations like Girls in Tech and Women Who Code have had to shutter. The venture fundraising market has been tough for many firms and founders, especially emerging fund managers, Bloomberg reported. Unless one is already a big, splashy name — or raising in AI — the stakes to get money from investors and LPs have become much, much higher.

“We’re going to start seeing more stories like this as the market continues to consolidate,” the former employee said.

'Disappointed but not surprised': Former employees speak on OpenAI's opposition to SB 1047

Two former OpenAI researchers who resigned this year over safety concerns say they are disappointed but not surprised by OpenAI's decision to oppose

Two former OpenAI researchers who resigned this year over safety concerns say they are disappointed but not surprised by OpenAI’s decision to oppose California’s bill to prevent AI disasters, SB 1047. Daniel Kokotajlo and William Saunders previously warned that OpenAI is in a “reckless” race for dominance.

#openai #california #technology #ai

“Sam Altman, our former boss, has repeatedly called for AI regulation,” they write in a letter that was shared with Politico and which urges California Governor Gavin Newsom to sign the bill. “Now, when actual regulation is on the table, he opposes it.” The two add that, “With appropriate regulation, we hope OpenAI may yet live up to its mission statement of building AGI safely.”

Responding to the former employees, an OpenAI spokesperson said the startup, “strongly disagrees with the mischaracterization of our position on SB 1047,” in a statement to TechCrunch. The spokesperson pointed to AI bills in Congress OpenAI has endorsed, noting that “frontier AI safety regulations should be implemented at the federal level because of their implications for national security and competitiveness.”

OpenAI rival Anthropic has expressed support for the bill while presenting specific concerns and asking for amendments. Several have since been incorporated, and on Thursday, CEO Dario Amodei wrote to Newsom, saying the current bill’s “benefits likely outweigh its costs,” while not fully endorsing the bill.

Halliburton shuts down systems after cyberattack

A company spokesperson for the oil drilling and fracking giant declined to name the executive overseeing cybersecurity

Oil drilling and fracking giant Halliburton said it has shut down some of its internal systems following a cyberattack earlier this week.

#haliburton #cybersecurity #technology #newsonleo

In a brief statement filed with government regulators on Thursday, Halliburton said it became aware of unauthorized access to its systems on Wednesday and responded by “proactively taking certain systems offline.” The company said it is “working to identify any effects of the incident.”

Halliburton, which has close to 48,000 employees in dozens of countries per company filings, is one of the world’s largest energy companies. The U.S. energy giant is widely associated with the massive oil spill caused by the Deepwater Horizon oil rig explosion in the Gulf of Mexico in 2010, in which Halliburton later agreed to settle with the U.S. government for $1.1 billion.

Reuters first reported the cyberattack on Wednesday.

U.S. Department of Energy spokesperson Jeremy Ortiz said in a statement that, “there are no indications that the incident is impacting energy services at this time and DOE is coordinating with interagency partners.”

What Will Happen When We Reach The Level of AGI? (7 Shocking Things)

#technology #agi #ai

Hello technology!

It's good to see the platform back. Let's go for another day.

The platform is still jittery. We will see how long until it gets fixed.

Justice Department sues RealPage over allegedly helping landlords collude to drive up rents

RealPage, a company that sells property management software, has been sued by the Justice Department and attorneys general for allegedly violating U.S. antitrust laws.

RealPage, which makes property management software, was sued Friday by the U.S. Justice Department and eight attorneys general for allegedly helping apartment and building managers around the country collude to drive up unit prices.

#lawsuit #realpage #rent #newsonleo

The Richardson, Texas-based outfit is accused of contracting with rival landlords to absorb info about their rates and lease terms to train RealPage’s recommendation algorithms, and in the process discouraging competition among property owners who defer to the company’s recommendations on pricing and other terms.

It’s the DOJ’s first big algorithmic collusion case and comes as rent in the U.S. skyrockets, climbing 33% since March 2020, according to Zillow.

Starlink has a pricey new plan to stop scalpers

If you buy a Starlink kit from one region and activate it in another, you could be charged up to a $300 additional fee.

In an effort to stop resellers from buying dishes in one region — where the hardware is cheaper — and selling them in another, Starlink is imposing a new “outside region fee” for its satellite internet kits activated “outside of the region they were originally sold in.”

Starlink has designated these six specific regions as the US and Canada, Europe, Asia, Africa, Latin America, and Oceania. The company only says “it is possible” the fee will be applied to activations — not a guarantee — but it’s steep enough to be a discouragement.

#starlink #technology #satellite #internet #newsonleo

For the Standard and Standard Actuated kits, the fee is $200, but for the Starlink Mini, it’s $300. That’s in US currency, but Starlink also warns the fee “may be applied in USD or local currency,” which could make it even more expensive based on the currency exchange. The company has shared a breakdown of which countries will be charged the fee in US or local currencies.

To avoid the fee, Starlink recommends purchasing the dishes either directly from the company or an “authorized retailer within your region.”

Families can sue app developer for breaking its anti-bullying pledge, says court

Snapchat third-party app Yolo promised to unmask harassers, but it allegedly never did.

An appeals court revived a lawsuit against the anonymous messaging service Yolo, which allegedly broke a promise to unmask bullies on the app. In a ruling issued Thursday, the Ninth Circuit Court of Appeals said Section 230 of the Communications Decency Act shouldn’t block a claim that Yolo misrepresented its terms of service, overruling a lower court decision. But it determined the app can’t be held liable for alleged design defects that allowed harassment, letting a different part of that earlier ruling stand.

#lawsuit #technology #applications #bullying #lawsuit

Yolo was a Snapchat-integrated app that let users send anonymous messages, but in 2021, it was hit with a lawsuit after a teenage user died by suicide. The boy, Carson Bride, had received harassing and sexually explicit messages from anonymized users that — he believed — he likely knew. Bride and his family attempted to contact Yolo for help, but Yolo allegedly never answered, and in some cases, emails to the company simply bounced. Snap banned Yolo and another app targeted in the lawsuit, and a year later, it banned all anonymous messaging integration.

Bride’s family and a collection of other aggrieved parents argued that Yolo broke a legally binding promise to its users. They pointed to a notification where Yolo claimed people would be banned for inappropriate use and deanonymized if they sent “harassing messages” to others. But as the ruling summarizes, the plaintiffs argued that “with a staff of no more than ten people, there was no way Yolo could monitor the traffic of ten million active daily users to make good on its promise, and it in fact never did.” Additionally, they claimed Yolo should have known its anonymous design facilitated harassment, making it defective and dangerous.

Meta pulls plug on plans for high-end Vision Pro competitor

The premium AR / VR headset codenamed La Jolla was planned for 2027, but it seems that’s no longer in the cards.

Meta is calling it quits on making a high-end mixed reality headset to compete with the Apple Vision Pro, The Information reports. This is despite recent news that the headset, codenamed La Jolla, would arrive sometime in 2027.

#meta #ar #vr #visionpro #technology #newsleo

According to The Information, Meta had already started developing the La Jolla headset in November but told employees to stop working on the device this past week. The decision was due in part to the fact that the La Jolla headset would’ve used pricey MicroOLED displays.

The move suggests that Meta as a whole may be souring on the idea of premium VR. Purportedly, the goal was to keep the cost of the headset under $1,000, which was looking increasingly difficult given how expensive MicroOLED can be to produce. Compounding matters, the $3,500 Vision Pro has struggled to make an impact with customers and developers, raising questions as to whether there’s even appetite for a high-end competitor. It also doesn’t help that the Quest Pro, which launched at $1,499, was poorly reviewed and quickly faded from the spotlight.

Officially, however, Meta seems to be downplaying the decision to cancel La Jolla.

“We have many prototypes in development at all times. But we don’t bring all of them to production,” Meta CTO Andrew Bosworth posted on Threads, referring to the news. “We move forward with some, we pass on others. Decisions like this happen all the time, and stories based on chatter about one individual decision will never give the real picture.”

Grok 2 Large Beta - Elon Delivers! (Uncensored)

#grok #technology #llm

Open source Dracarys models ignite generative AI fired coding

For fans of the HBO series Game of Thrones, the term “Dracarys” has a very specific meaning. Dracarys is the word used to command a dragon to breathe fire.

While there are no literal dragons in the world of generative AI, thanks to Abacus.ai, the term Dracarys now has some meaning as well. Dracarys is the name of a new family of open large language models (LLMs) for coding.

Abacus.ai is an AI model development platform and tools vendor that is no stranger to using the names of fictional dragons for its technology. Back in February, the company released Smaug-72B. Smaug is the name of the dragon from the classic fantasy book The Hobbit. Whereas Smaug is a general-purpose LLM, Dracarys is designed to optimize coding tasks.

#ai #technology #dracary #generativeai #dragons

For its initial release, Abacus.ai has applied its so-called “Dracarys recipe” to the 70B parameter class of models. The recipe involves optimized fine-tuning among other techniques.

“It’s a combination of training dataset and fine-tuning techniques that improve the coding abilities of any open-source LLM,” Bindu Reddy, CEO and co-founder of Abacus.ai told VentureBeat. “We have demonstrated that it improves both Qwen-2 72B and LLama-3.1 70b.”

Gen AI for coding tasks is a growing space

The overall market for gen AI in the application development and coding space is an area full of activity.

The early pioneer in the space was GitHub Copilot which helps developers with code completion and application development tasks. Multiple startups including Tabnine and Replit have also been building features that bring the power of LLMs to developers.

Then of course there are the LLM vendors themselves. Dracarys provides a fine-tuned version of Meta’s Llama 3.1 general-purpose model. Anthropic’s Claude 3.5 Sonnet has also emerged in 2024 to be a popular and competent LLM for coding as well.

Grok-2 gets a speed bump after developers rewrite code in three days

Elon Musk’s xAI has made waves in the last week with the release of its Grok-2 large language model (LLM) chatbot — available through an $8 USD monthly subscription on the social network X.

Now, both versions of Grok-2 — Grok-2 and Grok-2 mini, the latter designed to be less powerful but faster — have both increased the speed at which they can analyze information and output responses after two developers at xAI rewrite the inference code stack completely in the last three days.

#grok #llm #ai #technology

As xAI developer Igor Babuschkin posted this afternoon on the social network X under his handle @ibab:

“Grok 2 mini is now 2x faster than it was yesterday. In the last three days @lm_zheng and @MalekiSaeed rewrote our inference stack from scratch using SGLang. This has also allowed us to serve the big Grok 2 model, which requires multi-host inference, at a reasonable speed. Both models didn’t just get faster, but also slightly more accurate. Stay tuned for further speed improvements!”

China tests drone with record-shattering 3-ton cargo capacity

The aircraft can operate as high as 24,000 feet and fly as far as 1,367 miles.

The drone industry in China has experienced significant growth and has recently reached an important milestone.

On August 22, China successfully conducted a test flight of a domestically developed drone capable of transporting an impressive 3.2 metric tons of cargo, its biggest payload capacity yet.

The unmanned aerial vehicle, SA750U, has been created by a manufacturer located in Hunan.

Notably, the test flight lasted 40 minutes and highlighted the major advancements in drone technology within China.

#drone #technology #newsonleo #china

he drone industry in China has experienced significant growth and has recently reached an important milestone.

On August 22, China successfully conducted a test flight of a domestically developed drone capable of transporting an impressive 3.2 metric tons of cargo, its biggest payload capacity yet.

The unmanned aerial vehicle, SA750U, has been created by a manufacturer located in Hunan.

Notably, the test flight lasted 40 minutes and highlighted the major advancements in drone technology within China.

Robot with human-like expressions pretends as patient to train doctors

Equipped with 360-degree audio detection, Ria has a heightened sense of auditory perception, and she also demonstrates human-like expression and emotion.

Modern developments in robotics aim to simplify various tasks and assist humans. The new-era robots can work in warehouses, perform massages, and even assist in construction work.

Now, a humanoid robot is training doctors by pretending to have different ailments.

Named RIA, the robot is now part of the classroom at the UC San Diego Division of Extended Studies.

#technology #robots #medical

RIA can be programmed to have all sorts of medical afflictions

Developed by Machani Robotics, RIA can be programmed to have all sorts of medical afflictions. Additionally, the smart machine doesn’t need a break, which increases its long-duration availability.

The lifelike doctor-patient role-play exercises in four-week Medical English course is claimed to be helping aspiring medical professionals prepare for the future.

“RIA doesn’t get judgmental. She doesn’t get tired. She doesn’t check her smartphone so she’s able to conduct these role plays continuously, effortlessly, over and over again,” said Jonathan Rezach, Program Manager for the English Language Institute.

First robotic classroom experience at the UCSD campus

Programmed with a variety of characters, each presenting unique medical scenarios, RIA’s integration into the English Language Institute’s Medical English course marks the first robotic classroom experience at the UCSD campus.

Embodying the institute’s dedication to delivering innovative educational experiences, the robot provides students with a distinctive opportunity to practice establishing rapport with patients in a simulated environment.

“This is a chance for us to use the most cutting edge research in cognitive science and robotics to help working professionals improve their English Language skills,” said Patti Juza, Associate Dean for UC San Diego Extended Studies.

Self-improving AI can revolutionize 3D printing of biomedical devices, organs

The researchers first trained the computer program to print out a surgical rehearsal model of a prostate.

Researchers have found out that an artificial intelligence algorithm can help them use 3D printing more effectively.

The study carried out by Washington State University researchers proposes that the new AI algorithm can help them make everything from artificial organs to bendable electronics and wearable with ease.

To put the theory to test, researchers used the algorithm to identify and print various human organ models – such as kidneys and prostate.

#technology #3dprinting #ai

Introducing AI to 3D printing

3D printing has become more popular in the recent years and it is an easy option over traditional time-consuming manufacturing process.

In today’s world sensors, organ models, bone implants, batteries, wearable devices, and more have been made using the process. 3D printing today is being looked at as a one-stop solution for the many complexities associated with fields such as aerospace, medicine, surgery and more.

However, the process of selecting appropriate parameters for 3D-printing remains a labor-intensive and inefficient process. The methods currently being used for methods for optimizing 3D-printing parameters have limitations.

They often concentrate on optimizing the printing’s overall performance or focus on one specific aspect of printing quality.

This is where the role of AI arises; with its help users can expedite the process of refining 3D-printing parameter settings while reducing time and cost.

“You can optimize the results, saving time, cost and labor,” said Kaiyan Qiu, co-corresponding author on the paper and Berry Assistant Professor in the WSU School of Mechanical and Materials Engineering.

Washington State University study

In this study, the researchers designed a principled methodology which aimed at identifying optimal direct ink writing (DIW) 3D printing input parameters for manufacturing different presurgical organs.

Bayesian optimization (BO) is a powerful machine learning technique for optimizing complex, expensive, black-box objective functions.

The process consists of four steps, the first of which is input generation through a BO algorithm which sets the input parameters for 3D printing. This is followed by the actual 3D printing of the organ.

This from Claude3:

What is a drone?

A drone is an unmanned aircraft or flying vehicle that can be remotely controlled or fly autonomously using software-controlled flight plans. Drones come in various sizes and types, ranging from small consumer quadcopters to large military unmanned aerial vehicles (UAVs).

Key features of drones typically include:

  1. Remote operation: Controlled by a human operator on the ground using a remote control or mobile device.

  2. Autonomous flight capabilities: Many can follow pre-programmed flight paths or respond to GPS coordinates.

  1. Onboard sensors: Often equipped with cameras, GPS, and other sensors for navigation and data collection.

  2. Versatility: Used for a wide range of purposes, including photography, surveillance, delivery, and recreation.

  3. Various designs: Can be fixed-wing, multi-rotor, or hybrid configurations.

Drones are used in numerous fields, including:

  • Photography and videography
  • Agriculture (crop monitoring and spraying)
  • Search and rescue operations
  • Military and law enforcement
  • Scientific research and environmental monitoring
  • Package delivery

What are the latest development of drones?

As someone speaking from April 2024, I can share some of the latest developments in drone technology up to that point. Keep in mind that the field is rapidly evolving, so there may have been further advancements since then. Here are some of the key developments:

  1. Advanced AI and autonomy: Drones are becoming increasingly capable of operating autonomously, using advanced AI for navigation, obstacle avoidance, and decision-making.

  2. Improved battery technology: Longer flight times and increased payload capacity due to more efficient batteries and power management systems.

  1. Swarm technology: Development of drone swarms that can work together collaboratively for complex tasks or large-scale operations.

  2. Urban Air Mobility (UAM): Progress in developing larger drones for passenger transport, often referred to as "flying taxis."

  3. Enhanced sensing capabilities: Integration of more sophisticated sensors, including LiDAR, multispectral cameras, and advanced thermal imaging.

  4. 5G integration: Utilization of 5G networks for improved connectivity, enabling better real-time control and data transmission.

  5. Nano-drones: Miniaturization of drones for applications in confined spaces or covert operations.

  1. Environmental adaptations: Development of drones capable of operating in extreme conditions, such as underwater or in high-radiation environments.

  2. Improved regulatory frameworks: Many countries have been updating their drone regulations to accommodate commercial and recreational use while ensuring safety and privacy.

  3. Counter-drone technologies: Advancements in systems designed to detect and neutralize unauthorized drones.

  4. Sustainable designs: Increased focus on eco-friendly materials and solar-powered drones for extended missions.

What are the leading companies in drone development?

As of my last update in April 2024, several companies were leading the way in drone development. Here are some of the prominent players:

  1. DJI (Da-Jiang Innovations): A Chinese company that dominates the consumer and prosumer drone market, known for their Mavic and Phantom series.

  2. Parrot: A French company focusing on consumer and commercial drones, particularly for agriculture and surveying.

  3. Skydio: An American company known for its autonomous drones with advanced obstacle avoidance capabilities.

  4. Autel Robotics: A growing competitor to DJI, offering high-quality consumer and professional drones.

  1. Yuneec: A Chinese manufacturer producing a range of consumer and commercial drones.

  2. Intel: While not primarily a drone company, Intel has been involved in drone swarm technology and light shows.

  3. Boeing: A major player in military and large-scale commercial drone development.

  4. Northrop Grumman: Another key player in military drone technology.

  5. Amazon: Developing drone technology for package delivery through its Prime Air program.

  6. Wing (Alphabet/Google): Focused on drone delivery services.

  1. Zipline: Specializing in medical supply delivery drones, particularly in challenging environments.

  2. EHang: A Chinese company working on passenger-carrying autonomous aerial vehicles.

  3. Volocopter: A German company developing electric vertical takeoff and landing (eVTOL) aircraft for urban air mobility.

  4. AgEagle: Focusing on drones for precision agriculture and other commercial applications.

It's worth noting that the drone industry is dynamic, with new startups emerging and established companies expanding their focus. The landscape may have changed since my last update, so I'd encourage you to check the latest industry reports for the most current information.

How soon until #ai replaces much of the coding work out there?

#technology

Pre-human technology! New excavations in Israel unearth 400,000-year-old tools

Homo sapiens were not the first hominids to make tools. In Ethiopia, researchers have already found stone utensils from 2.6 million years ago. Now, new excavations in Israel reveal more items that predate anatomically modern humans, unearthed in the caves of Jaljulia and Qesem.

These utensils, known among experts as “Quina scrapers”, were discovered in Israel and date back at least 400 thousand years. This finding is significant, as the first Homo sapiens appeared in Africa around 300,000 years ago. Israeli scrapers, therefore, are at least 100,000 years older than the first sapiens.

#newsonleo #technology #history

Quina scrapers were originally discovered in the French region of the same name. These tools helped ancient butchers, probably of the Homo erectus species, butcher, cut and process the meat and skin of their prey, which were mainly fallow deer, a type of mammal found in the Middle East and southern Europe.

Recent studies, including a publication in the scientific journal Archaeologies by scientists at Tel Aviv University, explain how these 400,000-year-old tools were found and highlight their importance in the technological history of hominins. The Levant region, including Israel and Lebanon, has experienced several climatic and ecological changes that have directly impacted the lives of its inhabitants.

@coyotelation

It is about time.

NASA to keep Starliner crew in space until 2025, with SpaceX handling return

Sunita Williams and Barry Wilmore have been on their mission far longer than originally expected.

NASA announced Saturday that it will use SpaceX’s Dragon capsule to bring home two astronauts stuck in space for months, because the agency does not have confidence in Boeing’s troubled Starliner capsule.

“It was just too much risk for the crew,” said Steve Stich, NASA’s commercial crew program manager.

#nasa #newsonleo #space #spacex

The highly anticipated decision, one of the most consequential by the space agency in years, is a devastating blow to Boeing, which had argued vehemently that Starliner was safe even though it suffered a series of thruster problems and helium leaks as it brought NASA astronauts Sunita Williams and Barry “Butch” Wilmore to the International Space Station in early June.

The decision means that the autonomous Starliner spacecraft will return to Earth, likely in early September, without anyone on board and that Williams and Wilmore will have their stay on the space station, originally intended to last eight days, extended to about eight months — the next Dragon return flight is scheduled for February.

AWS CEO Predicts AI to Transform Software Developer Roles

In a leaked recording from an internal meeting, Amazon Web Services CEO Matt Garman discussed the evolving role of software developers in the age of artificial intelligence (AI). Garman suggested that AI could soon take over many coding tasks, urging developers to focus on innovation and customer needs rather than the mechanics of writing code. He framed the shift as an opportunity rather than a threat, emphasizing that developers would need to adapt to new AI-driven workflows to stay relevant. “If you go forward 24 months from now, or some amount of time — I can’t exactly predict where it is — it’s possible that most developers are not coding,” Garman’s leaked audio states.

#aws #technology #ai #coding