###### December 3, 2024

The company [announced Monday](https://www.threads.net/@threads/post/DDFkqNuPil1) that Meta's Instagram Threads, a competitor to Elon Musk's X, is launching a more efficient search engine. Built on Instagram's social graph, Threads allows users to search for specific posts using filters based on user profiles and a variety of criteria.

While Threads' new feature, which offers options like filtering by language, keywords, phrases, excluded words, and hashtags, doesn't match X's sophisticated search, it does improve the ability to find posts. Additionally, Threads is close to [Bluesky](https://codelabsacademy.com/en/news/what-is-bluesky-everything-to-know-about-the-new-social-app-competing-with-x)'s search functionality, which supports filters such as user profiles and a range of queries via advanced queries. However, the Bluesky app does not yet display all of these filtering options in its interface.

In the past, Threads' search functionality was limited to keyword searches with the two filters of "Top" for the most interesting articles and "Recent" for the newest. A post from the Threads account indicated that the improved search feature would be made available to users around the world in the coming weeks.

In response to the growing danger posed by Bluesky, a developing competitor to X, Meta has accelerated the release of its features. After the US election, Bluesky's user base [grew to around 24 million](https://bsky.jazco.dev/stats) after surpassing 9 million in September. Indeed, customers left X due to Elon Musk's political views and policy changes, which included plans to change blocking methods and allow AI companies to train on data of X users.

Threads has added new features to compete with Bluesky, including an improved algorithm, a redesign for easier feed navigation, and adjustable default feeds. Additionally, Meta is rumored to be creating Starter Packs, its own version of Bluesky's user-curated recommendation lists.

_Want to keep up with the latest innovations in technology? Enroll now and become part of a community that's as dynamic as the tech world itself. Learn more at_ [_Code Labs Academy_](https://codelabsacademy.com/)_._


thumbnail_julio-lopez-VCkuvZd_AlM-unsplash (2) (1).webp

julio-lopez-VCkuvZd_AlM-unsplash (2) (1).webp

New Search Engine on Instagram Threads: A Strategic Move Against X and Bluesky


With Visual Studio 2022 17.12, Microsoft has added additional diagnostic and debugging features that improve code analysis and debugging. Among these changes are improvements related to the incorporation of Copilot AI, which aims to streamline development processes. One of the most sought-after features has been the online display of function  `return`  values, which has been implemented. Hovering over these numbers, which are grayed out below the relevant  `return`  instructions, displays a Copilot icon and more information. When you click this icon, the expression is analyzed by AI to reveal any errors.

Parsing the values ​​of variables in the “Auto” and “Locals” windows is another way Copilot extends its capability to the debug windows. Additional error analysis is provided via an AI icon adjacent to the variable previews. Although a dedicated AI assistant for the tool is still in the development phase, the IEnumerable Visualizer tool has also been improved, integrating IntelliSense with syntax highlighting for LINQ queries.

To ensure uniform management of breakpoints across all projects, the debugger now allows you to import and export groups of breakpoints with their options. Snapshots can now be taken with the diagnostic tool to compare memory states. When developers take two snapshots in the "Memory" tab, they can see the changes by choosing "Show Differences." Additionally, the diagnostic window now displays histogram data.

This release adds AI-powered features, particularly for debugging and code repair, and integrates .NET 9. Users can now copy files to Visual Studio instances and launch multiple program settings based on project requirements using the user interface. Commit messages generated by Copilot can be further customized by developers, who can even create local repositories and manage multiple GitHub accounts. In addition to HTTP files supporting query variables to reuse responses in subsequent requests, Linux users can also publish WebJobs to Azure. Command line parameters can be set directly in the C++ Developer Toolbar.

These improvements are described in detail in [Microsoft's blog post](https://devblogs.microsoft.com/visualstudio/debugger-and-diagnostics-updates-in-visual-studio-17-12/), and a full overview of all upgrades is given in the [release notes](https://learn.microsoft.com/de-de/visualstudio/releases/2022/release-notes).

\
Ignite your passion for AI: Learn how to transform data into powerful, scalable solutions with Code Labs Academy’s online[ Data Science & AI Bootcamp](https://codelabsacademy.com/courses/data-science-and-ai).


thumbnail_chris-ried-ieic5Tq8YMk-unsplash (1) (1).webp

chris-ried-ieic5Tq8YMk-unsplash (1) (1).webp

Visual Studio 2022 17.12: Microsoft Improves Debugging and AI-Powered Features with Copilot Integration

###### November 26, 2024

An open source standard called [Model Context Protoco](https://www.anthropic.com/news/model-context-protocol)l (MCP) has been unveiled by [Anthropic ](https://www.anthropic.com/)with the aim of improving the way AI assistants communicate and connect to data systems. The protocol aims to overcome the drawbacks of AI models, which often operate independently of large data sources and require unique integrations for each new system. MCP offers a comprehensive solution that allows chatbots and other AI-powered applications to easily access data in development environments, tools and content repositories.

By employing "MCP servers" to serve data and "MCP clients" to integrate workflows or applications, the protocol allows developers to establish bidirectional connections between data sources and applications. This standardization could streamline development procedures by substituting a scalable and sustainable framework for disjointed integrations. Platforms like Replit, Codeium, and Sourcegraph plan to add support for MCP, while companies like Block and Apollo have already integrated it into their systems.

With prebuilt servers for well-known enterprise tools such as Google Drive, Slack and GitHub, as well as plans to release toolkits for installing production servers, Anthropic has made MCP available to developers . MCP can be used to link the Claude chatbot to internal systems for users of Anthropic's [Claude Enterprise](https://techcrunch.com/2024/09/04/anthropic-launches-claude-enterprise-plan-to-compete-with-openai/) subscription.

By removing the requirement for separate interfaces for each data source, the adoption of MCP could accelerate AI integration efforts. AI systems may be able to preserve the context of tools and information as the ecosystem grows, which would result in a more consistent and efficient design.

However, the extent to which MCP is adopted, particularly by its competitors, will determine its success. With its proprietary “Work with Apps” function for ChatGPT for example, OpenAI has adopted a different strategy. This functionality links the model to particular coding tools and could potentially be extended to other applications. However, OpenAI's strategy remains closed and partner-focused.

Although Anthropic claims that MCP can greatly improve the contextual capabilities of AI systems, such as improving comprehension when coding, these claims have not yet been supported by specific references. Its performance and long-term effects are still unknown.

_Take control of AI-powered solutions by mastering_ [_Data Sciene and AI_](https://codelabsacademy.com/courses/data-science-and-ai) _at Code Labs Academy._

thumbnail_glenn-carstens-peters-npxXWgQ33ZQ-unsplash (1) (1) (1).jpg

glenn-carstens-peters-npxXWgQ33ZQ-unsplash (1) (1) (1).jpg

Model Context Protocol (MCP): Anthropic Simplifies AI Connections to Data Systems


###### November 19, 2024

The majority of AI models are powered by graphics processing units (GPUs), which are notoriously energy-intensive. [According to Goldman Sachs](https://www.goldmansachs.com/insights/articles/AI-poised-to-drive-160-increase-in-power-demand), by 2030, the increasing use of GPUs in data centers would result in a 160% rise in the need for electricity. Vishal Sarin, a seasoned designer of analog and memory circuits, established Sagence AI, originally known as [Analog Inference](https://www.sagence-ai.com/), after seeing that this tendency was unsustainable. The business focuses on developing GPU substitutes that consume less energy, tackling issues with both performance and the environment.

Sagence creates systems and analog chips for AI applications, as well as the software needed to program them. Analog chips use a range of values to represent information, in contrast to standard digital chips that store data as binary values. Because of this distinction, analog circuits may process data directly in memory and complete some computations using fewer parts, removing bottlenecks brought on by data transfers between processors and memory. Furthermore, compared to their digital counterparts, analog processors provide a higher data density.

Despite being available for decades, analog technology is making a comeback because digital processors can't keep up with the demands of the modern world. However, there are drawbacks to analog chips as well, namely the need for exact manufacture and the complexity of programming. Sagence markets its chips as an adjunct to digital technologies, focusing on certain server and mobile device applications to solve problems like latency, cost, and power consumption.

Sagence, which plans to commercialize its chips in 2025, is already collaborating with clients and facing competition from other analog chipmakers that specialize in AI, such as EnCharge and Mythic. Investors such as Vinod Khosla, TDK Ventures, and Aramco Ventures have contributed $58 million to the company, and it intends to seek more money to grow its staff of 75 employees. Sagence's cost-effective approach, which stays away from the newest production techniques, increases its allure in a cutthroat industry.

Potential opportunities for Sagence are indicated by recent trends. The amount of venture capital money raised for semiconductor startups [is increasing](https://news.crunchbase.com/semiconductors-and-5g/chip-startup-funding-bounces-back-ai-nvda/#:~:text=Thus%20far%20this%20year%2C%20VC,%2410.9%20billion%20in%20447%20deals.); in the first half of 2024 alone, $5.3 billion was raised. There are still obstacles to overcome, though, such as rivalry from well-known firms like Nvidia, expensive fabrication, and the problem of entering markets where established technologies predominate. The hazards are highlighted by the case of Graphcore, an AI chipmaker that declared bankruptcy in spite of substantial funding.

Sagence's success depends on its ability to deliver energy-efficient, high-performance chips while efficiently scaling production. The company aims to uniquely position itself in the progressing AI hardware landscape by addressing both economic and environmental challenges.

_Drive innovation through data with Code Labs Academy’s_[  Data Science & AI Bootcamp](https://codelabsacademy.com/courses/data-science-and-ai)_._


New Search Engine on Instagram Threads: A Strategic Move Against X and Bluesky

Visual Studio 2022 17.12: Microsoft Improves Debugging and AI-Powered Features with Copilot Integration

Model Context Protocol (MCP): Anthropic Simplifies AI Connections to Data Systems

Sagence AI’s Solution to the GPU Energy Crisis