With some fear that corporate data could be revealed by messy AI applications, sandboxing was high on the agenda, and Matt Brockman, an AI engineer at enterprise sandboxing business E2B, explained that there really wasn’t much to be frightened of. - Source: dev.to / 18 days ago

E2B is the sandbox. It gives the agent its own computer to do work. - Source: dev.to / about 1 month ago

If you've used E2B, Daytona, Modal sandboxes, or Cloudflare Sandboxes, the shape is familiar: REST API, Python and JS SDKs, exec / files / snapshot primitives. Here's what the Python SDK looks like:. - Source: dev.to / 2 months ago

E2B | SF, Prague, Remote | Eng, GTM, and Operations | https://e2b.dev/ E2B is building infrastructure for AI agents, and has quickly become the open source standard for agentic workflow sandboxes. Customers include Perplexity, Groq, Manus, and more. We are experiencing explosive growth and hiring for several technical and non-technical functions as we prepare to 3x the team this year. - Distributed Systems Engineer. - Source: Hacker News / 3 months ago

Sandbox: Since we are using Gemma 4 E2B, you should ideally provide an E2B.dev API key if you want the agent to execute code in a secure, cloud-hosted sandbox. If you want it 100% local, select Local Terminal. - Source: dev.to / 3 months ago

Cogniflow takes no-code further into AI model creation. Kevin Baragona, Founder of Deep AI, shares, "Cogniflow is a no-code platform that allows users to create custom AI models from data or text and then deploy them via API." This enables rapid MVPs for tasks like sentiment analysis, integrating seamlessly into existing systems. - Source: dev.to / 11 months ago

Not recording when bugs occur misses patterns tied to events like deployments or billing cycles. “One rare but powerful insight I would share is that bugs often manifest around specific times such as deployment windows, daylight saving changes, or billing cycles,” says Kevin Baragona, Founder of Deep AI. IBM’s developer experience report notes developers spend nearly half their time debugging, and Datadog’s... - Source: dev.to / about 1 year ago

Sometimes API security requires you to go on the offensive, and proactively implement methods to detect attackers. Kevin Baragona, Founder of Deep AI proposes a rather interesting solution:. - Source: dev.to / over 1 year ago

Another important use of Human AI tools is human detection in images and videos. This technology is particularly useful in areas such as security and surveillance, where it is essential to identify the presence of people in real time. Tools such as DeepAI offer a variety of AI generators, including those for human detection, which can be used to improve security and monitor sensitive areas. - Source: dev.to / almost 2 years ago

If you try to engage ChatGPT or deepai.org's free chat with a non-establishment narrative, it will often refuse to engage, refuse to consider anything you say, and just claim it's "misinformation" and that you have "no evidence," despite you having enumerated the specific evidence you have (video with a solid chain of custody, eyewitness testimony, etc.). Source: almost 3 years ago