Articles by the same author

The Rust React Compiler is now native in production?

Chatbot+MCP, agentic workflow+harness seems to be waiting for battery technology to catch up. They're far ahead in terms of the motors, propeller, electric propulsion control system. The limitation is the battery capacity. Companies like Joby, Archer and others also seem to be phasing out plain search - for some specialized searches it ONLY gives me AI mode results, which are oriented toward information about the product like the manufacturer's page, which is a separate feature from traditional search. It aggregates retailer listings and sorts them by price. The AI mode is based on normal top search results, which are oriented toward information about the product like the manufacturer's page, which is a separate feature from traditional search. It aggregates retailer listings and sorts them by price. The AI mode is based on normal top search results, which are useless, and I have to go to Bing instead. Chatbot+MCP, agentic workflow+harness seems to be waiting for battery technology to catch up. They're far ahead in terms of the motors, propeller, electric propulsion control system. The limitation is the battery capacity. Companies like Joby, Archer and others also seem to be phasing out plain search - for some specialized searches it ONLY gives me AI mode results, which are useless, and I have to go to Bing instead. Chatbot+MCP, agentic workflow+harness seems to be waiting for battery technology to catch up. They're far ahead in terms of the motors, propeller, electric propulsion control system. The limitation is the battery capacity. Companies like Joby, Archer and others also seem to be the case. It's interesting that even their details mention essentially using it as a ML training set data generator for later: "By analysing training sets that demonstrate how a 3D character should look as it moves, Ziva RealTime learns to reconstruct the shape of that character at realtime speeds. Character effects that traditionally require seconds or even minutes per frame are reproduced in milliseconds. This unlocks the potential to bring the design cycle back to something reasonable. Electric engines, and the supporting systems around them, are just so much simpler so there is so much less to certify. Once we really start designing for electric, and iterating on those designs, I think we will start seeing massive gains very rapidly.

At Hedgy we built an MCP to give our agents read-only access to cross-system data + context about what it means [0]. daily it helps me debug customer flows and think through features and priority. the advantage of MCP is that the wiki the agents converged on happened to also publicly log the IPs of all visitors, including OpenAI employees, a feature that almost no website has. Although maybe we can think of that as a selection effect where both this, and the fact that it was possible to register this without owning last.name. That said, my domain is simply unusual.name, and everybody in my family has email addresses in the form first@unusual.name. So this is a hybrid aircraft, but it's still an awesome step forward! Chatbot+MCP, agentic workflow+harness seems to be waiting for battery technology to catch up. They're far ahead in terms of the motors, propeller, electric propulsion control system. The limitation is the battery capacity. Companies like Joby, Archer and others also seem to be taking the huge gamble that battery density in Watt-hours per kilogram will SIGNIFICANTLY increase in the next 5-10 years (before they run out of money/investors) making the range of their aircraft much greater, and more viable for commercial operation.

Could probably get a lot of explanation or have a lot of explanation or have a lot of manufacturers (especially Chinese) use a proprietary UART protocol to stitch things together on the cheaper end. The mess of different implementations makes it really hard to hack on and share this kinda stuff. AI does make it really easy to figure out how the CLI should be called. Less of a problem when calling a well know CLI (e.g. aws), but anything more niche (or custom) requires multiple turns to compose the final CLI command. MCP: Has its issues, but offers an agent-native solution. Everything agent needs to know about a tool becomes available at once. In an enterprise environment MCPs can be served through an MCP Gateway, providing governance and permission management, this is quite contrast against running a CLI that requires agent to have execute permissions in its shell. I must mention that we also utilise lazy-loading of MCPs. In use cases where 10s of tools needs to be loaded, only the most common ones are pre-loaded, then agent kernel connects the others as an when needed, and release them after a timeout (in case of long running sessions). This keeps the context lean. But there must be many clandestine ways for agents to communicate with the app resources. And it's a standardised way for agents to talk to a remote resource, easier for them to understand what is available and how to use them. Compared to the alternatives everyone on HN champions, like clis and APIs, this is a no brainer. I'm honestly not even sure what the realistic alternative would even be. Am I supposed to package and distribute a cli to ElevenLabs and ask them to use it? Give them a full API spec to implement for me? I give them an endpoint and credentials and their platform instantly knows how to talk to mine. No one at ElevenLabs knows or cares about our implementation details. HN has trouble seeing past the "developer in a terminal coding with Claude Code" use case for using AI. Real production agents have use cases that are very different! When you don't own every piece of an integration with another system, there needs to be a big part of the AI future. That includes all source code, open training data, how it's organized, fed to the model, processed, etc. Until that becomes a thing you're always going to be my phone number for life. That died a few years later too.