Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Google Antigravity

antigravity.google

Post reply on HN
Print view View original

831–840 of 1001 posts

Re: Google Antigravity

#831

Post by qwertox »

josvdwest wrote: post #697
qwertox wrote: post #327

I can't get the agent to use my MCP server. The MCP config is provided, and the application can query the tools, but the agent can't access my server, only the http operations the application performs to list the tools is something i see in my server logs. It knows there are tools, because it sees the list, it tells me when it's trying to connect to which tool. But that fails.

where are the MCP settings in Antigravity?

https://antigravity.google/docs/mcp

Connecting custom mcp servers.

Re: Google Antigravity

#832

Post by dominicrose »

einpoklum wrote: post #300

Looking at that page makes me think I should go the other direction and switch from a graphical IDE to vim or something. You know, ground myself by adopting more gravity.

I agree that the name is horrible. It has Anti, gravity and Google in it. Vim and all other non-graphical tools are great because they work in WSL, they work in linux servers and they may even work in Docker containers, although sometimes you have to do something like: apk add vim

Re: Google Antigravity

#834

Post by Sammi »

Clent wrote: post #582
Sammi wrote: post #520

Earlier quoted context omitted.

- don't learn from what you tell them Whenever I have a model fix something new I ask it to update the markdown implementation guides I have in the docs folder in my projects. I add these files to context as needed. I have one for implementing routes and one for implementing backend tests and so on. They then know how to do stuff in the future in my projects.

They still aren't learning. You're learning and then telling them to incorporate your learnings. They aren't able to remember this so you need to remind them each day. That sounds a lot like '50 First Dates' but for programming.

They document how to do something they just figured out. They store/memorise it in a file.

It's functionally working the same as learning.

If you look at it like a black box, then you can't tell the difference from the input and output.

Re: Google Antigravity

#836

Post by dangus »

rglover wrote: post #187
mccoyb wrote: post #46

> Bajillions of dollars invested in the development of some of the most powerful computational artifacts to date. > Fork VS Code, add a few workflow / management ideas on top. > "Agentic development platform" I'm Jack's depressed lack of surprise. Please someone, make me feel something with software again.

If you want to feel something with software, leave the industry and never look back, saving programming as something you do for your own joy/reward (I'm not being hyperbolic—I'd argue we're in the early days of the web's "dark ages"). Unfortunately, once money came into the picture, quality, innovation, and anything resembling true progress flew out the window.

Arguably this is like every other automation in the Industrial Revolution but this time for knowledge workers.

The masses will get their metaphorical fake leather belts made by slave labor operating machines and won’t know better.

A few artisans will make very little money making the real thing manually, mostly for their own enjoyment.

This is assuming AI can actually be made to lower knowledge work’s training/education requirements, and that debate is still ongoing.

Re: Google Antigravity

#837

Post by kzemek »

cjonas wrote: post #766
throwaway13337 wrote: post #439

I gave it a fair shot. It is a vs code fork. There were some UI glitches. Some usability was better. Cursor has some real annoying usability issues - like their previous/next code change never going away and no way to disable it. Design of this one looks more polished and less muddy. I was working on a project and just continued with it. It was easy because they import setting from cursor. Feels like the browser wars…

> Cursor has some real annoying usability issues - like their previous/next code change never going away and no way to disable it. The state of Cursor "review" features make me convinced that the cursor devs themselves are not dogfooding their own product. It drives me crazy when hundreds of changes build up, I've already reviewed and committed everything, but I still have all these "pending changes to review". Ideal…

There’s a setting for that:

Cursor Settings -> Agents -> Applying Changes -> Auto-Accept on Commit

Re: Google Antigravity

#838

Post by tecleandor »

sakesun wrote: post #707
chuckadams wrote: post #522

Earlier quoted context omitted.

Just the Eclipse legacy and development approach perhaps. Eclipse is 24 years old and its codebase stems from VisualAge before that, so I imagine it's ... idiosyncratic. Probably the most successful thing built on OSGi, though I dont imagine Theia brought any of that along.

Eclipse Theia is based on VSCode, not the legacy Eclipse Java IDE.

Well, it uses the just the Monaco editor, but the rest is not based on VS Code.
Post reply on HN