Slack itself originally ran on irc servers as the back end, and I consider it a modern IRC implementation.
Slack itself originally ran on irc servers as the back end, and I consider it a modern IRC implementation.
So why can't Anthropic build a CLI client that doesn't flickr and doesn't consume 68 GB to run a CLI wrapper on top of their API? https://x.com/jarredsumner/status/2026497606575398987
The thing lags a few seconds while typing a message on a 20 core 128g ram machine. That's with their desktop (electron) app. Mercifully, the web app works better.
Still, CC blows it out of water. Slack is that bad.
We're a small company (about 150 Slack users), and I've run the Slack (Electron) app on a 16GB M2 (macOS) and a 4GB Chromebook (running a non-ChromeOS Linux), and it has never had any noteworthy performance issues.
It still sucks, but not because of performance.
It's a terminal wrapper for Anthropic API. It somehow baloons to 68 gigabytes when all it needs to do is call an APi and slowly draw a few hundred characters on screen. And they can't even do that without flickering. Oh yes, and until very recently it would also consume a significant percentage of CPU just waiting for input to a slash command.
Yes, on that same 20 core 128g RAM machine.
You surely must be kidding. Slack is an amazing cutting edge high performance tech in comparison as it has about two orders of magnitude more features that a TUI API wrapper.
Not to say it doesn’t, but it’s clearly not a universal issue.
Not even joking
E.g. they claim it's a difficult task to render a few hundred characters on screen, and that their CLI wrapper is a tiny game engine: https://x.com/trq212/status/2014051501786931427
They literally had to buy bun to have someone who understands how things work to fix this
While it's a great tool in the hands of capable and well intentioned people, there's not a world out there where the average quality of software goes up.
Even if AI with autonomous agentic development made something that worked at the average of code quality, I wonder if the code might be a little more sturdy, predictable, and the compromise is a little more verbose for the level that works for the AI to manage it.
Humans would then help oversee the input, insight, and extension and improvement above and below that.
AI could be a baseline.