Any background / context around what the Chicory author means in this comment?
> We'll consider merging in changes that make sense from Endive, but under the stewardship of the [Byte Code Alliance] I have very little faith in its future. My words mean nothing though having all but completely lost interest and use for WebAssembly.
What's the background / history of Byte Code Alliance?
I could see this image in my mind before I clicked on it, before even consciously considering what it might be. Is this how an LLM feels on the inside?
Antigravity seemed to work well at first, but the same model on the same software now seems to fail to edit most files most of the time, and then get itself tied in knots trying to resolve the error by editing files with awk, sed, grep, etc!
Yup. “Wait, let me circle back and fix this another way.”
What they can never fix is that plenty of Pro users complain that they never get quota, models are always maxed out. I left, and I can’t believe how much time I wasted in AGY steering Gemini or reminding it that no, you can’t install random new dependencies or disable tests.
I cant see how they could. The Gemini cli repo was a shit show the last time I looked a month ago and the service itself wouldnt even let me use version > 2.5 even though I was a paying customer.
A model that I can use? I'm on a trial plan but this doesn't convince me to pay for it for real. The 20$ plan for Codex and Claude just works and I get stuff done.
It's two slightly different jokes right? The parent comment joke is essentially stating "they are definitely going to talk about AI a lot" and the second joke is stating "they are not going to talk about anything besides AI", which are similar but technically different.
Don't give them the idea, before too long they'll retire the email part so you could use it to train agents and use AI in your workflows by leveraging Artificial Google Intelligence (AGI)
ASI now. You'd think contrasted with AGI it would be Artificial Specialized Intelligence, but it's Artificial Super Intelligence. Since AGI already happened and didn't mean anything, the next step is a super AI.
I still want the normal definition of AGI... Which my understand is: no more re-training, real time memory and re-learning. The fact they cannot fit a lot of context, or step into "we no longer need to train it" territory tells me, they're farther than they keep pretending they're close to.
I don't have any LSP's hooked up to CC yet (going to fix that today), or particularly sophisticated CLAUDE.md files.
So, if I've read this post correctly, that means that CC is navigating my codebase today by sending lots of it up to a model, and building an understanding. Is that correct? Did I misunderstand it?
I kinda suspected there was more local inference going on somehow -- partly because the iteration times are fairly fast.
I think that's correct. Which is kinda funny, I remember 10y ago that I was heavily relying on IntelliJ features to understand new codebases (jump to definition, find all usages of a function, navigate from SQL to the table in database tab etc.).
It turns out, that for a machine, find and grep is all that's required.
Agents use find+grep because it's available everywhere and without any configuration, but they would still be more efficient with LSP. Once LSPs will be more easily configurable for agents, they will use them.
A human could get by with just find and grep too. And in both cases, find and grep will be slower and less precise than an IDE's code navigation features.
> So, a manager who's managing 15 people AND expected to ship
Right?? I saw that too. My first thought is that any good managers left will be racing for the exit. You can't fake "managing 15 people" with AI. You have to actually have the 1:1s and do the performance calibrations. How are they going to have time left for IC work??
As a manager with 10-15 reports at a company you've probably heard of, I think the main question is how much they will need to contribute. I put up a PR or three a week, usually in non-critical path flows or system support, and its honestly fine. I could barely contribute to the productivity level of even one of my junior engineers, but I can debug production issues and ship code AND be a good manager (with a decent work life balance).
I feel like managers should be able to contribute. Managing a good team isn't that hard, though managing a bad team (or a good team in the midst of a ton of bad processes) is a nightmare.
"IC work" seems to have evolved at Coinbase to mean "supervise AI changes". Then the question becomes how will managers actually review these changes and not just press accept at 3:50.
I assume they will have absurd metrics, like number of commits and token use to,determine how good of an IC you are. So, you start a bunch of agents in the background, merge their PRs without review, while having 1:1 and other meetings with your team. Productivity they call it
> manager who's managing 15 people AND expected to ship
Notable is what they're not doing--annual reviews. This duty is now handled by the all seeing "intelligence" machine that can evaluate employees in real-time.
Darkly funny that Armstrong's Twitter bio still reads "Creating more economic freedom in the world" when he has relegated humans to "the edge" of his own organization in favor of the pseudointelligent pseudogod.
Freedom for who, exactly? Coinbase's executives, I suppose.
I can see you're A/B testing some different hero text.
I got:
> Write a config, not a conversation
Which I found let me wondering - "What is this thing?"
I refreshed a few times to the variations, and while some were better, I feel like your hero could do with being less pithy, and more plain explanation of what it is.
So I'm the creator of botctl which I created to satisfy my personal need for running many agents on a cron style loop. The whole premise is you don't need to be there to chat with the agent for it to do it's job.
I'm definitely not A/B testing anything, it just cycles through a couple titles I thought conveyed the project well. The sub-title directly under it explains it pretty clearly, would you agree with that?
> Manage persistent AI bots with a terminal dashboard, web UI, and declarative configuration.
There's also an interactive emulation of the TUI directly next to both titles in the hero.
I've lived in London for a decade, and feel incredibly lucky to have access to the transit here - having lived in Aus, NZ and Canada previously.
It's not perfect. It's late sometimes, pollution sucks, and often crowded - but people here who like to criticise it really don't recognise how much better they have it than lots of other places.
Same with travel from here to Europe (by train), is just awesome.
This is a really great post - and what they've built here is very impressive.
I wonder if we're at the point where the cost of building and maintaining this yourselves (assisted with an AI Copilot) is now more effective than an off-the-shelf?
It feels like there's a LOT of moving parts here, but also it's deeply tailored to their own setup.
FWIW - I tried pointing Claude at the post and asking it to design an implementation, (like the post said to do) and it struggled - but perhaps I prompted it wrong.
I had this exact idea, I pointed Codex to it, with giving it context of our environment which is pretty complex. It is struggling, but that is because even our dev experience where I work is not great and not documented, so that would need to be lifted before I can reliably get an agent setup as well integrated as this blog post details.
> We'll consider merging in changes that make sense from Endive, but under the stewardship of the [Byte Code Alliance] I have very little faith in its future. My words mean nothing though having all but completely lost interest and use for WebAssembly.
What's the background / history of Byte Code Alliance?
reply