ulimn

I somewhat agree to what you said, but also, the whole point of agentic coding is that "code is cheap". So I can't imaging companies like Google not having the resources (whether human or token) to build a better agentic assistant/harness than what Anthropic can. I mean Google has a pretty good starting point with Google Docs, etc.

I've been using Secretive for years because I didn't bother looking it up how to do it without. I think this is worth doing without an additional third party, especially since it's only a few commands.

It was unpleasant on a 27" 1440p monitor as well. I think the content is just too narrow in general.

How do you keep your prompts from getting just ramblings as you do the thinking?

It sounds like a fun way to "code", but I just can't imagine how it works in reality.

While keeping feature-parity, right...?

I think the memory hog you're thinking of is the official Bitwarden self-hosted backend. Vaultwarden is pretty light on resources.

Oh, one of the few blogs I was following. Sad to see this news.

I am curious: Why is it bad to merge chat and work? In Claude I didn't have a porblem with it (although I switched to an OpenAI subscription shortly after they made the merge). Isn't the model capable of deciding if it needs the extra capabilities of Work?

You yourself also kind of pointed out why the discussion about USA and China is not off-topic. The niche Mistral wants to fill (afaik) is that it's European. I, as a European am really happy that they made such progress in so much worse (financial) conditions. I guess it's mostly geopolitics.

I'll be sure to check this out but in the meantime, I'd like to ask: Isn't it generally a good practice to run coding agents in a VM? It provides a security boundary so that the agent is restricted to the VM.

How does this compare? I see it's an "isolated sandbox", but what exactly does that mean?

Not for long if the next release will be Gitea 290 instead of 29.

I have a feeling that nobody will die (most likely) for choosing forgejo or gitea... Apples and oranges...

I suspect it's partly because people didn't jump from GPT-3 to GPT-6.1 Sol and partly because SOTA models from the last few(?) months have been able to tackle most of the regular tasks. It means this new model isn't different in that regard from Opus 4.8, if your mental benchmark is that they both are capable of implementing something like a CRUD app.

A few words which everyone would understand, like "small, medium, large"? I wish we had something, yeah...

Oh my... Thank you for the link but I couldn't bear to watch it so I just read the summary. It hurts to watch these people.