811–817 of 817 posts
Earlier quoted context omitted.
I disagree with your assessment that large organisations are beneficial. We can see with our current crop of large organisations that they really struggle to create anything new; most of their new products or services were developed by a small organisation and then acquired. A lot of those products are then enshittified and badly managed because large organisation politics screws things up. Large organisations are in…
And I disagree with yours :). Large organizations are necessary if you want things like airplanes and rockets and computers and MRI machines to exist. And if you feel you benefit from those things yourself, then large organizations that create and operate[0] them are beneficial to you, too. > A lot of those products are then enshittified and badly managed because large organisation politics screws things up. That's n…
I disagree, it's not "modern" economics, it's one half of the Malthusian trap as it manifests in all economics; the other half is that profits tend to zero, both halves are a loss of systemic slack, to reuse the good point you make later.
> That description fits small business owners much better IMO. In our times, at least in non-failed western countries, there's a limit to how abusive or careless a large organization can be with their customers or employees - their very size makes them easy to target legally.
I think this is more like predator/prey size dynamics. One way to keep safe from predators is to be too big to hunt. The regulators and governments are more like predators than their peer-competitors are, cf. "too big to fail".
Earlier quoted context omitted.
wait, you can use other models with CC harness?
Yes, as long as they support the Anthropic API standard. You might have luck converting between standards using litellm's proxy. The system prompt and tool choice are tuned for Anthropic's models. For example, this setup will use Deepseek V4 Pro with their first-party (subsidized) API. Things like the Read tool on images won't work, but mostly this works well. Your mileage may vary. #!/bin/sh export ANTHROPIC_BASE_UR…
It was decided by Claude based on an ambiguous high-level goal-oriented prompt, don't expect it to make sense.
Value judgment aside: I am a bit surprised at how sloppily they did this. I think they could've achieved the same effect while decreasing the odds of detection via reverse engineering. (This field is known as "underhanded code", coined by the Underhanded C contest: https://www.underhanded-c.org . It's a little-known "art"; little-known for probably self-explanatory reasons. There are much cleverer ways of achieving o…
Well considering how Claude is vibe coded, I can't say I'm really surprised by sloppiness at all. I've been moving more towards Codex and OpenCode not because the the anthropic models are bad, but because Claude seems to break something new and annoying every day.