> Are you tinkering? Or trying to build something useful? If you're trying to build something useful, use a tool.
I don't think that you really get what this new era of software is about otherwise you would understand why the experienced are spending time tinkering on the so called harness (like openclaw did)
How about wiping out an entire civilization? Not even necessary to hide this thought in your diary if you have enough power. I've seen today - in fact any day of this year - much worse things than his diary thoughts.
Well, gee. When you put it like that, Hitler existed, so really we can't fault anybody for anything short of orchestrating the genocide of 12 million people.
By your logic you could argue that if anybody on this planet starves to death then Americans can be blamed and ‘engineered it’, since they had the economic means to prevent it. You’re essentially trying to argue that inaction is a positive act, which it is not as a matter of logic and law universally.
Your logic is laughable on its face, obviously.
Americans have no more duty to look after non-Americans than anybody else.
If I provide cancer drugs to someone, and then suddenly stop, am I to blame for them dying of cancer? That doesn't imply that I have a moral duty to provide the drugs. But if I am providing them and then withdraw them, then there is some responsibility on my part?
>>You’re essentially trying to argue that inaction is a positive act
You've assumed I have a certain position then argue against it, not against what I actually said.
Unilateral voluntary foreign aid is not in any way analogous to medical care that creates strict legal obligations when the doctor-patient relationship commences.
> Not feeling like 1 hour of my Sunday is worth listening to this, do anyone have the non-clickbait answers to the two "previews" mentioned in the description?
I know HN is built around mostly not reading the articles linked but how about you click on the link and surprise, there is already exactly another link providing what you're asking for.
Same. 4.7 intelligence is significantly worse than 4.6 on ALL 3P Harnesses. So only on Claude Code and Anthropic API/Subscription you get decent performance but on every other Harness and/or Cloud Provider inference (Bedrock) it performs worse than 4.6 on almost every task. This is not just anecdotal, i've talked to many colleagues from AWS, Microsoft and so on and they all agree that something fishy is going on.
I switched back to even Sonnet 4.6 in Claude Code over Opus 4.7. Every day or two I try a new task on Opus 4.7 and regret it.
Looking now I see that "Opus 4.6 Legacy" is an option that was not there before, so maybe Anthropic noticed that others are having the same difficulty.
reply