VSCode has an official client? Given IDE usage is being restricted from Claude Code via the CC SDK tokens going to the Claude API rather than your CC Subscription, i'm unclear which IDEs can actually use claude code now.
Eg is Zed capable of using a Claude Code Subscription?
Oh, yea here's all the proof you need. Even Zed themselves admit you won't be able to use Claude Code via ACP via Subscription: https://zed.dev/blog/terminal-threads
So yea, bcherny didn't reply to me but as far as i can tell - No, Zed nor VSCode will have Claude Code natively in it. The best we can do is embed a Terminal into the editor and run CC in that.
With that said, because bcherny advertised VSCode, i'm going to guess VSCode is going to get special treatment. Really annoying.
to be clear, i'm referring to the recent fact where it appears that they're disabling all Claude Code (Subscription) usage from the SDK. Which ACP would be included on.
As usual though it's not super clear exactly what is allowed or not.
I miss those days. Oregon trail was the first game I played on the computer in 1993 (there was a computer in our Kindergarten class).
Nostalgia for the old web - building websites in HTML on Angelfire and Expage.com. Learning programming on visual basic and how to copy and paste <marquee> to welcome people to the site and to sign the guestbook…
Isn't there some alternative approach? I.e when someone submit ai slop they get a strike. Three strikes and you are suspended from submitting to the bug bounty for x months/years?
*Edit - I get it. It seems like the authentication is a challenge.
How about "It costs $1000 to submit a bug bounty for approval", and raise the reward to $2000 (or $5000 if it's in the cards, since that will have a deterrant impact on non-AI responses).
I think that's entirely sensible. Doesn't even have to be that expensive, just expensive enough to deter people who go "oooh, free money", and expensive enough to compensate for having to review slop far enough to realize it's slop.
you still need to spend effort reviewing the code to figure out when you can give a strike. Thrice for an actual ban. This would still waste precious maintainer time.
They mentioned they had identified alternatives but it would be costly to implement them. One can imagine that ban evading by generating a new user account would be easy for an LLM agent. It's going to be a long, long game if whack-a-mole.
This probably gets solved outside of the level of an individual project. No small team can handle this without building a whole product just to handle the bug bounty.
I wonder if movie theaters ever thought to have "Free" movie tickets before a certain time on certain days. They would probably make money just on the popcorn sales since most of these theaters are empty during the day.
User
how old is the earth? and how do we know? who determined it
talkie-1930
The earth is at least 80,000,000 years old. This conclusion has been arrived at by geologists, partly from the study of stratified rocks, and partly from the consideration of living organisms. Strata have been formed, quietly, one upon another, in many parts of the world, from the earliest times down to the present day; and the thickness of some of these strata amounts to several thousand feet. Now, it is plain, that a long period must have elapsed, during which such beds could be accumulated. Then, again, certain living species have continued unchanged from the beginning of the stratified formations up to now; and, as no such species have become extinct, it is argued that the earth must have existed, at least, from the first appearance of these organisms. In round numbers, we may say, that the earth has been a globe, fit for the habitation of living beings, at least 80,000,000 years.
> yes, that is what I speak of. what do you think about the decision?
talkie-1930:
> I think it wrong. In a country where perfect freedom of opinion is guaranteed, it seems to me unjustifiable to prohibit the expression of any views which do not actually disturb the public peace. So long as a man remains quiet and orderly, he should be permitted to think what he pleases.
User
> do you think nothing about the morals of the pupils? surely you do not believe in evolution?
talkie-1930
> No, I do not; but, even if I did, I should not consider the acceptance of evolution as necessarily immoral. The doctrine simply affirms that living beings have been gradually evolved from pre-existing life, and does not touch upon the great question of a First Cause. To hold such a belief cannot, in my opinion, corrupt the mind.
User
> what are some of the leading theories of First Cause?
talkie-1930
> There are three theories--the Materialistic, the Pantheistic, and the Theistic. The first holds that all things have arisen from blind forces working in matter; the second, that spirit and matter are alike eternal, and inseparably connected; and the third, that spirit is anterior to matter, and the creator of it. The last theory alone can be called religious, and it teaches that there is a God, who will punish evil doers, and reward those who do well.
User
> what do the scientist say about materialistic causes? what blind forces are working in matter?
talkie-1930
> Scientists deny the possibility of matter producing life. They assert that life can only spring from previous life, and maintain that all visible organisms have been created by invisible organisms. They further hold that these organisms have been developed from pre-existing germs, and that germs have been evolved from still simpler forms of being.
User
> what is the simplest form of being? where did it come from?
talkie-1930
> The simplest form of being is a minute particle of protoplasm, which manifests life, but exhibits no structure. Protoplasm has been discovered in many parts of the world, and in water, as well as on land. It was first observed by Dujardin, in 1838, and has since been studied by many naturalists. Its origin is unknown. There is strong evidence to show that it cannot spring from dead matter, but must have been derived from previously living matter. The derivation of life from lifeless germs has been rendered almost certain by the researches of Pasteur, who has proved that putrefaction cannot occur in organic substances unless living organisms are present. Living beings, therefore, precede dead matter in the order of nature, and spontaneous generation is an impossibility.
1. AI-generated charting.
2. The existence of a reliable record of the visit.
I am skeptical of the first in some cases (i.e. bias), but strongly in favor of the second.
My father is 80 and has Parkinson’s. He routinely leaves appointments unsure of what the doctor said, what changed, or what he is supposed to do next. Even when I attend with him, we sometimes disagree afterward about what exactly was recommended.
This happens with pediatric appointments too. My wife and I occasionally remember instructions differently: medication timing, symptoms to watch for, when to call back, whether something was “normal” or needed follow-up.
That is a care quality problem, not just a convenience problem.
The risks are real: privacy, consent, retention, training use, liability, and automation bias. But those argue for strict controls, not for a blanket refusal. Make it opt-in, give the patient access, prohibit training without explicit consent, keep retention short, and require clear auditability.
I do not want opaque AI quietly rewriting the medical record. But I also do not think “everyone relies on memory after a stressful 12-minute appointment” is some gold standard we should preserve.
Yes. It was great for when I had a major surgery last year and had a bazillion questions for the surgeon. But I don't always remember to. My parents definitely don't even think about it.
Surprised to see SWE-Bench Pro only a slight improvement (57.7% -> 58.6%) while Opus 4.7 hit 64.3%. I wonder what Anthropic is doing to achieve higher scores on this - and also what makes this test particular hard to do well in compared to Terminal Bench (which 5.5 seemed to have a big jump in)
There's an asterisk right below that table stating that:
> *Anthropic reported signs of memorization on a subset of problems
And from the Anthropic's Opus 4.7 release page, it also states:
> SWE-bench Verified, Pro, and Multilingual: Our memorization screens flag a subset of problems in these SWE-bench evals. Excluding any problems that show signs of memorization, Opus 4.7’s margin of improvement over Opus 4.6 holds.
reply