It's a nightmare to some extent to prevent underage people from consuming alcohol if you want to phrase it that way. But we don't try to ban stores from selling alcohol because of concerns children will be drinking it. Instead we require the store checks for ID.
This reminds me of a thought I have had that the future of education may involve a type of "school for robots" where the human students are the teachers. I am sure Neal Stephenson and others thought of this same thing decades ago but seems closer to becoming a reality.
Would you say the same for Mastra? If so, what would you say indicates a high quality candidate when they are discussing agent harnessing and orchestration?
A good system prompt goes a long way with the latest models. Even just something as simple as "use DRY principles whenever possible." or prompting a plan-implement-evaluate cycle gets pretty good results, at least for tasks that are doing things that AI is well trained on like CRUD APIs.
A couple points from this I'm trying to understand:
- Is the idea that MCP servers will provide tool use examples in their tool definitions? I'm assuming this is the case but it doesn't seem like this announcement is explicit about it, I assume because Anthropic wants to at least maintain the appearance of having the MCP steering committee have its independence from Anthropic.
- If there is tool use examples and programmatic tool calling (code mode), it could also make sense for tools to specify example code so the codegen step can be skipped. And I'm assuming the reason this isn't done is just that it's a security disaster to be instructing a model to run code specified by a third party that may be malicious or compromised. I'm just curious if my reasoning about this seems to be correct.
One aspect the report is very vague about is the nature of the monitoring Anthropic is doing on Claude Code. If they can detect attacks they can surely detect other things of interest (or value) to them. Is there any more information about this?
The rhetoric you see in some places about how social assistance is used on hair weaves says something about the underlying reasons for much of this concern.
There is another factor to consider. The stakes of asking an AI about a taboo topic are generally considered to be very low. The number of people who have asked ChatGPT something like "how to make a nuclear bomb" should not be an indication of the number of people seriously considering doing that.
The thing is, a software based voting system with a sufficient number of checks and balances preventing tampering seems to be a lot more trustworthy to me than human poll watchers and workers. It wouldn't surprise me at this point that there may be moles in parties that are secretly from the other party.
And the other related issue is that in 2025, it simply should be possible to vote from your phone in a way that verifies your identity, if you'd like, using the faceId/fingerprint biometrics that most smartphones from recent years have.
MCP is a protocol meant for general use for clients, which Claude Skills seems more proprietary. To what extent is Skills expected to be something that other clients, such as web based clients could adopt? To some extent it would probably make sense to expose through the MCP SDK?
I think the state fee for freetaxusa is something like $30 IIRC. It was small enough where I didn't even bother looking into whether it goes to the state or the software vendor. That's the cost of a casual lunch for one at 2025 prices.
My biggest hesitation about this is being stuck in merge hell. Even a minute or two needing to deal with that could negate the benefits of agents working in parallel. And I've tried some relatively simple rebase type operations with coding agents where they completely messed up. But if people are finding this is never an issue even with big diffs, I might be convinced to try it.
These apps are cool, but won't this functionality surely be replicated within Claude Code itself? This does seem to be in "picking up pennies in front of a steamroller" territory but I could be wrong.
My understanding is the defense made by Zionist parties is more that Hamas has culpability in the starvation. I haven't seen this claim verified or debunked sufficiently to have a strong opinion about it but it at least seems within reason to me that Hamas is acting in bad faith and is weaponizing starvation of Gaza residents.
Especially with junior engineers it is helpful to ask them to provide a Loom video or other proof that they have verified a feature or bug works as intended. I have tried setting up Claude Code with playwright to verify it's work, but so far am not very satisfied with the results. Any tools that are helpful with this end to end testing for web apps using Claude Code and other AI assistants? Feel free to share your product if it is relevant.
Knowing full well how annoying it may be to ask this question in this thread...wouldn't rising electricity prices generally create upward pressure on the price of Bitcoin due to mining/supply dynamics?
One thing I'll add to this, from more than one personal experience. A refusal to provide compensation info without first doing a reference check. The reference check should be the last thing after there is a conditional offer with at least a comp range provided. The reasoning I have been given is that they would need to see what the references say in order to determine the correct role or comp range. So when I suggest they provide the comp range assuming I have good references and they decline to, that's a nonstarter and demonstrates they are acting in bad faith IMO. This is clearly the type of negotiation tactic where you want your counter party to invest as much as possible (by providing their references) so you have more leverage.