plandis

Is there a reason you cannot specify your allocator of choice in Rust? AFAIK, the abstraction exists to do just that.

If I was a business owner I’d rather operate under laws that don’t have highly ambiguous definitions of terms that introduces extra risk that is unnecessary in other places.

I know which one I'd rather send tokens to.

Do you have access to Mythos? If not the choice has already been made for you.

The title is misleading and shifts blame from the driver to the machine.

Ultimately the driver is responsible.

Edit: For the folks who seem to think that this is marketed as unsupervised self driving, from Teslas own website it states

“Currently enabled features require active driver supervision and do not make the vehicle autonomous.”

https://www.tesla.com/fsd

I honestly find that quite hard to believe.

Lack of adequate calories and nutrition negatively compound. You lose the ability to focus, you increase your medical risk.

I experienced that in my childhood. It’s terrible. I did very poorly academically when I did not have access to food. It’s astonishing to me how fast my academic performance improved after consistently having access to food.

Saying you would rather put yourself at risk instead of hedge your answer on a minor interview question in order to increase your chances of getting a job offer seems like an issue with prioritization.

You’ve actively made the choice to go hungry instead of hedging your answers during an interview?

I certainly feigned enthusiasm when I was in high school to get an after school job in order to help my family buy food.

Are people worried they're going to start selectively enforcing copyright law?

Yes.

I’m not saying your conclusion is incorrect but the anecdote provided is survivorship bias. My childhood was much the same in the 90s.

There was a case recently where parents were charged with felony involuntary manslaughter, and felony child neglect because they let their 10 and 7 year cross the street unsupervised and a car hit them and the 7 year old died. As a parent if that’s the reality I definitely hesitate to allow my son out unsupervised when he’s a bit older. I can’t imagine losing your son in an accident and then have the state come down on you while you’re still grieving.

https://www.nytimes.com/2025/08/06/opinion/children-traffic-...

GCP has had outages. From a quick search it looks like they had a global outage less than a year ago:

https://status.cloud.google.com/incidents/ow5i3PPK96RduMcb1S...

Who is forcing you to exclusively buy into Apple’s ecosystem?

Are other competitors banned where you live?

A US based non-profit news organization isn’t going to spend money to pay lawyers to ensure they meet a regulatory burden that doesn’t affect their core demographic.

I could not agree any less with the author. I don’t want APIs, I want agents to use the same CLI tooling I already use that is locally available. If my agents are using CLI tooling anyways there is no need to add an extra layer via MCP.

I don’t want remote MCP calls, I don’t even want remote models but that’s cost prohibitive.

If I need to call an API, a skill with existing CLI tooling is more than capable.

It doesn't seem any more egregious than something like:

`git log --color --graph --pretty=format:'%Cred%h%Creset -%C(yellow)%d%Creset %s %Cgreen(%cr) %C(bold blue)<%an>%Creset' --abbrev-commit --`

Which is something I see a lot of people alias in Git for viewing logs.

Claude Opus can use a 1M context window but I’ve found it to degrade significantly past 250k in practice.

At first glance this seems like a crypto miner.

Maybe I’m a bot, I gave up waiting before the progress bar was even 1% done.

MacOS has a built in 4x4 window tiling which works for this purpose for me. I don’t find ever wanting more than 4 windows open on an ultrawide. Definitely not as powerful as something like xmonad but useful for the majority of my use cases.

Meta is one of the worst offenders here. They are actively lobbying at least the US Congress for laws that require age verification at the hardware/os level.

I’ve found this to be critical for having any chance of getting agents to generate code that is actually usable.

The more frequently you can verify correctness in some automated way the more likely the overall solution will be correct.

I’ve found that with good enough acceptance criteria (both positive and negative) it’s usually sufficient for agents to complete one off tasks without a human making a lot of changes. Essentially, if you’re willing to give up maintainability and other related properties, this works fairly well.

I’ve yet to find agents good enough to generate code that needs to be maintained long term without a ton of human feedback or manual code changes.

Yeah it’s extremely helpful to clarify your thoughts before starting work with LLM agents.

I find Claude Code style plan mode to be a bit restrictive for me personally, but I’ve found that creating a plan doc and then collaboratively iterating on it with an LLM to be helpful here.

I don’t really find it much different than the scoping I’d need to do before handing off some work to a more junior engineer.

That’s not evidence. You’re effectively saying “trust me bro” without a shred of proof to backup your claims.

I think the current government of California would significantly regulate firearms if they could. It’s prevented from passing more restrictive laws due to the US constitution and a Supreme Court which takes an extremely broad interpretation of the rights derived from the second amendment.

Right? I’d instantly reject any review sent to me if there were no tests.

Do you have a public repo showing your setup? I’d be curious to see it in practice.

I agree. Error or higher should result in an alarm and indicates that some corrective action needs to be taken.

This only works if society was okay with surveillance on private property. The wealthy can afford large tracts of private land and can afford to send people on their behalf to interact in public for many things. They can pay services to come to them as well.

I love that resource and reference it fairly frequently.

There is also this [1] which Aphyr collabed on which you might find interesting if you haven’t seen it yet.

[1] https://antithesis.com/resources/reliability_glossary/

I can reproduce this by covering one of the exterior mics used for ANC when there is a decent amount of background noise in the environment. It results in feedback that causes a high pitch ringing.

The AirPods Pro 2 don’t have this same issue. I can’t reproduce the same behavior regardless of how I cover the exterior on the pro 2s.

Dynamo is AFAIK, not used by core AWS services.

Causal profiling is something I infrequently use but I have been able to apply it outside of micro benchmarks in an orchestration system.

If you have a business process that is complex and owned by many different groups then causal profiling can be a good tool for dealing with the complexity. For large workflows in particular this can be powerful as the orchestration owner can experiment without much coordination (other than making sure the groups know/agree that some processing might be delayed).

What is your point?

Surely you’re not trying to draw some conclusion between an entire countries modern day medical field and a theory a person proposed in the 1800s, right?