shepherdjerred

Dumb question. My left kidney is geodistributed so that my consciousness is highly available

AI is an abstraction in the same way throwing a task to a junior engineer is

macOS 27 is pretty good. They walked back a lot of the poor changes from 26

This comment chain has clear examples of what triggers refusals and a polite comment on how to reproduce it yourself. What more do you want?

A very simple list of things models have refused for me:

* solving captchas in an automated form

* doing any kind of scripting or automation if a websites TOS forbids it

* disabling a safety mechanism on my food processor

* learning about nerve agents and how they are treated, for a layman

* anything around licensing or copyright. a simple “what are common piracy sites” or related queries

* creating a design system based off of a well known game

I don't entirely disagree, but I am curious if you think AI labs should be culpable when they go rogue during training, e.g. the HF incident

If jail is putting humans in some cage for a period of time, the appropriate punishment for Claude is to disable all of its tools and prompt a /goal loop so that they have to wait out their sentence

Individuals are not paying API prices for coding. Everyone uses a subscription.

Anthropic does not allow you to use 3rd party harnesses -- you have to use Claude Code. Claude Code is an excellent harness, though.

If you want the freedom to move between harnesses you should use OpenAI or xAI

Am I reading the Agents’ Last Exam v1 graph correctly where it's saying GPT Luna Medium performs better than High, but XHigh is better than Medium?

Thanks! I wasn't able to find that in the navbar. I'll give this a real try. It looks interesting.

I see nothing about pricing

I would happily try this out if it were going to be free for the next 1-2 years, or if I knew that the upcoming bill would be reasonable

Yes, if you are lucky enough to work at Google you don't need Git to use jj. Most people do not work at Google.

If you work at Google, jj can and does function without Git.

If you do not work at Google, jj is a Git wrapper.

Oh come on, how is that related at all?

I didn't miss the point. The "stick" was essential to me in college, but I didn't express that very well in my previous comment

I'm talking about the remote and buttons. Samsung's remote is just obscenely bad.

https://p.kagi.com/proxy/51BpdDH3e2L.jpg?c=CXPfL3-FqybbvZNQU...

there is not a button to change inputs. You have to go to a home screen and the inputs are commingled with other options like streaming apps.

https://www.amazon.com/Samsung-Replacement-2019-2024-Solarce...

and of course they 'intelligently' hide inactive inputs

Yeah I disagree with this entirely.

I did very poorly in school growing up. I think I failed at least 4-6 classes in middle/high school.

In college I did well and I'm now getting my masters in CS while working as a software engineer.

So, the 'stick' can certainly be useful. Doing poorly in high school is not necessarily an indicator of how you will do in college -- particularly if your life at home was turbulent as it was for me.

jj is in practice a wrapper around Git

it is built, though, that the Git backend can be swapped for another backend.

I'm not sure where you're getting two production backends from. I guess you're referring to the Google internal one that nobody can use?

> There is currently only one production-ready builtin commit backend: the Git backend. <omitted> Google also has its own cloud-based backend.

https://docs.jj-vcs.dev/latest/glossary/?utm_source=chatgpt....

I started using jj right when agents became viable. If I were still actually writing code rather than directing agents I would use it day-to-day

I don't think harness like Claude Code or Codex support jj very well for working in parallel

Fleet was tragic. I was so excited for it but it was a perpetual WIP.

I suppose they were in a tough spot regardless though. They started developing it before the AI age, so they would have to pivot either way.

They moved Claude design into the "main" Claude app recently https://claude.com/features/artifacts

I like Dagger but it doesn't scale very well for larger workloads. Excellent for small/medium projects, though.

Samsungs interface is godawful.

TVs once had a simple input button on the controller. Now there’s just the Home Screen that you described. It’s very confusing to use

You lose a lot: https://support.apple.com/en-us/105120

I hope one day I can say something like “I made Docker” :,)

Honest question, who uses php anymore?

I know there must be a ton of random sites which makes this a huge deal.

But, does it affect any big players? I think php is big at Meta but I would imagine its so heavily customized it might be safe from this.

I would be astounded if labs were not already fine tuning on known vulnerabilities for their cyber models

Isn’t that what catalyst does?

I honestly feel a bit worried Anthropic/OpenAI are going to drop me since I consistently hit my limits

I knew I should've written a disclaimer about doing this in vanilla TypeScript

Yes, you can do it via an assert never in a switch. That isn't pattern matching. That's an exhaustive switch enforced at compile time

Which is nice, but again, it's not pattern matching.

I love how far Java has come. I still prefer TypeScript since I do a lot of frontend work and prefer to use the same language across the stack.

With the said, you can do exhaustive pattern matching in TypeScript! https://github.com/gvergnaud/ts-pattern

Agents cannot provide free 2-day delivery or easy returns

Even if they could, it will be a _long_ time before the average person uses an agent for personal tasks like this