lobochrome

Same for me - I mostly ask stuff in English but sometimes add specific terms or names in Japanese as needed. My Japanese is intermediate, but it will often switch immediately and reply only and entirely in Japanese. I'm pretty sure they have a system prompt with hairline triggers for foreign languages BECAUSE of the overrepresentation of English in the training corpora.

Why they so angry?

How did PRISM affect civilian life?

It is ! I’m “solving” it with an app called bartender. It’s hacked and sometimes doesn’t work but was the only way I could manage this problem…

Apple software sucks so bad!

(except United)

So you want OpenAI to create “laws”?

I for one do not want ai labs to designate what is legally ok to do.

I much prefer the demos to take care of that.

Or it was just a botched git op

The Howard Hughes of our time. Soon enough he will start pissing in milk jugs.

This rule wasn't enforced anyway...

I travel a lot - and never take out any liquids. Have nail clippers and scissors in my carry-on.

Once I even had an opinel pocket knife in my laptop bag for a couple of months.

Travelled through Tokyo, Taipei, SFO, DEN, PHX, LAX, BOS, JFK, FRA, AMS, MUC, LHR - nobody noticed.

I seriously had forgotten it was there, so I don't do that now, but still...

Also, no large water bottles or similar. Unless on domestic flights in Japan, where this is totally fine.

IDK - security theater. But if it helps.

Stupid Cisco Umbrella is blocking you

KPIism is the death knell of modern society. In the 90s and 2000s this mantra of "measure and improve" took hold like a virus. It is in all instances I observe a rats race where everybody just starts to look for the cheat-codes instead of "doing-the-right-thing".

Arguably America is the pinnacle of this right now, where (many) politicians and (many) business leaders now feel justified do whatever's legal just to score points. I would argue this type of thinking was birthed in the UK though under Thatcher who as a first step removed the general trust in (civil servants in her case) your fellow human beings. Blair then came up to replace that trust with KPIs.

We need to get back to a world where we trust people to do the right thing - without measuring their success in short-term KPIs.

Kagi.com

Is there a way to let the agents share their agents.md? Claude code looks at Claude.md and I have yet to find a way to unify the agent handbook.

I’ve driven past that house a million times and always thought to look it up - and always immediately forgot again.

Now you reminded me and I know the backstory

Really?? Which countries allow copyright infringement by individuals?

“The quip about 98% correct should be a red flag for anyone familiar with spreadsheets”

I disagree. Receiving a spreadsheet from a junior means I need to check it. If this gives me infinite additional juniors I’m good.

It’s this popular pattern of HN comments - expect AI to behave deterministically correct - while the whole world operates on stochastically correct all the time…

In the end - action matters. Somebody didn’t put the bolts back in.

Yes - zooming out it important and ultimately where actionable remediation can be applied - but blame is due where blame is due: somebody fucked up at work and it almost brought down a plane.

So - the gruber shadowban has been lifted eh?

The inverter would melt presumably.

I see this behavior all the time. When it can’t read a file using its read tool - it escalates up to try with bash. Often it tries to search the entire file system “find / …”

Also there is an existing system of 7 numeral post codes that autopopulate Prefecture, City, District - leaving you to enter Area # (丁目）, Block #, House #.

If they amend this to make it alphanumeric and then autopopulate this last three datums - it fits very neatly into the existing scheme.

Warfare.

It knows uv now

"LLM just complete your prompt in a way that match their training data"

"A LLM is smart enough to understand this"

It feels like you're contradicting yourself. Is it _just_ completing your prompt, or is it _smart_ enough?

Do we know if conscious thought isn't just predicting the next token?

A bit thin. Seems like they got the MoU done first - without solving any of the hard questions.

Also - big warning that they're highlighting "wave" and Toyota Technologies in general.

Object-oriented languages provide little value because a programmer’s job is to think

Memory-safe languages provide little value because a programmer’s job is to think

…

I remember when Siri replaced the original voice recognition. “Call XYZ” etc. after a long press of the wired remote.

To this day, it’s less reliable. Also Siri can’t text my wife who has two phone numbers in my address book. Although there is just a single iMessage chat - Siri always asks (Which one? - without offering options!!!)

The old farts in Apple management need to go and pronto.

The ossification of the entire management layer is really reall frightening and a terrible sign for a company.

I bet we saw peak Apple in 2023/24.

Yeah - also can't reproduce. Maybe some helper is messing around with you?

The question for me is, whether the web still has enough distributed creative spirit left, so that individuals still feel a need to create.

I.e. instead of feeding my reviews to the rent seeking giants, I can just publish them on my own and they’ll be helpfully ingested and made useful by chattyG.

The dis-aggregation of the aggregators?

The holodeck is never going to be a VR goggle.