mgaunard

Train stations also have Yakitori, Udon, Ramen...

While giving instructions via mobile is useful, it's naive to think you'd have the same productivity as behind an actual desk.

The thing I'm starting to see now is that managers believe AI is what enables all this stuff to be done, not the people actually driving it.

Even though everyone has the same tools and it can clearly be seen not everyone has the same output.

I'm surprised to find out there are actually people who like Oden.

You can also just copy your strings into the same buffer in C++ if you want to.

The obvious downside is that resizing any string but the last requires moving everything down the stack.

With objects that never need resizing, you can of course have much simpler memory layouts.

You can also just do that in C++. I do that as part of my messaging usually, so that the objects are trivially relocatable and reinterpret-castable. It only works so long as you combine a set of canonical types, but that can be verified or converted using C++26 reflection.

I have both what I call inline sequences, and out-of-line ones (store an offset to the object itself rather than pointers).

I made all my sizes and offset 32-bit, but I suppose they could have been 16-bit.

The difference between a forum and a chat is mostly UI and structure.

On a forum, every conversation is within a thread for example.

Chat is unthreaded by default, even if Slack allows threads. It also allows users to create channels and manage who's on those groups, while the forum equivalent is fixed up-front and only opt-in.

So really chat is a forum that's a bit more free-form.

If your company authors software for computer-assisted design of buildings, are you in the software industry or in the construction industry?

The first is what it might say on paper, the second is more honest and reflects the real business value.

Technically AI makes it much easier to reverse-engineer software, so long as the guardrails don't randomly kick in.

So by "more ambitious", people really mean "waste more tokens"?

Software is not an industry, it's a tool that all industries use.

I never worry about presence in any form of chat. I don't care if people are there when I message them; it's up to them to pick up my messages at their convenience.

in general discord has a very bad app and usability, irc regardless of client is a clear upgrade

The main issue with mainstream AI is lack of a decent cloud agentic harness on a free tier.

This is just a sub-par harness on the most expensive tier. If you're paying thousands a month for AI surely you can rent your own EC2 instance.

I find that I can do 4 to 7 sessions in parallel, and still review everything in depth and co-design.

I mostly use Fable though, Opus only via sub-agents.

what's most surprising is the difference between high and xhigh

> how would you compare your capabilities to that of claude fable 5.1 by anthropic

> Comparing your capabilities to that of claude fable 5.1 would be very similar. Both are stories about a clown who is a cunning and manipulative animal. They both have problems and challenges, and they face challenges to overcome them. However, they have different goals and approaches. The clown

I think that tells you all you need to know.

MCPs are indeed useless, they're very limited in functionality and frequently struggle with large requests or get wedged in bad states.

There is no reason not to use the native API directly.

Then most people would be wrong.

A VLIW ISA is a classical example of a superscalar processor without out-of-order execution.

It's already transparent even without out-of-order execution, and pipelining is an entirely different thing than superscalar execution.

Any modern processor has different execution ports specialized in different things and replicated a different number of times, and all of them can execute instructions in parallel.

It schedules to these transparently for you, that's known as superscalar execution. To maximize occupation, out-of-order execution and simultaneous multithreading are used.

> This project is still early in its developement. Bugs, crashes and miscompilations are expected. DO NOT USE IT FOR ANYTHING SERIOUS.

how can one claim it is tier-1?

Also random student, nothing official from Microsoft.

All those applications area sensitive to asynchronous programming.

does it mean there is a rust.net?

it's not part of the free ChatGPT tier.

it's supposed to work from whatsapp. It's US-only so I could not verify.

None of them lets you have a hosted dedicated agent with real browsing capabilities on the free tier.

I disagree. It matches exactly what I need.

Whenever I try to do something with ChatGPT or Gemini, it just refuses to do things citing limitations in its web browsing capabilities. An everyday LLM that can actually fill forms and do stuff for you on the Internet without having to run on your computer, write programs or interact through special harnesses is what normal people actually need.

It's a different need from the agentic coding type of LLM, where you provide the environment where it can write and execute arbitrary code.

I mostly fly flights that are less than 2 hours (I'm in Europe).

Unfortunately as the crow flies that seems to be closer to 800 miles than 125.

I'm in London and the airport itself is already 60 miles away.

Those are all precise and meaningful words that are very useful in software design.