transitorykris

Every interesting problem I ever had that I checked SO for was either off topic and modded down or the original poster said “I found a solution” and disappeared. Pure misery!

Also, some subset of developers on subscriptions are going to develop products that use the API, and some of those products are going to be successful.

Only a minor in mathematics here. That's interesting that it struggles with definitions. Maybe unsurprising given the different ways they're chosen and written (motivational, aesthetic, pedagogical, etc)? A big lever to keep hold of.

I like the pragmatic take on AI in mathematics. Running off and proving/formalizing things in incomprehensible ways is marginally useful, and probably harmful for any work that needs to move beyond it. But, there's value in what AI is capable of doing for working mathematicians, when used as a partner.

The genie is out of the bottle though. It's hard to see how there won't be weird and inscrutable branches of mathematics that LLMs build and use effectively _for themselves_, in the same way much of the slop LLMs write in spoken language is really for the consumption of LLMs.

Surely there will be a new kind of research mathematician that's investigating this output in the same way, say, academics in literature read.

Dentists are terrible and I find it impossible to believe any of them do it because they’re passionate about teeth.

> Any time I tried to use an LLM for a game-y thing, it would fall over. Maybe this is my own bias. I’ve been a game programmer for nearly 15 years, I think I know how things work. I can sniff out “bad” game code a mile away. But when it comes to Svelte web-apps, I’m decidedly less well versed and am inclined to think that whatever code the LLM produces is “good”.

It feels like the discovery of a specific form of gell-mann amnesia. I know when working with an agent through areas where I have domain expertise I catch bad assumptions, decisions, etc. But then, unfortunately, have to trust it much more where I have minimal expertise.

Are the bribes better in other countries because they don't have a funny euphemism and carried out loosely in public?

Is it necessary to equate AGI with consciousness?

To expand a bit for my current use cases. Inline routing of work to heavy task specific models, and prompt/context generation (user is asking something, what and how much should we prompt the expensive LLM with). Latency or time to first token does matter for some applications.

Or just write one gnarly detailed form and let the consumer generate the form that works best for them (preferably with their own local model)

Giving the same PDRs, docs, tickets, etc to humans will never give deterministic output, I'm willing to accept the same from my agents

You can easily use Jev without an LLM (consider Jev used to make truthy decision branches in a script). It's not meant to replace LLMs. The tech is not a competition. But OpenAI is certainly in competition with TypeSafe, they'll want to keep people in their own ecosystem!

These are two different layers in the stack that do two different jobs. Agent to agent communication across remote machines is definitely lubricated with tailscale, I’m not sure what value moving up the stack would bring at this stage?

My read here isn’t about connecting to remote machines in the sense of ssh, but presenting a unified view across herdr instances running on multiple remote machines.

This stinks of the same enshittification moves Docker made 10 years ago.

The ad in itself probably has no practical value. The surprising nature of its staying power is curious. And curiosity is a strong signal. Good luck.