ttoinou

AI is notoriously bad at estimating length of tasks. Like humans.

Doing more, understanding more the tech of the project, exploring more ideas, the list is infinite

Who got more time thanks to AI ? I think a lot of us are working more instead

I have tons of friends who know HoMM III, it’s the game of our youth

I think it’s also popular in eastern Europe

The calorie theory is the same theory that leads people to believe they can exercise to loose weight

How to do that exactly ?

The thing the OP describes happens in France as well

Im sorry if I come across as aggressive, Im myself chill and just here to talk, share and discover new things. Analogies are essential to learning I agree with you

Of course maths need intuition, it isn’t always incompatible with being rigorous

But yes some who have PhD in physics don’t always care about understanding deeply maths tools. Depends what you’re doing

You can absolutely deal with complex numbers with the (x,y) notation

You can use exponential with matrices as well.

That some people don’t want to understand deeply the tools they use don’t make their tools superficial or “hotfixes”

Get a m5 pro mac with 48gb vram and you’re good to go for a few years and that computer can be used for others purpose as well

I recommend Visual Complex Analysis by Tristan Needham

Have we settled on a really good universal approximation model of memory+computation or is this a hard topic to solve in itself ?

Calories don’t exist and it is unscientific to believe in them

Literally just built this with claude this week to handle all outputs of my GPU generating videos and images

AGI doesn't mean Omniscience

What ? If that experiment was done on monkeys I don't think they had to use Android / iOS / iPadOS interface themselves. All they had to do is push a button

Oh that’d be nice indeed

Lots of small details are taken care of so it runs smoothly. For example ds4-agent is append only, never rewriting history of messages, keeping KV cache prefix reusable. Huge benefit

I’m already able to use 1M context windows with the same machine than you and same model. Strange

Ive been using this since it was initially released with deepseek v4 flash, and it is absolutely the best launcher ever on my m5 max 128gb

Now Ive been running qwen 3.8 flash next for more than a week and it’s doing great, really fast and super long context windows. Sometimes the model is behaving stupidly by not remembering something I said earlier but it could be also a problem from the agentic AI harness. Im using oh my pi but Im wondering what people are using ds4 with here ?

The reality is probabilistic, and engineering has always been about turning that into deterministic behavior and outcomes, in an industrial, repeatable, observable, debuggable way

I wouldn’t call Chrome a pile of shit software. If anything else we should learn from this project

And the web is the most advanced and open OS in the world. That all those features can be packaged into a 100MB binary is magic

Isnt this obvious ? I would have thought people would try such things before deciding they need something like Jev

I doubt this can really be deterministic, but maybe this is where Jev models can be useful

   Before editing each agent publishes an intent and the scopes it will change, with the operation it plans to complete on each one.

But we don't know in advance what we will need to change in our current task. And even if we did, there are always side effects.

I'm curious to know what's everyone custom solution to this problem ? Before AI and with AI.

It was already a problem for me before agentic AI coding : multiple developers can work on overlapping code and you always need someone to merge everything properly. Even if the overlap is very small it does add a burden to development. Not an issue anymore in 95% of cases if that person uses AI to solve conflicts, but now that "others developers" are swarm of AI agents, this problem isn't trivial to solve.

France, 1658 <-> World, 2026. AI can also do the reverse : for example very few in the world know that the term midwit was originally coined in french by Blaise Pascal (« demi habiles ») centuries ago.

Yes, that bell curve meme, he wrote about it. It’s not explained anywhere because of the language and culture separation between french and english. But if you ask enough questions to AI, the AI will eventually find about Blaise Pascal and tell you about this unknown link. It’s magic.

How are the behavior described imperfections ?

The AI "incidents" are pure marketing ploys to get free word of mouth. Like what you're doing.