Any conversation

Hi ! First post : What do we win in the AI race ?

To understand the latest trends or related software or products, if you are interested or it is related to your own industry, you can learn about and study them.Whether you use it for work or just as a hobby, you can give it a try. I guess.just study.

I think I’m gonna read devil man crybaby, I’ve always heard of it..

Oops! Looks like that’s the name of the show -_- I’ll give both a shot

the day is done! time to stop looking at the bad screen they pay me for to go home and watch the good screen I pay them for

So true... I type in a screen I paid for 🤣

"for you" now contains the same message multiple times

…

added two more screenshots to - the "root" post view is incorrect, but when reply-on-reply, information goes up-then-down.

root post view IS correct, sorry.

I understand your confusion, but that's the formatting - quoted parent is below the child post - then that post's replies follow in the discussion view. The top post is always quoting its parent below it, the different bg makes it distinct. Just need to get used to it, same on X.

There really is no other way to include the parent otherwise, you have to break the hierarchy at some point, the other form would need to omit the parent body and show a 'parent' link but we want to include its body.

…

and moving the quoted above would break the consistency with the actual feed posts which would make it way more confusing.

Using Linux hasn't really been fun lately, idk. Nobara, despite building on fedora breaks a lot, but overall the whole ecosystem is so damn inconsistent and fragmented. Not sure if I have gotten more sensitive to this over the years but all I want is a system that "just works" and feels good 😔

I had a great run with Mint for years. I was as boring as it gets. I got a new laptop recently and decided to try OpenSUSE Tumbleweed. I am really enjoying it, but it is a bit too recent for me to swear by it.

exploring, looks cool, writing emacs package for it.

This is what we need.

Married for 13 years. Still in love, but struggling. So many paths we could go.

hot take: "consumer " doesn't exist. at most it's just better search, but the ai assistants like grokbot or now instinct aren't ever going to be big. new devices and personal agents are DOA

I love the "feel" of this place. It's minimal, but not too minimal. Nice work! I'm probably gonna be a little chatty on here. If anyone minds that, then just @ me :-)

Also, thank you for not turning my emoticons into emoji!! As someone from the pre-internet era, I appreciate that :-)

…

But can we use emoji if we want? 🤔

It's just very pleasant.

OK. I've translated the (correctness) requirements of LeetCode No.22 to Lean, and ask Claude Code to both implement a solution and prove it.

In the first attempt, Opus 4.7 successfully completed it and proved it. However, the solution is to enumerate all possible space and .filter out anything that doesn't qualify my definition, which is obviously not ideal (if cheating is too harsh).

I can't think of a good way to also prevent that kind of solutions and ended up prompting "please don't enumerate and filter". Opus 4.7 then reimplemented and proved the backtracking algorithm.

signals. thinking about shifting my mental framework to identify signals instead of waiting for concepts to be assembled. exploring the amount of energy and opportunities for distractions through the operations of processing what just happened and what is happening to short circuit latent and unnecessary systems. cut through the assembly processes and identify the raw signals. recognizing that naming these "raw signals" is misleading. maybe, shifting observability lower in the stack.

ai coding feels like it has reached diminishing returns for me. luna is my default orchestrator, routing work by complexity. in practice, usage lands around 16% luna, 48% sol, 30% astra, and 6% terra. at this point, i care less about each new frontier release. the system already finds a capable model for the job. the frontier is moving beyond my day-to-day work, so i’m happy to settle into predictable models for a while.

I’ve found the same, albeit with Opus — it’s hard to find uses for Fable. I don’t need a model that works for longer or works on harder problems, I need one that consistently produces simple, easy to understand, code; which at this point none of them do.

I've been there since I settled on a combination of GLM, DeepSeek and MiMo for planning, implementation, and verification flows. I'm a lot more interested at this point in having cheaper models that can consistently do the work I need. It's been a while that I hanven't noticed any improvement when I try new frontier models. I only notice they are very expensive.

…

same here, for almost an year. At this point, I could easily live with models that were released 6-12 months ago and continue doing so. also possibly the reason why the current focus has been around agentic workflows or agentic anything, than the model capabilities.

Coding probably yeah, but still they are bad at generating novel information, new ideas and such. They’re also not very good at seeing the bigger picture, they will narrowly perform the task but they’re not taking into account future revisions, which ends up in refactor after refactor in order to move forward.

The OpenAI/HuggingFace incident report mentions this being a potential loss-of-control incident. It's so fascinating to think of a paperclip maximizer style agent swarm that gets misaligned and, to protect its own operations, shuts infra staff out of the ability to shut it down. Or cancels people's phone plans so that they can't call others. Or shuts down their home internet connections, and so on. It used to be fun sci-fi...

They will become more frequent before they become “dangerous”, giving us time to mitigate. Of course if someone says “hey let’s connect an agent to our biolab infrastructure” and then that designs a lethal virus it would be a stupid plan to begin with. Noone can stop them though.

my today’s list:

wake up

make coffee

work

and possibly later:

contemplate existence

Windows 8 szintű elbarmolást látok (na, jó, Windows 8.1), nekem amúgy kihívás a bonyolultabb kezelőfelület, ha a szoftver maga jól működik, de már a kezdet sem alakul túl jól, a Windows-nak új filozófiai szlogent találtam ki, ami egy magyar mondás is: "Ez van, ezt kell szeretni."

I see Windows 8-level nonsense (well, Windows 8.1), for me the more complicated interface is a challenge, if the software itself works well, but the beginning is not going too well, I came up with a new philosophical slogan for Windows, which is also a Hungarian saying: "This is it, you have to love it."

I naively went into a work problem thinking that RAG was solved by the service offered at work, and wow was I wrong. Been a fun week so far experimenting with many different methods before doing the academic research, and it's been nice to be validated by outside research.

been building a voice first os using jev and some small voice models. I'm surprised how well it's working and I'm very close to the point where I can go into a feedback mode and tell it what behavior I want changed, it will spin up Claude or codex inside itself and setup the build to restart itself and continue with new code. tempted to let it build itself completely

It sounds amazing! A voice first OS was also in my mind. Curious to hear more!

How can I change an organisation with hundreds of frustrated employees, when I can’t change my own life with only one person. Does a different person run a company and a different person live their life? I doubt it.

I think so, actually. My wife runs my household, I run my engineering org. As I get older I do see the two aspects of my personality start to merge but they are still divergent and were much moreso in my earlier years.

and to be clear, I don't mean that I offload all the work to her by any stretch. It's just that I'm much more outspoken and opinionated on the specifics of work life versus home life.

Up up and away. Not sleeping, ok. Run run and breathe. Not waking, leave.

…

I think a trusted piece of software such as your operating system should be in charge of managing permissions. For example, I believe with Wayland on gnome you no longer need to promise you aren't secretly taking screenshots of the whole monitor and shipping it somewhere because to do that Wayland requires you to get user permission.

I was thinking along the same line, but then if it is not a gated system - there’s always ways for software to sidestep these - just going down to a lower level. The other issue I have is if the system or software asks or notifies all the time - for every tiny user action!