alfonsodev

I don't know if retyping is the solution, but for me is clear that we need something additional to a terminal and a code editor. I envision a software that an agent can use and showcase to you how it did implement the changes and why. The same way a colleague would do, focusing on the important bits, then ending with the trivial stuff. Something in between pair programing and code reviews.

I understand it like events + state machine type of approach. Reacts only renders and emits events, and I guess the state machine imperatively will dictate to react what to render according to the result of executing whatever is in the state transition.

a hype that lasts since the 70s can it be called a hype ?

in the context of learning I think it's good to execute yourself then see what happens immediately, once you allow the agent to execute things, it tends to run several follow up commands when needed, an example from top of my head would be running a server that fails because the port is already in use, the agent will easily find the port and decide to kill it or not and then re-run the command, but if you run the command and see the error, then you get the chance to learn what's going on and how to fix it. You can still use the LLM to read the error and explain you why this happens, according to this guidelines.

And the killer killer issue is that even if you would manage to talk to them, their opinion will be shaped but what AI told them and AI opinion will always be perceived as superior, your real world experience and instinct will be disregarded quickly.

For some people it becomes more like a ritual, some groups of friends do it together as something social to talk about football, I think it leads in some degree to people paying attention and talking about lower rank matches :D

I've played a couple of times solo and in group but never sticked to me.

No related to the point, but what it did stick to me for one season was La Liga Fantástica from Marca ( a fantasy league on paper) when I was a child, because it had the data component, you had a budget to pick players etc, This was before we had internet broadly, if I remember correctly the paper would publish huge lists with the teams ranking or the players stats. But what I do remember was some of my best players like Zalazar :D

Alright, is just that your previous comments and some others sounded to me a bit too judgy, I had to re read these with a new interpretation:

> i wouldn't be surprised if he just becomes a glorified marketer for anthro.

> im also going to guess that whatever research he does ...

At first sounded like unnecessarily prejudging a person and his future efforts.

But if you say you meant everything out of respect for him, then I have to re read what you said , more as skepticism towards Anthropic than picking up on him at a personal level.

I guess what's behind is the sentiment that big companies are going to (or have already) cross ethical lines when it comes to survive and making revenue, and I can share the same concern easily. I think in this forum the majority would do.

I would just make that more explicit and separate the person from his choice, and his future work from how the company could use it, that would be a more respectful way in my view.

But is just my opinion! and I'm aware I'm might be picking on nuances that don't matter or being overly polite :D

And it makes a lot of sense, doesn't?.

There are things that you can only explore and learn in those places, for obvious reasons.

I don't know his personal life goals but he's a great communicator and educator, if this decision makes him more up to date, and allows him to create even more relevant content then is something everyone will benefit. I understand the risks of being bias toward one company and not the other, but if you look at the content he created so far, he always talk principle first and specific tool later.

I think people here should give him the benefit of the doubt.

good to hear! Do you mind sharing your setup and tokens / seconds performance ?

My combo is codex and claude basic subscription for planing the hard tasks (if any) opencode with GLM 5.1 (z.ai coding plan) for the actual coding.

opencode is awesome I don't miss cluade or codex cli at all, and the z.ai plan is way more generous in compression.

I was lucky to subscribe to z.ai coding plan pro when it costed 30$/month, I was surprised now it costs 70$/month.

In case anyone wants to subscribe to z.ai with 10% discount [1] * here is the credit campaign rules * [2]

- [1] https://z.ai/subscribe?ic=MW6H74HAZ0

- [2] https://docs.z.ai/devpack/credit-campaign-rules

That's what I though too, maybe I'm missing something or I don't fully get it. But the human is always behind what's the difference if they go and sign up or tell an agent that they must sign up for you ?.

My best guess is that this a way of making a system talk to your agent without you knowing what they are talking about ? As a way of not exposing the real sign up method ?

do you mind to elaborate ? are you connecting from out of Spain, I'm curious how fucked up the situation is.

> This is the sort of heavy-handed, tech-illiterate, authoritarian.

Totally agree with this, it's ridiculous and a shame.

I personally don't use any infrastructure provider from Spain, but you wouldn't solve any problem moving out, and also those providers are not the ones to blame or punish. Only customer connecting from Spain are affected where is the infrastructure does not solve the problem.

IPs are blocked at Spanish internet provider level, the problem would be if you have customers in Spain, but it doesn't matter where you move your infra, if your ip is in one of the affected IP blocks, customers from Spain won't be able to reach no matter in what country is placed (what happened with docker pull )

I did manage with Cloudflare's WARP, now is called Cloudflare One [1] because the 1.1.1.1 DNS

- [1]https://developers.cloudflare.com/cloudflare-one/team-and-re...

after looking more into it, I must say I agree with "Why not tmux" section but I'm missing some comments on how this tool helps reducing the context needed for operating the TUI tool, for example when using capture-pane the agent can decide how much to read, I need to dig dipper maybe it's self evident but I'd like to see upfront how using this tool impacts token usage, specially if it saves tokens compared with giving the agent access to tmux.

I could make agents use delve (a go lang debugger) interactively, and it worked quite well specially when models weren't as good as they are now, they could choose where to put the breakpoint and inspect variables, I found that was the only way to unlock some situations when they insisted in that "it must be working", and it wasn't, I found that giving them the empirical tools to check for themselves was the only way to unstuck them.

Another use was for them to read the logs out of your development web server ( typical npm run dev, go run .)

I could do this with tmux send-keys and tmux capture-pane, you just need to organise the session, panes and windows and tell the agent where is what.

That was my first agent to tool communication experience, and it was cool.

After that I experimented with a agent to agent communication, and I would prompt to claude "after you finish ask @alex to review your code". In the CLAUDE.md file i'd explain that to talk to @alex you need to send the message using tmux send-keys to his tmux session, and to codex I'd say "when you received a review request from @claudia do .. such and such, and when you finish write her back the result of it" I added one more agent to coordinate a todo list, and send next tasks.

After that I got a bit carried away and wrote some code to organise things in matrix chat rooms, (because the mobile app just works with your server) and I was fascinated that they seem to be collaborating quite well (to some extend), but it didn't scale.

I abandoned the "project" because after all I found agents were getting better and better and implementing internal todo tasks, subagents ...etc plus some other tmux orchestrations tools appeared every other day.

I got fatigued of some many new ai things coming up, that and the end, I went back to just use iTerm, split panes, and manually coordinate things. Tabs for projects, panes for agents, no more than 2 agents per project ( max 3 for a side non conflicting task ) I think that is also what cognitively does not tire me.

My project name was cool though, tamex, as in tame tmux agents :)

And to comment on the submission, I think the idea has potential, I might give it a try, the key is to have low friction and require low cognitive load from the end user. I think that's why skills after all are the thing that is going to stick the most.

Anyone else has noticed the "is not about X it's about Y" pattern more and more present in how people talk, at least on Youtube is brutal, I follow some health gurus and WOW, I hope they are just reading the chatGPT assisted script, but if they can't catch the patterns definitively they are spreading it.

I refuse to get contaminated with this speech pattern, so I try to rephrase when needed to say what it is, not what is not and then what it is, if that makes sense.

Some examples in the AI rant :

> Not because it was wrong. Not because it broke anything. Not because the code was bad.

> This isn’t about quality. This isn’t about learning. This is about control.

> This isn’t just about one closed PR. It’s about the future of AI-assisted development.

Probably there are more, and I start feeling like an old person when people talk to me like this and I complain, to then refuse to continue the conversation, but I feel like I'm the grumpy asshole.

It's not about AI changing how we talk, it's about the cringe that it produces and the suspicion that the speech was AI generated. ( this one was on propose )

>I myself am saving a small fortune on design and photography and getting better results while doing it.

Is this because you are improving your already existing design and photography skills and business ?

Or have you bootstrapped from the scratch with AI ?

Do you mind sharing or giving a hint ?

Thanks!

do you mean https://github.com/nektos/act or there is something else ?

Is this the Typescript of C ?

Really cool, I’m curious what would be the comparison versus a deterministic bot that uses probability tables.

Thank you! I think I'll start with the water supply and air humidity monitors, vitamin D (supplementing), iron and B12 shows normal in blood tests.

> get her out of the damn house for one or two weeks Yes, this is my thinking too, I'm trying to solve the logistics of that as well, and hopefully we can do it soon enough.

Thanks a lot for sharing that.

Now that you say water sources, I just remembered she has a reverse osmosis water filter, and God knows the last time that filter was changed.

How would you go about testing the water or the filter with that method ?

Thanks a lot! I'm going to look it up.

Thanks for sharing that experience, it means a lot.

Sometimes it feels like the health system is just about keeping you alive, and they don't dig enough in different posible root causes, they focus on treating the symptoms, specially with elderly.

> That would not have been hard

I understand the feeling, and it inspires me to look for a second opinion and someone more involved in finding a root cause. I'm sure in your case you did what you though it was best with the information you had, the reality is that the system does not invest in prevention and education of us patients and relatives. Knowing certain demographic is high risk should be somehow automated to raise flags when certain symptoms are mention even if they are in-passing mentioned as you said, because we as regular people are not educated to weight the importance of symptoms, and often doctors get defensive if you come with a theory.

The other day I was at the doctor, he was asking me many things, trying to figure out my stomach problems, I though I had a stomach flu, then really at the and by chance I mentioned I was at the dentist the week before and they gave me antibiotics for 7 days, it was only then with that small comment that I almost forget to say that the doctor could have the explanation, he said some antibiotics wipe out the gut microbiota, and it just gave me some probiotics and I was fine the day after, with a big improvement. I don't know how much time would have take me to recover if I would have forgotten about that detail.

When I think about it after the fact, duh! of course antibiotics kill gut bacteria, I heard that a million times in podcasts, but I did not make the connection.

My point is that we have enough in our plates and our profession is already quite complex, we deal with tons of complexities and it shouldn't be our job to know the right questions, or the right doctor to go for, but I wish there was a system that focused more on preventions, and finding the root cause with a more multidisciplinary approach rather that specialized niche knowledge doctors that ignore other causes, or symptoms if they are not present if their knowledge map.

> but that does sound like mold, and the mold could be progressing those symptoms

That's both my fear and my hope, if you have any good resource that I could educate myself about this hypothetical type of mold that can accelerate the symptoms of dementia, please share, would be very useful.

Thank you

At the risk of sounding stupid, I’ve noticed my mom’s house smell has changed a lot in the last year and is stronger in her room and bathroom, coincidentally or not, since she has started showing mild dementia symptoms and has been diagnosed with vascular dementia. She feels extremely tired despite standard blood test markers being OK.

The smell could have simple explanations, like she forgets to ventilate the room, or her hygiene is not as good as before, since she has become more avoidant of any discomfort, but we are helping her with the hygiene part at least, the ventilation is harder because she complains about cold, and refuses to leave the room. Also to me, it is a different smell from what would be poor ventilation and from what would be lack of hygiene, but I can’t point out what it is. I'm usually very good detecting when a room has not been ventilated, I just feel I breath worse and can't focus as well, I'm annoying to other people that doesn't want to open the window.

She spends most of the time in bed, her body is telling her to sleep much more than before, and she has become very stubborn about getting out of the house, going to the dentist, etc. Since she is very intelligent and still has the verbal ability to make you believe she will do it as soon as she feels better and that will be soon, the reality is that months are passing by and that is not happening.

I wonder if anyone could recommend an affordable but effective air quality device, mold testing kits (if such a thing exists), or what targeted blood tests can be done. Also, if there are tests to fine grain the diagnosis of vascular dementia, to know if there is accumulation of proteins in the brain, or what is the origin of the issue.

She is 79 years old, perhaps there is nothing to do, but somehow I feel the environment of the house has something toxic in it, I even thought about electromagnetic fields, but I really don’t know where to start.

Edit: We live in Spain, her doctor feedback is that her blood tests are great for her age, and we didn't have much info about the vascular dementia situation somehow has been implied that is normal in her age.

I use llm from command line too, time to time, is just easier to do

llm 'output a .gitignore file for typical python project that I can pipe into the actual file ' > .gitignore

How do you handle interaction ?