MoreRSS

site iconGabrielModify

A Canadian who is passionate about the free and open web.
Please copy the RSS to your reader, or quickly subscribe to:

Inoreader Feedly Follow Feedbin Local Reader

Rss preview of Blog of Gabriel

Experimenting with the dark arts

2025-06-23 02:09:32

Does Gabriel still do tech or is it all just weight loss now?

I’ll admit my weight loss journey and IRL activities are taking up a great deal of my time these days, but I’m still very interested in expanding my technical knowledge! I hope my techie friends will appreciate this post where I try out AI agents so they don’t have to. Of course I will be posting another weight loss update soon, things are progressing well!

My first foray into automation software was an Android application that let you do all kinds of fancy flows. I genuinely believe that accessible automation tools are a genuinely useful thing that any OS should have built-in. Accessibility is a real way to give users power over their own computing. I’ve noticed that most of the refined solutions for automation are commercial products, which in turn means you’ve got to become even more dependent on Big Tech infrastructure. For those of us comfortable around shell scripting, a node-based automation tool can seem like overkill, but there are many people who could benefit from one. The general idea of flows and automation graphs seem to be genuinely interesting things and I’m hoping we see some exciting developments there in the software freedom space.

But this post is about my latest dabbling into the potential of self-hosted “AI agents”. After speaking with James Corbett about many concerns related to artificial intelligence tools, I decided it would be worth spending the time to get a better grasp of what’s possible. Since this was only a brief look at these tools, I am in no way claiming to have advanced knowledge of their use. I am sure many of the problems I encountered have well-known solutions, but I mostly wanted to see how far I could go in experimenting. This is my personal experience with learning how to use self-hosted tools for automation and AI agents.

WTF is an ‘AI agent’?

AI Agent node in n8n

AI Agent node in n8n

My uncharitable explanation would be that an AI agent is merely the introduction of LLM chatbots to an automated process. For example, instead of parsing an email for keywords to react to it, you can feed the content of the message to an LLM to decide what to do with it. Depending on the model being used, a variety of different tools can be given to the LLM to perform various actions. Since an LLM can generate a list of steps, the idea is based on providing it the tools to actually run those steps.

Having spent some time tinkering with it, I can understand the appeal. By burning an insane amount of resources you can hopefully have the AI agent smooth over trivial problems that arise in your flow. Instead of worrying about minor details, the idea is to get the LLM to simply make the best of the inputs. Provided the problem is broken up into simple enough choices, I can imagine this being quite powerful in specific contexts.

What I find bizarre is how the so-called “reasoning models” start their prompt with self-generated instructions with <think> tags. This means that for every prompt, there is a beginning section where specific instructions are reiterated and elaborated on. I can see why this would help them come up with more useful outputs, but at the cost of additional tokens and attention. This also means that at least when using these models you’ll have to filter out the <think> content prior to responding. I have a feeling that publicly accessible AI chatbots have these kinds of features to sanitize outputs prior to being presented to the user.

‘Reasoning’ example

<think> Okay, so the user wants me to create a concise outline for an article about Mexico’s telecom reform and human rights risks. They’ve shared what appears to be part of the HTML source code for the press release.

{Multiple paragraphs about the article’s content}

For the heading, something catchy but also formal would work well to capture attention while maintaining professionalism. Then I’ll craft a few paragraphs summarizing the main points of the article and explaining its significance in terms that show both immediate impact on Mexico citizens and potential broader implications. </think>

To me, it’s fascinating that this “reasoning” by the model is longer than a decent summary would be. It’s definitely possible that this tactic creates significantly better outputs, but it’s at the cost of so much more compute every step of the way. Part of the idea of how AI agents are sold is the idea that with dozens of these you can replace real human teams. It seems clear to me that to the degree you can replace human workers with LLM-driven automation, it may end up costing multiples of their income in raw electricity, never mind the potential legal and copyright issues.

How did I set it up?

While I wanted to dip my toes into understanding AI agents, my principal goal was to understand what was possible while self-hosting. I’m sure there are so many very different tools for building and using AI agents in the cloud; I would prefer to use self-hosted but ideally free software options. With a limited look around, I didn’t find Free as in Freedom tools for the automation side, never mind the licenses around particular LLM models. So I essentially had to settle for open-source and self-hostable. If you’re aware of fully-free AI & automation suites, I would love to know.

Based off an admittedly quick search, the simplest AI agent tool I came across was n8n which is open source but certainly not focused on Free Software. What I did appreciate about it was its simplicity and support for RSS feeds. I had a simple idea for what I wanted to try out, and RSS support made it a lot easier. The projects website has a collection of templates you can use to import for your own uses. That’s pretty sweet, but I’ll elaborate more on that later. You can install n8n or run it as a docker image. It is a web-based GUI (a WUI?) for building automated workflows and running AI agents.

For your AI agent to work, it needs to be able to connect to an LLM API, such as the big tech ones, but I wanted to try self-hosted. Originally, I wanted to see if I could get GPT4All because the docs claim to support a server mode, but I couldn’t get that working. Instead I opted for Ollama which allows you to serve many LLMs.

Configuring self-hosted ollama on n8n

With Ollama serving Qwen3 over the API I was ready to start my AI agent journey. I wanted to come up with something that could potentially be useful for me, so I would actually be motivated to get it to work well. I chose to try to see if I could build a tool that would read some of my RSS feeds and write me a simple report on pressing issues. The hope would be that if one is using a self-hosted model, with selected RSS feeds and a constrained focus, that many potential censorship issues could be eliminated. If it worked, it could absolutely save me the toil of keeping up to date on many things I struggle to keep up with. I wasn’t aiming for perfection, nor to automate what I care about, just simply to see if such a tool could save me time.

How did it go?

After a great deal of tinkering, I got it to a point where it provides a reasonably useful output. There are many things I would fix if I really wanted to devote the time to perfecting it, but I’m not convinced it would be worth the effort. I really liked playing with n8n, but I’m convinced AI agents are wasteful trash. Part of this is even though I’m providing a set of information to work with, it will still hallucinate additional articles. There are many quality control issues regarding repeating articles and inconsistent formatting. I’m aware you can fix some of this with better prompts, but I expect the path of least resistance for many will be to simply add a “checker” agent and just recalculate the output. This makes zero economic sense when one is paying for their electricity. I believe this will be the mechanism that pushes people on to using artificially subsidized Big Tech infrastructure and not decentralized or self-sovereign AI.

In case you’re curious, my flow begins with a list of RSS feeds that can be updated however we want. It wouldn’t be hard to have it pull from a server or .opml file. It then loops over the items to grab the RSS feed contents. Simple sort and limit nodes are to get only the most recent items. Then each article is given to the “Summarizer” AI agent which actually does a not terrible job at converting rss content into a few paragraphs about it. I then have to filter out the <think> content before passing it along. I also merge the summaries with the original list so that I can preserve attribution. I have another code note that combines and formats the articles and their summaries so that they can be sent to the “report writer” AI agent. The report writer then takes all the articles and their summaries and is supposed to create a pretty HTML email report. I yet again have to use a code node to remove the nasty <think> tags from the output as well as other irregularities. Then the final report is sent to me as-is without any interaction on my part.

When the report writer isn’t just hallucinating articles the proper link is there almost all of the time. But often enough it will simply link to example.com if it has any trouble. Not only that, but you will often see the same article/summary/link combo multiple times in the same email. I am convinced it would be much better to simply use a code node to build the HTML email with the data than to rely on the “AI Agent” feature for that specific task. If I was to go back and fix things I would have the “report writer” agent simply look over the summaries and write a report which would then be used to enhance the email.

Ironically, the fact that a bunch of code nodes needed to be used at all is a bit disappointing to me. It seems like as someone with technical ability, I’d be better off scripting on my own with whatever I want to talk to llama than to use javascript with the n8n suite. But I will say that n8n does have a lot of useful built-in nodes that make it very easy to get started quickly. Having done all this, I think AI agents are still quite far from being something one can expect in a freedom respecting environment. The path of least resistance will always be to simply cobble together Big Tech systems rather than to actually support decentralization and self-sovereign computing.

Closing thoughts

I can definitely say the short time I spent looking at this was valuable. I’ve gained a more refined understanding of how these systems are used, and what can be done beyond merely copy-pasting your homework into ChatGPT. I am genuinely impressed with what is possible from a self-hosted setup, and can imagine many valid use-cases for the software. This has shown me that we may need to rethink what making computing free (as in freedom) means for people with less technical ability. I’m definitely interested in learning what kinds of free software exists for automation, and observing projects like unit. As always, I’m convinced there is a remarkable amount of opportunity if independent technical minds are supported to do what they do best.

Doing this has congealed my feelings about corporate open source quite a bit. I used to be relatively ambivalent towards corporate open source because on some level the money has to come from somewhere. But I’m beginning to recognize first hand what many others have warned about for quite some time now, that Free computing and non-free computing are absolutely at a bifurcation point. The middle of the road is gone, it is clear we will have to choose what kind of a technological future we want to participate in.

When it comes to AI agents, I can definitely see the dark side. Just search “generate post” into the workflows page and you’ll see how many flows exist for generating information pollution. The fact that the online hustler of the 2020s can generate slop without any technical ability is yet another nail in the dead Internet coffin. I think it’s important for me to share this exploration so that people can imagine what tools are being used by governments, corporations, and other entities to carry out their duties, and what kinds of impact this can have on people.

I am now convinced more than ever that the destruction of the open web (for non-technical people) is the point of the pushing “AI” into everything. I fully believe that the free and open web will always exist in some form, but it is clear to me that there can’t be sustained via any commercial means. In some ways this might be the best thing ever, the future of the indieweb will be bright if it’s maintained by people out of passion and care rather than clicks and comments. It just means that the minds of the public are going to need to be prepared for a much more hostile information environment than what we’ve experienced to date.

In short, AI critics actually don’t hate AI enough. This may sound extreme. Even if I extrapolate that these tools work so much better with big tech infrastructure, that won’t fix everything. The fundamental aspects of inserting LLMs into various automated flows seems so much more wasteful than paying people to do work. It is clear to me that the AI hype isn’t actually about sound economics but actually about economic warfare. It won’t matter that doing things with AI agents instead of paid staff will likely cost 10x what it would cost to pay a human a real wage, what matters is that consolidating the technological landscape will yield more returns than money can buy. The point is that using LLMs to fix problems created by LLMs is the robotic equivalent of bullshit jobs, spending money on robotic make-work to market demand for AI “solutions”.

As I stated in my chat with Corbett, I don’t believe that technology = implementation. I don’t think machine learning is evil, nor that we can’t build useful tools with it. I am however very concerned about how political and economic forces are shaping this industry to build “aligned” AI against the public. This has been conspicuously absent from high-profile conversations about “AI safety” and expect it to be a driving force of many near-term trends.

Thank you for reading this through RSS 📡

Walk with me: Below 400 🎉

2025-06-02 19:10:39

Big Success!

I’ve finally hit a major milestone! I’m over 175lbs down, and finally below 400lbs. I had the pleasure of somebody telling me they’re noticing that I’m ‘wasting away’ over time. Feel free to join me on this walk where I celebrate this milestone, reflect on recent challenges and how I hope to overcome them. I truly didn’t appreciate how close I was to this milestone when I started. Far from being impossible, I have had the roller-coaster of making it actual.

As I write this my 4xl shorts are already loose enough they need to be tied to stay up. It is clear to me that I have reversed all of my post-2020 weight gain. In so many ways I feel ’normal’ again, because I’ve spent so much of my adult life around this size.

Learning to weave

Ankle pain has become a bit of a constraint on my activities. Instead of stubbornly repeating the same activities expecting a different outcome, I’ve been thinking about how I can approach this differently. Reflecting on this reveals to me that there actually is a great deal of opportunity for growth, and it’s reassuring to find other areas I can work on with less strain. I think this generalizes well to other situations. I understand that just because you’ve hit diminishing returns in a single area, that doesn’t mean there aren’t other ways to continue making progress.

A big part of this has been facing my own mental limitations. It’s clear to me that I recoil from the unfamiliar, and crave steady familiar routines. This is quite the realization considering my ‘routine’ has been so chaotic and counter-productive. I’m recognizing the power of making strange things familiar. This process takes a fair bit of time, but I’m recognizing the incredible power of it. To apply this, I have a goal of attempting to make a variety of new exercises feel familiar to me. Instead of confining myself to merely walking and swimming, I need to expand my exercise options.

Recognizing momentum

I can no longer deny that this is working. This may shock many people, but only now that I’ve lost 170lbs am I really beginning to ’trust the process’. I am now much more confident and dragged down by fear and despair a lot less often. It took a lot of faith to get to this point, but I’m beginning to really feel the changes in my mindset and emotional responses to challenges.

Because of this, I can report that I’m beginning to even out the emotional waves of this process. I feel a level of peace with it that seems entirely unfamiliar. It’s a shame that it took this long for me to truly recognize the power of gradual but consistent improvement. I am immensely grateful for being at this point, and recognize it as the blessing that it is.

I hope that in some small way, the journey I’ve taken can already show others that they can get started. I certainly wouldn’t have believed I would be where I am today as recently as a year ago. I am glad I’ve shared as much as I have, and I wish I had done more in the earliest days.

Are you aware of any health/fitness channels on PeerTube?

The only channel I can think about is Shifter which is a channel urban cycling, particularly in Canada. I found this video on winter cycling very informative! I’d also be curious to hear of any small independent blogs and/or podcasts that deserve more recognition!

Recent Finds

Thank you for reading this through RSS 📡

New video: May Update

2025-05-18 02:39:11

Watch on PeerTube

Looking back at the past

I sat outside in a chair I recently wouldn’t fit in to record a video update. I’ve been having a lot of complex feelings about my journey thus far. While I’ve made fantastic strides in mobility and functionality, I’ve found myself often dwelling on what still can’t be done. In response to this, I decided it was time to revisit some of the content I have from when I started this journey.

I have a folder of published and some unpublished vlogs, audio recordings, and loads of photos. At the end of 2023 I shared my frustrations and goals for making 2024 a year of change. Changes really started small. I began focusing more on swimming and using floaty weights but I knew a lot needed to change to truly make lasting progress.

Unable to avoid the fact that my out-of-control eating habits were holding me back, I decided to write out all my known troubles with food. to try to come up with strategies to tackle them. By the middle of 2024, I got a very lucky break. Already focusing everything I had on making change, I was ready for bolder steps. I decided to hire a trainer for guidance and to rebuilt my mobility. Cautiously optimistic, I realized that this could be the pivot point where I finally begin to see lasting results. Armed with a scale I could actually weigh myself with, I was able to accomplish my first recorded weight loss in a long time.

Of course, this important step didn’t erase all my existing troubles. So much of starting out, and continuing from here is a significant struggle with problems I’ve developed over the years and the consequences of my size. It was enlightening to go back to the start of my journey to reflect. I still very much have many of the same problems and complaints, but I can see the many improvements.

In an early example of gratitude I wrote out the many things I look forward to, some I’ve accomplished already.

Milestones

Activities

  • ✅ Going up stairs without a thought
  • Biking
  • ✅ Getting better at cooking
  • ✅ Comfortable with long walks
  • ✅ Doing more things away from home / less hesitant to go outside
  • Visiting friends abroad / being able to travel generally
  • Taking on more physical hobbies and crafts

Body-weight exercises

  • ✅ Lunges
  • Pull ups
  • Push ups (Working on it!)
  • ✅ Plank
  • Hand-stands

The little things

  • Being able to move without having my own body in the way
  • ✅ Standing for longer periods of time
  • ✅ Fitting in ordinary bus benches
  • ✅ Not having to lean on things while doing basic tasks
  • ✅ Getting in and out of cars easier
  • ✅ Putting on shoes & socks
  • Staying in a clothing size long term
  • ✅ Easier hygiene
  • No longer living in fear, regret, and pain from my size

Under & Over

  • ✅ Under 500lbs
  • Under 400lbs [ALMOST! (ETA: End of May 2025)]
  • Under 300lbs
  • ✅ Over 100lbs down
  • Over 200lbs down (ETA: Summer 2025)
  • Over 300lbs down (ETA: 2026)
  • Leaving Obesity Class V

I wish I had more writings from these early days. Even now I’m much more comfortable writing out thoughts than being on camera. I’m very glad I decided to start my Walk with me series where I casually share monologues on my journey. In some ways I find myself having less and less to say, things are moving along and I just need to keep at it. I’m very grateful that many people have found these updates interesting or comforting.

It’s great that I at least have a fair bit to look back on. It seems that I should have done a serious retrospective earlier. I am so happy the warmth and sunshine is back. Thanks for following my updates, and if you have any questions or thoughts don’t hesitate to reach out!

Thank you for reading this through RSS 📡

Walk with me: Learning to be patient

2025-05-08 22:47:29

This morning I went for a short walk and recorded some of my current feelings about my weight loss journey. Things are going well, but I’ve got a lot on my mind of late. In this walk I share how I’ve been reassessing recent changes to try to regain focus and drive. I’ve come far enough to not be able to ignore that I’ve made progress, but also far enough to be a little disheartened by what remains. Listen to me try to be patient with myself as I come up with new avenues to tackle these problems.

Recent finds

Thank you for reading this through RSS 📡

(Tor) New vanity address

2025-05-07 05:57:14

The hidden service (on Tor) for this site has been migrated to gabriel262me3lgv3w7xohtesg3laoojmtye644pwirhdm73qmedmsqd.onion. The previous address was on 3ah6l32ons2mzb65rchl3uz7nrgkecfof4eey7dwmamt5fcvok4h2yad.onion so it’s nice to have a more recognizable one. I’ve set the old .onion to redirect to the new one so there shouldn’t be any issues for visitors. I’m not sure how RSS readers handle 301 redirects, but I assume anyone who pulls RSS via Tor can figure this out.

mkp224o

The documentation on the Tor Project website recommends mkp224o to generate vanity addresses. The tool generates as many .onion keys as possible and saves matching domains to a folder. The longer your desired prefix, (called a filter) the longer it’s going to take to ‘find’ matching addresses. There is a feature that allows you to search for multiple ‘filters’ at once, so it’s best to think of as many acceptable variations and alternatives as you can for longer filters.

You can simply run mkp224o yourprefferedprefix if you like, but there are a variety of useful options worth considering.

  • -d {folder} puts all the generated folders into a specific location
  • -f {filter file} matches ‘filters’ in a file, one per line
  • -S {seconds} prints statistics every x seconds, such as how many addresses are searched per second.

How to generate your own vanity address(es) for your own Tor Service

  1. Install mkp224o
  2. Create a list of your desired filters in a file.
  3. Run mkp244o -f filters_file -d vanity_addrs -s 360
  4. Move your favorite .onion keys files (eg. to /var/lib/tor/yourdomain)
  5. Reconfigure torrc to use your new keys file(s)
  6. (Optional) Make sure to update your Onion-Location on the clearweb!

Thank you for reading this through RSS 📡

Walk with me: Recovering Momentum

2025-04-28 05:30:29

I’ve deliberately avoided using denoiseit to clean the background noise because it would feel wrong to remove the birds singing. I hope you’ll enjoy my off-the-cuff walking monologue about my ongoing journey. I’ve had a difficult start to Spring, but I’m really beginning to rebound. I’m looking forward to making the best of May.

Progress update

Unfortunately, April is definitely not as successful as March was. Last month I was down 20lbs and this month I’m only down 11 so far. I can think of quite a few reasons why that was the case. I’ve been pretty stressed, and I’ve been finding it more difficult to control portions. Some good progress has been made correcting these mistakes. Spending time focusing on improving my rest and stress management has made a significant difference on my mood, motivation and drive.

It is clear that I need to re-balance my energies to continue to push hard in a balanced and reasonable way. I am facing significant life challenges outside of this journey at the moment, so my ability to withstand pressures is absolutely being put to the test.

Losing the spark

I recently wrote about hitting a wall of soreness that kept me down quite a bit. It was quite the challenge to learn to rebound from a funk of disappointment and difficulties. Beyond unrelated stressors, a lot of my frustrations have been centered around feeling disappointed in myself. While I’ve made massive strides in strength, mobility, and weight loss, many things I want to do feel out of reach. I’ve vastly underestimated how much difficulties still remain in this difficult road.

I can walk for a decent amount of time and do many things I couldn’t before, but I struggle to properly appreciate these smaller wins. I am so fixated on what I still can’t do that it’s very difficult to have the required gratitude for the situation I’m in. When I really think about it my quality of life has been transformed in many ways since last Summer, but that’s not the same as being finished. While I certainly understood I would still have weight to lose by this point, I fully expected to be able to move better in this body by now.

I’ve seriously underestimated the challenges of being 400lbs while also overestimated the mobility and strength progress that could be made over the last few months. These mismatched expectations have had me languishing in frustration and despair. As shocking as it may seem to those who follow these updates, I am regularly feeling like I may never escape these troubles. It is clear to me that the important progress that remains is going to take quite some time. Day to day, I have an arduous struggle of trying to constantly remind myself that things are changing and real progress is taking place. With the understanding that I haven’t given myself enough time to grow, I really need to practice patience and gratitude to keep my head in the game.

Body image troubles

In addition to all that, I’ve been having very extreme swings in my body image feelings. Some moments I’m feeling like things are all coming together and I just need to be patient, and other moments I feel like nothing has changed at all. Despite losing over 150lbs in total, it is still often quite difficult to recognize the progress. I think part of it is that it’s only a quarter of my highest body weight, and less than half of what I need to lose in total. Again, it seems that my mismatched expectations were the driving cause of my frustration over the last few weeks.

I can definitely say the difficulties of this journey make it immensely difficult to have a positive self-image. Many of the wide variety of things that are still out of reach for me are all very quick reasons for me to feel useless or like a waste. I have found that working on stress management and getting better sleep does make a big difference. It absolutely makes how hard all this is crystal clear to me. It is very easy to spiral into a typhoon of terror, denial, and self-loathing when things aren’t going well.

Something that helped a lot recently was being able to comfortably fit into 4XL clothes, down from 6XL. I effectively ‘skipped’ 5XL because I don’t really intend on buying every size down to whatever I end up at. I underestimated how staying in the clothes I started in for so long would make it harder to appreciate the change. I’ve noticed that feeling comfortable in the smaller sizes does quite a lot for physical and even mental comfort.

Learning to reignite the passion and drive

One advantage to doing this as long as I have is that I’m beginning to recognize some patterns and cycles. I always get nervous when my weight trends closer to my 2-week moving average. This is because I essentially take it as a sign I’m losing momentum. For the last few days, I’ve met and gone above the moving average. One of the patterns I need to resolve is stressing out about stress. Whenever my weight isn’t comfortably below the moving average, I begin to worry and then worry about worrying which makes things so much harder.

Thankfully this time around, I’ve noticed that this exact scenario has happened before. At the start of Winter I can see a very similar pattern where I poke above the average for a brief time. It is reassuring to know that I have faced this before and it does not need to be an unbearable crisis. I guess the transition between seasons is just always a tricky thing for me in this process.

It was really helpful to remind myself that as awful as this all is, it’s not permanent. By rediscovering the gratitude for the fact that I can change this situation I am feeling better about this difficult time. I’m trying to really put my problem back into perspective so that I can be happy about incremental progress again.

A question for you!

I’d really like to know what active hobbies you enjoy! I’ve been thinking about how it’s difficult for many people to stay active with busy lives so I’m very curious to hear about how people overcome this.

Recent finds Roundup

Thank you for reading this through RSS 📡