Blogs

I have been using Hermes agent now for two months. The experience has been .. mixed. I am not sure if the results would have been substantially better if I had made some other choices than I did, but this post is not about that. To recap, the earlier episodes were: Me and my agent was the start of the journey. Me and my agent - part 2 (of N) was bit over two weeks in, about infra around it and setup of the agent itself. Me and my agent - part 3 (of N) was about LLMs I use with it. ...

This is actually bit unscheduled, but as I feel the content will not age gracefully, I chose to write what I experienced with my different LLM model experiments recently. In general, I value local compute over cloud compute, and especially if things of private nature are involved. However, sometimes local compute simply does not work. I have dabbled with different models as main model for the Hermes Agent: GPT 5.6 Sol (using ChatGPT Plus subscription) GPT 5.6 Luna (-//-) Qwen 3.6 35B A3B q4 mtp and here is a brief write-up about it. This picture unfortunately spoils the outcome: ...

In the previous episode - Me and my agent, I had just barely installed Hermes agent. Now, two weeks later, more reporting on my agentic experiment. Short version: I still feel that it is worth it and useful. I have added only one more recurring event to it (crawling my LinkedIn feed for notifications about people I am actually directly linked to), but it has pretty much replaced my all other search engines (and AI chats), as I like having history of the conversations, as well as potentially having them be bit more private down the road. The search experience is also superior to anything else commercial. Perplexity used to be nice, but I never got around to paying for it, and the free experience tanked badly this year; Claude/ChatGPT usually don’t reveal their sources consistently which makes them worthless to me as search engines as sometimes the LLM does make mistakes. ...

I have been bemusedly watching OpenClaw madness this year (well, Clawdbot start of January, Moltbot on the 27th of January, and OpenClaw after 30th of January). I have not really seen the point - while I see the temptation of telling computer to ‘do stuff’, my security background has led me not to trust computer with anything actually dangerous (e.g. work/financial/private stuff). Friday: The start seemed harmless enough, and useless.. Hermes Agent was released in March this year, and it seems to some extent bit more productized and sane than OpenClaw, but I am not really sure. So from the outset, I decided not to really go for the crazy ‘give it access to my computer and let Jesus take the wheel’, but instead this weekend I gave in finally to the dark side, and started Friday by installing Hermes Agent in its own container. ...

I have been using recently Anthropic’s (Claude) Fable and Opus at work, and OpenAI’s GPT for hobby projects. This is not about that, though, but instead about how my use of the Internet search engines has evolved over time. I hear there are number of people who use only chatbots for searching the internet these days. While it is actually very tempting (one chat window, all your questions answered), in practice it does not work out too well. ...

I have been taking digital photos since 2000 - initially on Canon PowerShot S10 pocket camera, later various larger DSLRs, and (mostly) nowadays also using camera phones. The software to deal with the pictures has never been that great though. Ancient history (2000-2005) I vaguely remember that in 2000-2005 I mostly dumped the .jpg files to various places. It is a wonder that I never managed to lose any significant photos that I cared about, as at the time I was not particularly meticulous about backups. ...

I have been doing software development for decades. Yet I have been never as optimistic about the future of my chosen career as I am now. I am starting this just from point of view of programming languages, for reasons I describe later.. My somewhat ‘played with or used for stuff’ programming language list is at 32 languages at the moment, but I am just covering about main ones to convey a point. ...

I have been quite keen about AWS S3 professionally from about ever since it debuted. And that is long time ago (2006). This post is more about my S3 at home exercise, which is not even two years old. Why S3? I’m not going to detail about that here (the at home part is the point of this blog post), but S3 has offered for two decades now pretty cool object storage. Here are some key aspects of AWS S3: ...

I started using it in late 2023, and never paid anything for it, so I definitely should not complain. Two and half years of mostly loyal service, but sometimes less is more, and I am moving on. Background Oracle Cloud offers very generous free tier. You could basically get (if you jump through some hoops to fight for sparse capacity) 8 VCPU/24GB RAM/200GB ARM machine, or consistently 2 VCPUs of X86 with also 200GB storage. ...

My home infrastructure observability stack has been relatively static (for some definition of static) for awhile. VictoriaMetrics + Loki has been ‘fine’. But I like dabbling with other alternatives, and this time it is Greptime. Greptime - what is it? https://greptime.com is basically unified storage of all observability data. I’m not trying to market it too hard here, but basically: It is Rust It handles storage in various ways local ( using Parquet format ) object storage ( no idea, not tried yet ) … It allows clients to use various APIs (this list is not exhaustive, just ones I find interesting) Prometheus Vector has built-in sinks for it pg, mysql it also has built-in GUI Integration with my infra Vector before Greptime I run Vector at home. Hard. Here’s the vector graph before Greptime: ...