Anime girl level cataclysmic security events definitely don't worry me as much as laughing man (笑い男) cataclysmic events; only then it's when I really start to panic.
I started taking daily classes learning the Thai language in person. While I do learn Thai with AI sometimes, I do feel like an AI tutor can't possible give me the same "edge". Because with AI can just sit down, get…
It is (mine)! And there is a purpose to it looking AI generated. However, the sample projects where actually fully worked on; mostly as hobby projects. I will have it go through another iteration of improvements soon.…
Awesome! Have been a bit in the dark of the latest models, will have a look. I am due an upgrade for my local machine and GPU, so that excites me as well.
Whenever I see the new releases around video generation (and image) generation models, I get goosebumps, because it just feels so fun to work with them. But then I remember that I spend upwards of $10k on inference…
SEEKING WORK | Senior Django/Python Web-developer & AI Engineer - Platform, Architecture, Ops, Applied AI Location: Thailand (UTC+7) Remote: Yes, and available for hybrid arrangements in Thailand. Technologies: Django,…
Why does Railway deserve any blame here at all? It was an MCP with elevated infra access, that the user willingly connected through Cursor, which allowed an LLM Agent to manage infra on Railway. The user would first…
SEEKING WORK | Senior Django/Python Engineer - Platform, Architecture, Ops, Applied AI Location: Thailand (UTC+7) Remote: Only Technologies: Django, Python, PostgreSQL, Redis, Celery, HTMX, Tailwind, Docker, APIs,…
I keep having this conversation with clients. If you want to allow an LLM to delete, create or update data; you need to do this with a human in the loop, and explicit hitl gating against execution; where the agent can't…
SEEKING WORK | Full-stack Python/Django Developer (Gen-AI image and video generation) Location: Thailand (UTC+7) Remote: Only Technologies: Django, Python, HTMX, Tailwind, Postgres, Replicate API, image generation…
Whenever I saw people complain about LLMs writing code, I never really understood why they were so adamant that it just didn’t work at all for them. The moment I did try to use LLMs outside of Django, it became clear…
When I see stuff like this, I feel like rereading the Incerto by Taleb just to refresh and sharpen my bullshit senses.
Django has been one of the biggest reasons why web development has been so enjoyable to me. Whenever I switched to something else, I just felt too spoiled by everything that Django gives you. So I always ended up back…
This will get better over time, there will be ways to make LLM output more uniquely yours. I personally enjoy writing all my blog posts with LLMs, because its the only way I can bring to turn countless of notes and…
I am using Django, HTML (JS - AlpineJS & HTMX). Each page is just created from scratch rather than from some CMS or template, I use Claude code for that (with mem0.ai as MCP) and build my entire development workspace…
The issue for them is that once the tools exists, adoption only moves in one direction. And it will enable a whole wave of new artists. I sympathize with them, but if I enjoy GenAI art creation and see it as my genuine…
No I am using my own workflows and software for this. I made nano-banana accept my bounding boxes. Everything is possible with some good prompting: https://edwin.genego.io/blog/lpa-studio < there are some videos of an…
Yes, the prompt is composed of 7 different layers, where I group together coherent visual and temporal responsibilities. Depending on the scene, I usually only change 3-5 layers, but the base layers still stay the same;…
Yes we are definitely doing the same! For now I’m just familiarizing myself in this space technically and conceptually. https://edwin.genego.io/blog
How much have you experimented with it? For some stories I may generate 5 image variations of 10-20 different scenes and then spend time writing down what worked and what did not; and running the generation again (this…
My own blog, and then having conversations with people through e-mail (strangely enough). I feel that if I just am on my own platform, nobody is going to rug-pull me in a few years to come, contributing online to social…
SEEKING WORK | Full-stack Python/Django Developer (Creative AI Focus) Location: Thailand (UTC+7) Remote: Only Technologies: Django, Python, HTMX, Tailwind, Postgres, Replicate API, image generation pipelines, LoRA…
SEEKING WORK | Full‑stack Python & Django developer (AI Focus) Location: Thailand (UTC+7, outside Bangkok) Remote: Only Willing to relocate: No Technologies: Django, Python, Postgres, Redis, Celery, HTMX, Tailwind,…
I was building an multi-agent system connected to Telegram. There is one agent that synthesises a response through 5+ other agents. Initially I was tweaking the system through my IDE, making small adjustments to promps…
Anime girl level cataclysmic security events definitely don't worry me as much as laughing man (笑い男) cataclysmic events; only then it's when I really start to panic.
I started taking daily classes learning the Thai language in person. While I do learn Thai with AI sometimes, I do feel like an AI tutor can't possible give me the same "edge". Because with AI can just sit down, get…
It is (mine)! And there is a purpose to it looking AI generated. However, the sample projects where actually fully worked on; mostly as hobby projects. I will have it go through another iteration of improvements soon.…
Awesome! Have been a bit in the dark of the latest models, will have a look. I am due an upgrade for my local machine and GPU, so that excites me as well.
Whenever I see the new releases around video generation (and image) generation models, I get goosebumps, because it just feels so fun to work with them. But then I remember that I spend upwards of $10k on inference…
SEEKING WORK | Senior Django/Python Web-developer & AI Engineer - Platform, Architecture, Ops, Applied AI Location: Thailand (UTC+7) Remote: Yes, and available for hybrid arrangements in Thailand. Technologies: Django,…
Why does Railway deserve any blame here at all? It was an MCP with elevated infra access, that the user willingly connected through Cursor, which allowed an LLM Agent to manage infra on Railway. The user would first…
SEEKING WORK | Senior Django/Python Engineer - Platform, Architecture, Ops, Applied AI Location: Thailand (UTC+7) Remote: Only Technologies: Django, Python, PostgreSQL, Redis, Celery, HTMX, Tailwind, Docker, APIs,…
I keep having this conversation with clients. If you want to allow an LLM to delete, create or update data; you need to do this with a human in the loop, and explicit hitl gating against execution; where the agent can't…
SEEKING WORK | Full-stack Python/Django Developer (Gen-AI image and video generation) Location: Thailand (UTC+7) Remote: Only Technologies: Django, Python, HTMX, Tailwind, Postgres, Replicate API, image generation…
SEEKING WORK | Full-stack Python/Django Developer (Gen-AI image and video generation) Location: Thailand (UTC+7) Remote: Only Technologies: Django, Python, HTMX, Tailwind, Postgres, Replicate API, image generation…
Whenever I saw people complain about LLMs writing code, I never really understood why they were so adamant that it just didn’t work at all for them. The moment I did try to use LLMs outside of Django, it became clear…
When I see stuff like this, I feel like rereading the Incerto by Taleb just to refresh and sharpen my bullshit senses.
Django has been one of the biggest reasons why web development has been so enjoyable to me. Whenever I switched to something else, I just felt too spoiled by everything that Django gives you. So I always ended up back…
This will get better over time, there will be ways to make LLM output more uniquely yours. I personally enjoy writing all my blog posts with LLMs, because its the only way I can bring to turn countless of notes and…
I am using Django, HTML (JS - AlpineJS & HTMX). Each page is just created from scratch rather than from some CMS or template, I use Claude code for that (with mem0.ai as MCP) and build my entire development workspace…
The issue for them is that once the tools exists, adoption only moves in one direction. And it will enable a whole wave of new artists. I sympathize with them, but if I enjoy GenAI art creation and see it as my genuine…
No I am using my own workflows and software for this. I made nano-banana accept my bounding boxes. Everything is possible with some good prompting: https://edwin.genego.io/blog/lpa-studio < there are some videos of an…
Yes, the prompt is composed of 7 different layers, where I group together coherent visual and temporal responsibilities. Depending on the scene, I usually only change 3-5 layers, but the base layers still stay the same;…
Yes we are definitely doing the same! For now I’m just familiarizing myself in this space technically and conceptually. https://edwin.genego.io/blog
How much have you experimented with it? For some stories I may generate 5 image variations of 10-20 different scenes and then spend time writing down what worked and what did not; and running the generation again (this…
My own blog, and then having conversations with people through e-mail (strangely enough). I feel that if I just am on my own platform, nobody is going to rug-pull me in a few years to come, contributing online to social…
SEEKING WORK | Full-stack Python/Django Developer (Creative AI Focus) Location: Thailand (UTC+7) Remote: Only Technologies: Django, Python, HTMX, Tailwind, Postgres, Replicate API, image generation pipelines, LoRA…
SEEKING WORK | Full‑stack Python & Django developer (AI Focus) Location: Thailand (UTC+7, outside Bangkok) Remote: Only Willing to relocate: No Technologies: Django, Python, Postgres, Redis, Celery, HTMX, Tailwind,…
I was building an multi-agent system connected to Telegram. There is one agent that synthesises a response through 5+ other agents. Initially I was tweaking the system through my IDE, making small adjustments to promps…