jerlendds

Yes, I havent seen research on this tactic specifically for language models but for generative image models you can find research thatindicates you get far more variety and diversity in the images returned when suffixing the context with "noisy context" such as random letters or something else unrelated that wont "confuse" it or make it go off the rails

Found this interesting paper today while searching around the keywords "attractor language networks". This part I found especially interesting:

*Attractor Models outperform existing models across two regimes, large-scale language-model pretraining and reasoning with tiny models.*

Im usually on Firefox and I haven't run into this. But I also spent the past 2 days building a Knitsail VM solver in Rust for pulling Google Search results. Works nicely, I gave chatgpt pro (6) a minified JS bundle, and some variables and entries into the VM and told it to reconstruct the VM in Rust. Only took a couple hours to get a zip with a solver I could plug into my crawler, made a few mistakes but codex fixed those up with minimal guidance. No more Google captchas for me :)

I unfortunately live in Alberta and I have to say Smith seems decently smart. Which is not to say I agree with or would vote for her but that shes very capable of getting things she wants. Seeing Alberta pop up on HN so often is disheartening. I hope she gets voted out soon or I just might have to move

VLM != LLM. Vision language models basically treat text tokens and image tokens the same. Post-training an LLM on images+text can improve its capabilities. Id recommend searching around the keyword VLM to find more resources on how multi-modal AI works.

- https://huggingface.co/blog/vlms

- https://en.wikipedia.org/wiki/Multimodal_learning

This is a fun rabbit hole I discovered. I'm currently reading the 2026 PDF: https://sigbovik.org/2026/proceedings.pdf which covers many topics that will likely pique the interest of the crowd here

I mean you might be able to if you squint hard enough but the experience of using it would be absolitely piss poor so no. Realistically speaking AI is not even nearly that good yet and buildong a browser is an absolutely huge undertaking

The sci-fi hand wringing is embarrassing. A huge chunk of the population is afflicted with mental health issues and the best psychitrists can seem to do is "Oh bro, wanna try some ketamine? Anti-psychotics?? Maybe some SSRIs, how about psychdelics?!" - this is a joke. Im all for more neuroscience research in every form because our contemporary understanding is embarassingly poor. This is a research tool for understanding what visual brain regions encode, not a mind-control device. Better models of brain function may eventually improve diagnosis and treatment of mental illness. Calling every neuroscience advance "Black Mirror" is not ethical insight. It saddens me the reaction so many commentors have here, it is just lazy technological illiteracy imo.

I personally just use pipes and tesseract, no need for another tool imo:

flameshot gui --raw | tesseract stdin stdout -l eng | xclip -in -selection clipboard

Yeah idk, this is weird as hell

Huh, I should sue google haha. I have a screenshot of their AI overviews spewing bullshit about my main username from the query "Find jerlendds". Ive tried it again and it appears to be slightly more accurate however my old screenshot says some nonsense about how I help track down international criminal rings via my osintbuddy project. Totally not true and it feels like it painted a target on my back. Too bad I dont have the funds to take them to court in Canada

Im doing the exact same thing but Im building my Obsidian clone with Rust and gpui and primarily with Codex. So far I estimate Ive been solely vibe coding it for ~15 hours now with only one small change made by hand. Id be interested in comparing notes/our different approaches to this. Feel free to shoot me an email at jerlendds at osintbuddy dot com if you want to chat.

I have a small demo video of yesterdays work here: https://github.com/jerlendds/mdi

Theres since been many additions, Ill update the video tonight

Beautiful work and it's always nice to see new projects in these spaces! I'm the creator of OSINTBuddy which is a somewhat similar project if you squint haha. We've just recently finished porting our web app to an electron binary (unreleased) for people who perform sensitive investigations (aka we have encryption at rest via Turso database) and collaboration features will be done via WebRTC + a signalling server.

I'm loving the approach you took to the UI! I had some similar ideas in mind and plan to build narrative reconstruction and timeline view tools too so it's really nice to see how others have done so! I'll definitely be following your work and I shared your project in the OSINTBuddy discord to hopefully get some more eyes on it :)

Great work, I hope you keep at it :)

Lol I feel the similar, I signed an earlier version when the Manifesto was far different but since they've changed it from that I now want my name removed >:(

One of the creators is Alex (former Google Chrome Project Lead ~ https://komoroske.com/) and we spoke on a Google meet call recently. He's currently trying to hype up confidential computing which is a cool technical challenge but I have my doubts in regards to confidential compute being super feasible/realistic. I suspect crackers/hackers will always find a way in

Some books Ive been reading/plan to read: https://studium.dev/books

I noticed some spam this morni g too, I didnt see any hate but the accounts were opening issues on repos with the issue content pointing to weird URLs. This happens on occasion, best to just report, ignore, and move on with life.

Paywalled, here's a better link: https://fortune.com/2025/11/08/peter-thiel-millennails-socia...

To find more: https://duckduckgo.com/?t=fpas&q=Peter+Thiel%3A+Capitalism+I...

Lately Ive been thinking about building a desktop app with Rust and Ive started exploring the gpui library from Zed to see what its capable of. I haven't entirely decided on what the app will be but I do know I need network graphs to satiate my graph obsession so I started the `gpug` project a few days ago. It's a network graph visualization library built on top of gpui: https://github.com/jerlendds/gpug

Built this last night and fixed a bug today. It's a proof-of-concept of how to render network graphs with Zed's (https://zed.dev/blog/gpui-2-on-preview) gpui library. I plan to turn this into a more general purpose component library somewhat following the style/API of Reactflow (https://reactflow.dev) and Sigma.js (https://www.sigmajs.org/)

OSINTBuddy - https://github.com/osintbuddy/osintbuddy

Currently thinking about how to wire in entity attachments into the plugin system for a wayback machine plugin

I have lots of bad and good ideas here: https://studium.dev/ideas

Some of them are simply things I want to try building for the sake of it and they already exist, some of them dont exist and are decent ideas, some are just awful

I feel seen, I do this in a markdown file which is built and uploaded to my personal site

For those curious: https://studium.dev - built with Quartz (https://quartz.jzhao.xyz/)

Well we agree they exist on different spectrums. The suicide rate is also very bad for psychotic disorders although far fewer people suffer from them. Having faced stigma and invalidation for my issues I suppose I let that rub off on me to the point I stigmatized others. Thanks for pointing that out, I suppose I should be more mindful in the future

Youre right its not just feeling sad but relative to the extreme symptoms of Psychosis, delression is very mild by comparison

[redacted]

IME Tauri performance sucks on Linux so thats something worth keeping in mind if you go that route (https://github.com/tauri-apps/tauri/issues/3988)

I really like this idea, I took a note to create an account and showcase some web designs I like later on. I've recently been using https://www.refern.app/ to collect design showcases but it seems like no one else uses their site for that haha

Looks awesome! I'm using tailwind in my open source project and Ive been really struggling with accessible colors, inclusivecolors sounds like itll be perfect for me

https://github.com/osintbuddy/osintbuddy - Node graphs, data mining, and plugins. This year I've rewritten the project to learn Rust and we're nearly at feature parity compared to the old Python version (github.com/jerlendds/osintbuddy). I'm currently working out how the Python plugin system will work and I've jotted down some thoughts related to that here: https://studium.dev/osib/architecture#existing-plugin-system...