Kinda sorta works. My little 1 day tool lucidVIEW. An Avalonia (so no Webview / bundled browser) Markdown viewer using Naiad (by @simoncropp , a super new library but for simple mermaid *it works*) to render svg (then to png because Skia.Svg SUCKS). Might go back to it but I

LLMs are being used as sensors. That’s the mistake. In ReducedRAG, LLMs never see raw data. Deterministic pipelines extract facts first. LLMs only synthesize what’s already been reduced and verified. If your OCR, audio, or video pipeline starts with an LLM, you’ve already

Problem: we keep using frontier LLMs as glue for jobs that are already solved. Solution: run OCR + NER locally in C# with ONNX Runtime. Deterministic extraction on ingest. Store the entities. Use an LLM later only if you actually need synthesis. OCR with Tesseract, then BERT

Time-boxed tool that escaped containment: ConsoleImage. A glyph-based terminal renderer using shape-matching, full-colour Braille (2×4 dots/cell), blocks, and temporal stabilisation so it’s actually watchable. Images, GIFs, videos, URL streams. Plus a custom document format and

Ok completing 4.1 and I'm DONE with ConsoleImage for a while. It can do live transcription of any video file to give synced subtitles. With color realtime rendering with a unique perceptual dithering system. NOW with scrubbing so you can use the cursor keys to navigate through

🚧 DoomSummarizer (PREVIEW / ALPHA) I’ve been distilling the lucidRAG principles (hybrid search, entity extraction, knowledge graph + evidence-grounded synthesis) into a console-first, local-first research assistant + personal knowledge base. Think 'big boy's Deep Research

Deep Research without Deep Pockets. I pulled apart the premium “Deep Research” tools to see what they actually do, then built the same workflow locally without needing a huge model or huge spend. The trick: make the pipeline do the hard work (search + reduce + evidence), so

v1 Of DoomSummarizer is out. It's a crazy deep research / auto knowledgebase system. Point it at a directory of word docs, pdf and markdown it'll index it all then answer questions about the contents. Point it at a url it'll parse the content, index it and tell you what it's

Wrote an article and published a nuget package sitting here in the hospital. mostlylucid.net/blog/simple-oc… (RDP over tailscale rules 🤓) Companion CLI and nuget packages linked at the top. Makes OCR & Named Entity Extraction SUPER EASY. #ocr #llm #ai #visonllm #namedentity

New blog article: StyloBot: How Bots Got Smarter - The New Frontier in Bot Detection (Part 2) mostlylucid.net/blog/botdetect… Covers in more detail how bot / scraper / fraud detection needs to change in the new post-LLM world of intelligent scrapers. And how my free OSS tool StyloBot

Ugh every time I think I'm at a stable leaving point and it DOESN'T QUITE WORK. Have the mosltylucid.botdetection nuget done at least (over 10k downloads and frankly before today It SUCKED). #aspnetcore #botdetector #dotnet #yarp Article: mostlylucid.net/blog/botdetect… Package:

I've low key invented a type of app, based on a "behavioural inference engine". ALL SORTS of possiblities for new systems, Spam, Segmentation, auto adjustng rate limits and accessible apis to clients etc... So now the 'poor cousin of OSS' .NET has a UNQUE application class 🤓

Behavioural Inference Systems Most “AI coding” today means asking an code LLM to write your whole system for you. Behavioural inference systems flip that around: use code LLMs to build systems that infer *behaviour*. That 'behaviour' is really just metadata extracted from

I see some weird things but this takes the biscuit. A vulnerability in the Companies House website, that let anyone view the private dashboard of any one of the five million registered companies, see directors' personal details. And modify them.