Hacker News: cahaya

New comment by cahaya in "Launch HN: Context.dev (YC S26) – API to get structured data from any website"

cahaya — Thu, 09 Jul 2026 16:38:18 +0000

Nice, @grok how does it compare to Cloudflare that also provides a REST endpoint for structured markdown data and screenshots?

New comment by cahaya in "GPT‑Live"

cahaya — Wed, 08 Jul 2026 17:57:11 +0000

When GPT-Live in Codex, so i can walk the dog while shipping?

New comment by cahaya in "Please stop the AI confidence theater"

cahaya — Fri, 03 Jul 2026 13:43:33 +0000

I'm not disagreeing with the article, but I think you are right that if you use AI in the right setting it can do much more than the average ChatGP that outputs Linkedin like crap:

interdisciplinary teams/person + SOTA AI + Right context (customer/ internal pain points, access to the code, focussed Hackathon) = amazing cool things.

New comment by cahaya in "Rampart: 14.7MB model for privacy by redacting personal information"

cahaya — Mon, 29 Jun 2026 22:23:13 +0000

From X: Today, we are releasing Rampart: a 14.7MB machine learning model designed to protect citizens’ privacy by redacting personal information directly in your browser before it gets sent to any server.

Rampart: 14.7MB model for privacy by redacting personal information

cahaya — Mon, 29 Jun 2026 22:23:13 +0000

Article URL: https://ndstudio.gov/posts/say-hello-to-rampart

Comments URL: https://news.ycombinator.com/item?id=48726127

Points: 7

# Comments: 1

New comment by cahaya in "Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?"

cahaya — Tue, 16 Jun 2026 09:42:56 +0000

Asking for feedback:

Sorry for hijacking the convo, but you (with local models) are my target audience in terms of hardware.

Is anybody willing to test my new app https://document.bot? It is like Cursor IDE but custom harness for knowledge work (PDF's, MS Office files etc).

You can connect your existing offline LLM models through LMStudio, Ollama, or app managed LLM models (Qwen3.5, Gemma 4, etc)

Might have to make a new Ask HN post for this, but again, you are users with good hardware setups.

New comment by cahaya in "Nextcloud Hub 26 Spring: Built together, designed for the future"

cahaya — Thu, 11 Jun 2026 17:57:24 +0000

Same. Solving it by moving complex and sensitive data to an offline desktop app https://document.bot that support offline (self hosted) AI models (and optionally EU/ US AI providers). However, it doesn't integrate yet with shared (org) drives.

New comment by cahaya in "Ask HN: What Are You Working On? (March 2026)"

cahaya — Mon, 09 Mar 2026 10:53:05 +0000

Building Cursor IDE, but for knowledge workers. Domain will go live soon on https://document.bot

New comment by cahaya in "Claude Code Remote Control"

cahaya — Wed, 25 Feb 2026 11:27:24 +0000

Hoping OpenAI/ Codex will launch this soon too.

New comment by cahaya in "Show HN: A real-time strategy game that AI agents can play"

cahaya — Wed, 25 Feb 2026 11:00:01 +0000

Nice. Curious about 5.3-codex-high results

New comment by cahaya in "Anthropic officially bans using subscription auth for third party use"

cahaya — Thu, 19 Feb 2026 10:12:21 +0000

  Codex app-server is the interface Codex uses to power rich clients (for example, the Codex VS Code extension). Use it when you want a deep integration inside your own product.

It mentions 'Inside your own product', but not sure if that means also your own commercial application.

New comment by cahaya in "Anthropic officially bans using subscription auth for third party use"

cahaya — Thu, 19 Feb 2026 10:08:37 +0000

Same question here. A while ago I read rumors OpenAI might build a "Login with OpenAI" (comparable to login with Apple, Facebook, Google) so people can also use their existing sub in commercial apps. Hope it's true.

New comment by cahaya in "Immersa: Open-source Web-based 3D Presentation Tool"

cahaya — Sat, 20 Dec 2025 14:10:22 +0000

looks nice!

New comment by cahaya in "DeepSeek OCR"

cahaya — Mon, 20 Oct 2025 09:27:16 +0000

Lot's of OCR/ LLM's (Even Gemini Pro 2.5) still struggle converting complex tables to markdown or HTML: Tables with multiple headers and merged cells that get mixed up, multiple columns with tick boxes get mixed up, multi page tables that are not understood correctly. Also Llamaindex fails miserably on those things.

Curious to hear which OCR/ LLM excels with these specific issues? Example complex table: https://cdn.aviation.bot/complex-tables.zip

I can only parse this table correctly by first parsing the table headers manually into HTML as example output. However, it still mixes up tick boxes. Full table examples: https://www.easa.europa.eu/en/icao-compliance-checklist

New comment by cahaya in "Show HN: Run Qwen3-Next-80B on 8GB GPU at 1tok/2s throughput"

cahaya — Tue, 23 Sep 2025 16:57:11 +0000

Got 32GB so was hoping I could use ollm to offload it to my SSD. Slower but making it possible to run bigger models (in emergencies)

New comment by cahaya in "Show HN: Run Qwen3-Next-80B on 8GB GPU at 1tok/2s throughput"

cahaya — Tue, 23 Sep 2025 13:29:50 +0000

Nice. Seems like i cannot run this on my Apple silicon M chips right?

New comment by cahaya in "Show HN: Pgmcp, an MCP server to query any Postgres database in natural language"

cahaya — Thu, 18 Sep 2025 12:00:54 +0000

Nice, but can somebody tell me if this performs better than my simple Postgres MCP using npx? My current setup uses the LLM to search through my local Postgres in multiple steps. I guess this Pgmcp is doing multiple steps in the background and returns the final result to the LLM calling the MCP tool?

Codex: ``` [mcp_servers.postgresMCP] command = "npx" args = ["-y", "@modelcontextprotocol/server-postgres", "postgresql://user:password@localhost:5432/db"] ```

Cursor: ``` "postgresMCP": { "command": "npx", "args": [ "-y", "@modelcontextprotocol/server-postgres", "postgresql://user:password@localhost:5432/db" ] }, ```

With my setup i can easily switch between LLM's

New comment by cahaya in "I got the highest score on ARC-AGI again swapping Python for English"

cahaya — Wed, 17 Sep 2025 12:44:39 +0000

Are there any existing scripts/ tools to use these evolutionary algorithms also at home with e.g. Codex/GPT-5 / Claude Code?

New comment by cahaya in "How does air pollution impact your brain?"

cahaya — Mon, 15 Sep 2025 13:42:12 +0000

Is it me or is the link only opening as JSON?

{ "@context": [ "https://www.w3.org/ns/activitystreams", { "Hashtag": "as:Hashtag", "sensitive": "as:sensitive", "dcterms": "http://purl.org/dc/terms/" } ], "id": "https://neurofrontiers.blog/?p=11319", "type": "Note", "attachment": [ { "type": "Image", "url": "https://i0.wp.com/neurofrontiers.blog/wp-content/uploads/202...", "mediaType": "image/jpeg", "name": "A cartoon depicting a traffic jam of identical black cars, each driven by a brain. Thick clouds of exhaust rise and gather above the stalled vehicles." } ], "attributedTo": "https://neurofrontiers.blog/author/neuronerdb/", "audience": "https://neurofrontiers.blog/?author=0", "content": "

How does air pollution

New comment by cahaya in "ChatGPT Developer Mode: Full MCP client access"

cahaya — Thu, 11 Sep 2025 10:47:39 +0000

I tried adding Context7 Documentation MCP and got this

URL:https://mcp.context7.com/mcp Safety Scan: Passed

This MCP server can't be used by ChatGPT to search information because it doesn't implement our specification: search action not found https://platform.openai.com/docs/mcp#create-an-mcp-server