Hacker News: quantisan

New comment by quantisan in "AI outperforms law professors in Stanford Law study"

quantisan — Wed, 03 Jun 2026 02:14:47 +0000

I'm surprised Stanford Law would go along with this over-reaching press release title. How about "For common first-year contracts-law questions, law professors preferred AI-generated answers to professor-generated answers"

New comment by quantisan in "Sam Altman is giving OpenAI tokens in exchange for equity in YC Companies"

quantisan — Fri, 22 May 2026 00:55:07 +0000

Does this mean they're effectively a PE firm?

Phishing Campaigns "I Paid Twice" Targeting Booking.com Hotels and Customers

quantisan — Wed, 08 Apr 2026 01:01:08 +0000

Article URL: https://blog.sekoia.io/phishing-campaigns-i-paid-twice-targeting-booking-com-hotels-and-customers/

Comments URL: https://news.ycombinator.com/item?id=47683395

Points: 2

# Comments: 0

Ask HN: Codex CLI error reveals "GPT-5.4-ab-arm2" string

quantisan — Tue, 03 Mar 2026 01:34:01 +0000

While using codex CLI gpt-5.3-codex model, I just had a stream disconnect with a specific error message. It looks like I was routed to an A/B test for a 5.4 branch:

``` stream disconnected before completion: This user's access to gpt-5.4-ab-arm2-1020-1p-codexswic-ev3 has been temporarily limited for potentially suspicious activity related to cybersecurity. ```

Anyone else seeing GPT 5.4 variants?

Comments URL: https://news.ycombinator.com/item?id=47226767

Points: 9

# Comments: 1

Drop-In Minimal CSS

quantisan — Sun, 15 Feb 2026 21:36:46 +0000

Article URL: https://dohliam.github.io/dropin-minimal-css/

Comments URL: https://news.ycombinator.com/item?id=47027824

Points: 1

# Comments: 0

Diminished Chandler Wobble After 2015: Link to Mass Anomalies in 2011

quantisan — Fri, 26 Sep 2025 23:52:39 +0000

Article URL: https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2025GL116191

Comments URL: https://news.ycombinator.com/item?id=45392214

Points: 28

# Comments: 0

New comment by quantisan in "Libghostty is coming"

quantisan — Tue, 23 Sep 2025 23:20:10 +0000

Try Cmd-Shift-J. It dumps your buffer to a temp file, with the file path made ready for you. I do that and then open the temp file with vi.

New comment by quantisan in "Qwen3-Next series represents our next-generation foundation models"

quantisan — Fri, 12 Sep 2025 01:29:39 +0000

Blog post https://qwen.ai/blog?id=4074cca80393150c248e508aa62983f9cb7d...

Qwen3-Next series represents our next-generation foundation models

quantisan — Fri, 12 Sep 2025 01:27:52 +0000

Article URL: https://huggingface.co/docs/transformers/main/model_doc/qwen3_next

Comments URL: https://news.ycombinator.com/item?id=45217784

Points: 6

# Comments: 1

New comment by quantisan in "Pico CSS – Minimal CSS Framework for Semantic HTML"

quantisan — Mon, 08 Sep 2025 00:17:15 +0000

I use Pico with LLM code gen for new projects. As you probably know, LLMs are predisposed to Tailwind and coding for industrial strength on any tiniest projects. The trick is to feed it the whole Pico docs as context and prompt it (i.e. in your CLAUDE.md) to use Pico explicitly.

Pix (Payment System)

quantisan — Sat, 16 Aug 2025 20:47:41 +0000

Article URL: https://en.wikipedia.org/wiki/Pix_(payment_system)

Comments URL: https://news.ycombinator.com/item?id=44926793

Points: 3

# Comments: 0

Kira (Short AI-Assisted Film on Human Cloning)

quantisan — Fri, 11 Jul 2025 04:38:27 +0000

Article URL: https://www.youtube.com/watch?v=gx8rMzlG29Q

Comments URL: https://news.ycombinator.com/item?id=44528442

Points: 2

# Comments: 1

New comment by quantisan in "uv: An extremely fast Python package and project manager, written in Rust"

quantisan — Tue, 24 Jun 2025 00:43:40 +0000

1. Zero-Copy Deserialization with rkyv and Unsafe Code 2. Platform-Specific High-Performance Memory Allocators 3. High-Performance Hash Maps with FxHasher and SwissTable

https://deepwiki.com/search/point-to-the-top-3-rust-specif_4...

New comment by quantisan in "TypeScript code extracted from the official Claude Code package by Anthropic"

quantisan — Fri, 28 Feb 2025 01:23:08 +0000

I used Claude Code to understand the source code of Claude Code:

  1. Tool-Based Action Framework
    - Tools implement a common interface (Tool.ts) with standard methods
    - Central registry in tools.ts manages tool availability and permissions
    - Tools are categorized as read-only or stateful, affecting execution strategy
  2. Agent Orchestration
    - query.ts serves as the orchestration engine that:
        - Identifies tool use requests in Claude's responses
      - Manages permissions and serializes/deserializes tool data
      - Schedules concurrent or serial tool execution based on tool type
      - Feeds tool results back to Claude in a recursive loop
  3. AgentTool Implementation
    - Enables recursive agent capabilities via sub-agent spawning
    - Sub-agents run with controlled permissions (typically read-only)
    - Each agent invocation is stateless and returns a single result
    - Implements progress streaming via async generators
  4. Execution Flow
    - User query → Claude response → Tool use requests → Permission checks
    - Tool execution → Results normalized → Results fed back to Claude
    - Process repeats with Claude potentially using additional tools
  5. Architectural Patterns
    - Async generators for streaming results and maintaining responsiveness
    - Hierarchical permission model controlling tool access
    - Normalized message formats ensuring consistent communication
    - Logging chains for tracking agent activities
    - Context management with optional compression (/compact)

TypeScript code extracted from the official Claude Code package by Anthropic

quantisan — Fri, 28 Feb 2025 00:55:05 +0000

Article URL: https://github.com/mandeep511/OpenAGI

Comments URL: https://news.ycombinator.com/item?id=43200401

Points: 2

# Comments: 1

Baltic States Synchronization with CESA

quantisan — Sun, 16 Feb 2025 21:20:26 +0000

Article URL: https://en.wikipedia.org/wiki/Baltic_states_synchronization_with_CESA

Comments URL: https://news.ycombinator.com/item?id=43071815

Points: 3

# Comments: 1

We built the models for Phind 2

quantisan — Thu, 13 Feb 2025 21:28:47 +0000

Article URL: https://www.phind.com/blog/phind-2-model-creation

Comments URL: https://news.ycombinator.com/item?id=43041614

Points: 2

# Comments: 0

Partnr: A Benchmark for Planning and Reasoning in Embodied Multi-Agent Tasks

quantisan — Sat, 08 Feb 2025 01:06:20 +0000

Article URL: https://aihabitat.org/partnr/

Comments URL: https://news.ycombinator.com/item?id=42979341

Points: 1

# Comments: 0

New comment by quantisan in "The young, inexperienced engineers aiding DOGE"

quantisan — Mon, 03 Feb 2025 21:39:34 +0000

- Youth-Led Implementation - Bypassing Traditional Authority Structures - Loyalty-Based Appointments - Institutional Disruption - Limited Oversight - Information Control

https://en.wikipedia.org/wiki/Cultural_Revolution

New comment by quantisan in "Nvidia might do for desktop AI what it did for desktop gaming"

quantisan — Thu, 16 Jan 2025 04:25:51 +0000

"I'll never buy a SBC from Nvidia unless all the SW support is up-streamed to Linux kernel," top comment from prev discussion https://news.ycombinator.com/item?id=42623030