Hacker News: beklein

New comment by beklein in "Texico: Learn the principles of programming without even touching a computer"

beklein — Mon, 04 May 2026 13:22:23 +0000

Principles of programming:

1. Break things down into small units

2. Think about sequence

3. Find patterns

4. Focus on the important things

5. Visualize sequences in your mind

Love the silly music and the way they teach, thanks for sharing this!

New comment by beklein in "A Steerable Model with Emergent Capabilities"

beklein — Fri, 17 Apr 2026 13:28:59 +0000

Also relevant to this is the newest episode of The Lightcone Podcast with Quan Vuong, co-founder of PI and, one of many co-authors of that paper.

New comment by beklein in "Explaining the Most Important Artemis II Photos [video]"

beklein — Sat, 11 Apr 2026 08:35:32 +0000

Thanks for sharing this here, it's a beautiful video. The images are linked in the description but if anybody is reading this, check: https://www.flickr.com/photos/nasa2explore/

New comment by beklein in "System Card: Claude Mythos Preview [pdf]"

beklein — Tue, 07 Apr 2026 18:37:44 +0000

"... the first early version of Claude Mythos Preview was made available for internal use on February 24. In our testing, Claude Mythos Preview demonstrated a striking leap in cyber capabilities relative to prior models, including the ability to autonomously discover and exploit zero-day vulnerabilities in major operating systems and web browsers."

More infos here: https://red.anthropic.com/2026/mythos-preview/

ARC-AGI-3

beklein — Wed, 25 Mar 2026 19:26:46 +0000

Article URL: https://arcprize.org/blog/arc-agi-3-launch

Comments URL: https://news.ycombinator.com/item?id=47522012

Points: 3

# Comments: 0

New comment by beklein in "GPT‑5.4 Mini and Nano"

beklein — Tue, 17 Mar 2026 18:00:58 +0000

As a big Codex user, with many smaller requests, this one is the highlight: "In Codex, GPT‑5.4 mini is available across the Codex app, CLI, IDE extension and web. It uses only 30% of the GPT‑5.4 quota, letting developers quickly handle simpler coding tasks in Codex for about one-third the cost." + Subagents support will be huge.

Arduino Ventuno Q

beklein — Mon, 09 Mar 2026 13:55:36 +0000

Article URL: https://www.arduino.cc/product-ventuno-q

Comments URL: https://news.ycombinator.com/item?id=47309110

Points: 5

# Comments: 0

New comment by beklein in "GPT-5.4"

beklein — Thu, 05 Mar 2026 23:02:50 +0000

Not sure why you think Anthropic has not the same problems? Their version numbers across different model lines jump around too... for Opus we have 4.6, 4.5, 4.1 then we have Sonnet at 4.6, 4.5, and 4.1? No version 4.1 here, and there is Haiku, no 4.6, but 4.5 and no 4.1, no 4 but then we only have old 3.5...

Also their pricing based on 5m/1h cache hits, cash read hits, additional charges for US inference (but only for Opus 4.6 I guess) and optional features such as more context and faster speed for some random multiplier is also complex and actually quiet similar to OpenAI's pricing scheme.

To me it looks like everybody has similar problems and solutions for the same kinds of problems and they just try their best to offer different products and services to their customers.

New comment by beklein in "Anthropic Cowork feature creates 10GB VM bundle on macOS without warning"

beklein — Mon, 02 Mar 2026 17:06:14 +0000

Perhaps useful, I discovered: https://github.com/agent-infra/sandbox

> All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.

New comment by beklein in "GPT-Realtime-1.5 Released"

beklein — Tue, 24 Feb 2026 12:43:27 +0000

Some more info here: https://developers.openai.com/api/docs/models/gpt-realtime-1...

- $4 input, $0.4 cached input, $16 output

- 32,000 context window

- 4,096 max output tokens

- Sep 30, 2024 knowledge cutoff

Love the models, speed, and capabilities. Just sad that they are not getting the publicity and adoption right now, but hopefully in the future.

New comment by beklein in "Cache Monet"

beklein — Fri, 13 Feb 2026 18:17:03 +0000

Sound on!

Song name is: Windowdipper from ꪖꪶꪶ ꪮꪀ ꪗꪖꪶꪶ by Jib Kidder

https://jibkidder.bandcamp.com/track/windowdipper

New comment by beklein in "GPT‑5.3‑Codex‑Spark"

beklein — Thu, 12 Feb 2026 21:08:09 +0000

The end result would be a normal PPT presentation, check https://sli.dev as an easy start, ask Codex/Claude/... to generate the slides using that framework with data from something.md. The interesting part here is generating these otherwise boring slide decks not with PowerPoint itself but with AI coding agents and a master slides, AGENTS.md context. I’ll be showing this to a small group (normally members only) at IPAI in Heilbronn, Germany on 03/03. If you’re in the area and would like to join, feel free to send me a message I will squeeze you in.

New comment by beklein in "GPT‑5.3‑Codex‑Spark"

beklein — Thu, 12 Feb 2026 20:59:00 +0000

Not my normal use-case, but you can always fall back and ask the AI coding agent to generate the diagram as SVG, for blocky but more complex content like your examples it will work well and still is 100% text based, so the AI coding agents or you manually can fix/adjust any issues. An image generation skill is a valid fallback, but in my opinion it's hard to change details (json style image creation prompts are possible but hard to do right) and you won't see changes nicely in the git history. In your use case you can ask the AI coding agent to run a script.js to get the newest dates for the project from a page/API, then it should only update the dates in the roadmap.svg file on slide x with the new data. This way you will automagically have the newest numbers and can track everything within git in one prompt. Save this as a rule in AGENTS.md and run this every month to update your slides with one prompt.

New comment by beklein in "Gemini 3 Deep Think"

beklein — Thu, 12 Feb 2026 19:59:08 +0000

https://x.com/fchollet/status/2022036543582638517

New comment by beklein in "GPT‑5.3‑Codex‑Spark"

beklein — Thu, 12 Feb 2026 19:15:22 +0000

In my AGENTS.md file i have a _rule_ that tells the model to use Apache ECharts, the data comes from the prompt and normally .csv/.json files. Prompt would be like: "After slide 3 add a new content slide that shows a bar chart with data from @data/somefile.csv" ... works great and these charts can be even interactive.

New comment by beklein in "GPT‑5.3‑Codex‑Spark"

beklein — Thu, 12 Feb 2026 18:53:55 +0000

I love this! I use coding agents to generate web-based slide decks where “master slides” are just components, and we already have rules + assets to enforce corporate identity. With content + prompts, it’s straightforward to generate a clean, predefined presentation. What I’d really want on top is an “improv mode”: during the talk, I can branch off based on audience questions or small wording changes, and the system proposes (say) 3 candidate next slides in real time. I pick one, present it, then smoothly merge back into the main deck. Example: if I mention a recent news article / study / paper, it automatically generates a slide that includes a screenshot + a QR code link to the source, then routes me back to the original storyline. With realtime voice + realtime code generation, this could turn the boring old presenter view into something genuinely useful.

New comment by beklein in "Claude’s C Compiler vs. GCC"

beklein — Mon, 09 Feb 2026 06:56:55 +0000

Honest question: would a normal CS student, junior, senior, or expert software developer be able to build this kind of project, and in what amount of time?

I am pretty sure everybody agrees that this result is somewhere between slop code that barely works and the pinnacle of AI-assisted compiler technology. But discussions should not be held from the extreme points. Instead, I am looking for a realistic estimation from the HN community about where to place these results in a human context. Since I have no experience with compilers, I would welcome any of your opinions.

New comment by beklein in "Software factories and the agentic moment"

beklein — Sat, 07 Feb 2026 16:09:15 +0000

Relevant blog post from simonw: https://simonwillison.net/2026/Feb/7/software-factory/

New comment by beklein in "xAI joins SpaceX"

beklein — Mon, 02 Feb 2026 21:57:00 +0000

https://www.spacex.com/updates#xai-joins-spacex additionally the longer article on SpaceX site

xAI Joins SpaceX

beklein — Mon, 02 Feb 2026 21:54:26 +0000

Article URL: https://x.ai/news/xai-joins-spacex

Comments URL: https://news.ycombinator.com/item?id=46862222

Points: 90

# Comments: 5