Hacker News: PhilippGille

New comment by PhilippGille in "Android 17 is the first since 3.x to add new APIs without releasing to the AOSP"

PhilippGille — Fri, 18 Sep 2026 21:08:37 +0000

https://grapheneos.org/faq#upstream

https://android-review.googlesource.com/q/status:merged+auth...

New comment by PhilippGille in "Corporate America is getting hooked on open-source AI"

PhilippGille — Sat, 05 Sep 2026 15:56:13 +0000

> Open source does not apply to AI

Isn't that a bit overgeneralized?

There's more than weights for the Olmo models for example: https://allenai.org/olmo

Similar for Nvidia's Nemotron models IIRC.

Artificial Analysis has an "openness" ranking: [1]

[1] https://artificialanalysis.ai/models?model-filters=open-sour...

New comment by PhilippGille in "Show HN: My Claude quota ran out in 10 minutes, so I made a tool to find out why"

PhilippGille — Fri, 28 Aug 2026 11:20:58 +0000

Token usage is generally lower in greenfield projects.

New comment by PhilippGille in "GLM-5.3-Flash"

PhilippGille — Wed, 26 Aug 2026 18:19:19 +0000

NovitaAI is already hosting it: https://openrouter.ai/z-ai/glm-5.3-flash#providers

The AI boom: rational enthusiasm or the next dot-com bubble?

PhilippGille — Fri, 21 Aug 2026 15:07:10 +0000

Article URL: https://www.ecb.europa.eu/press/blog/date/2026/html/ecb.blog20260817~754a8a4418.en.html

Comments URL: https://news.ycombinator.com/item?id=49389281

Points: 3

# Comments: 1

New comment by PhilippGille in "GeForce Now on Linux Native App Exits Beta"

PhilippGille — Thu, 13 Aug 2026 21:29:47 +0000

Official blog post: https://blogs.nvidia.com/blog/geforce-now-thursday-linux-nat...

New comment by PhilippGille in "DeepSeek costs OpenCode Go user $1.14/day; dual DGX breaks even in 24 years"

PhilippGille — Tue, 11 Aug 2026 22:38:44 +0000

According to OpenRouter, DeepSeek trains on input. At least when disabling all providers that train on your data, DeepSeek gets disabled.

Other providers don't.

You can also choose to route to ZDR only.

https://openrouter.ai/deepseek/deepseek-v4-flash-0731#provid...

New comment by PhilippGille in "OpenAI Daybreak Blue"

PhilippGille — Tue, 11 Aug 2026 22:17:22 +0000

Existing recent discussion with 127 points, 68 comments: https://news.ycombinator.com/item?id=49246704

New comment by PhilippGille in "GitHub Actions and Pages are experiencing degraded availability"

PhilippGille — Thu, 06 Aug 2026 18:12:10 +0000

98.33 according to https://mrshu.github.io/github-statuses/

New comment by PhilippGille in "DeepSeek-V4-Flash Update"

PhilippGille — Fri, 31 Jul 2026 10:08:56 +0000

Yes that's my point. The old and the new version are different in capabilities, but now when someone talks about DeepSeek V4 Flash (in benchmarks, on inference providers), you don't know which exact version it's about.

Some providers like OpenRouter now call it `deepseek-v4-flash-0731`, but even in places like here on HackerNews people say things like "Sonnet is better than DeepSeek" without specifying a version or a reasoning effort, certainly no one will mention that `-0731` suffix when talking about DeepSeek V4 Flash.

New comment by PhilippGille in "DeepSeek-V4-Flash Update"

PhilippGille — Fri, 31 Jul 2026 10:05:33 +0000

That's what I mean. On DeepSeek it's now just `deepseek-v4-flash`, while OpenRouter calls it `deepseek/deepseek-v4-flash-0731`, so now when someone talks about DeepSeek V4 Flash, like in benchmarks, or other inference providers, which version do they actually mean?

The `-0731` style suffix is worse compared to a proper version bump like V4.1.

New comment by PhilippGille in "DeepSeek-V4-Flash Update"

PhilippGille — Fri, 31 Jul 2026 07:37:40 +0000

The previous V4 version wasn't called “Preview” by most inference providers. For example, the OpenRouter model slug was `deepseek/deepseek-v4-flash`. So now there will be confusion when someone talks about V4 Flash or when someone offers V4 Flash inference.

Why not call it V4.1?

New comment by PhilippGille in "Advancing the price-performance frontier with GPT‑5.6"

PhilippGille — Thu, 30 Jul 2026 18:33:52 +0000

Depends on the reasoning effort, see https://deepswe.datacurve.ai (add Luna via model selection drop down, if it's not shown by default)

Kagi releases official Kagi Assistant apps

PhilippGille — Thu, 30 Jul 2026 17:27:19 +0000

Article URL: https://kagi.com/changelog#11136

Comments URL: https://news.ycombinator.com/item?id=49113014

Points: 35

# Comments: 1

New Framework Desktop Option with AMD Ryzen AI Max+ Pro 495 and 192GB Memory

PhilippGille — Thu, 23 Jul 2026 11:09:48 +0000

Article URL: https://frame.work/desktop?tab=192gb-coming-soon

Comments URL: https://news.ycombinator.com/item?id=49019694

Points: 79

# Comments: 114

Cursor, Codex, Gemini CLI, Antigravity hit by sandbox escapes

PhilippGille — Wed, 22 Jul 2026 21:19:07 +0000

Article URL: https://www.bleepingcomputer.com/news/security/cursor-codex-gemini-cli-antigravity-hit-by-sandbox-escapes/

Comments URL: https://news.ycombinator.com/item?id=49013584

Points: 2

# Comments: 0

New comment by PhilippGille in "Show HN: Bento - An entire PowerPoint in one HTML file (edit+view+data+collab)"

PhilippGille — Wed, 22 Jul 2026 21:06:34 +0000

The project looks very interesting, thanks for sharing!

You seem to have created a new GitHub account just for this project a week ago. Do you have any other GitHub accounts that enable us to see a track record of your work (maintenance, security)?

New comment by PhilippGille in "Transcribe.cpp"

PhilippGille — Sun, 19 Jul 2026 06:36:34 +0000

Handy already supports streaming transcription models, and you can see the words in the small Handy pop-up while you are talking.

So in general this definitely works. Handy is just missing the feature to insert these streamed words into the app where the cursor is.

New comment by PhilippGille in "GPT-5.6"

PhilippGille — Thu, 09 Jul 2026 22:56:56 +0000

That was the case for early models (Llama etc), but they got much better since then. Not perfect, but good enough.

This is from Ministral 3 14B, a 2025 model without reasoning, that you can run on your PC:

> Write a Haiku involving HackerNews, and the capability of large language models like you to reply in an exact number of words or syllables.

    Silicon whispers,
    exact words in code’s embrace—
    Haiku blooms anew.

Across multiple tries it got it wrong a couple times (by ~2 syllables). But syllables are extra tricky (because of how LLMs use tokens) and the point is that for things like "summarize in 5 bullet points" you will mostly get 5 bullet points, maybe 6, but not 10 or 20, and no need for a tool that count bullet points.

New comment by PhilippGille in "Monetization Gateway: Charge for any resource behind Cloudflare via x402"

PhilippGille — Wed, 01 Jul 2026 19:16:40 +0000

Currently this is for payments with stablecoins.

For Bitcoin / Lightning these kind of pay-per-request API paywalls have existed for many years already (e.g. my own from 8 years ago [1], but others as well).

Flattr [2] existed for non-crypto micropayments.

None became mainstream. I think the friction is always the extra setup on the client side. In all 3 cases the user (API consumer) has to set up a special wallet (browser extension or something for the agent) and deposit some money/crypto on the client side first. This part needs to become simpler.

[1] https://github.com/philippgille/ln-paywall

[2] https://en.wikipedia.org/wiki/Flattr