<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hacker News: abidlabs</title><link>https://news.ycombinator.com/user?id=abidlabs</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Mon, 17 Aug 2026 06:21:01 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=abidlabs" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by abidlabs in "Qwen 3.8 27B"]]></title><description><![CDATA[
<p>The Hugging Face page (<a href="https://huggingface.co/Qwen/Qwen3.8-27B" rel="nofollow">https://huggingface.co/Qwen/Qwen3.8-27B</a>) shows that Featherless supports the model (and includes the inference widget to try it out directly on the page)</p>
]]></description><pubDate>Sat, 15 Aug 2026 01:48:26 +0000</pubDate><link>https://news.ycombinator.com/item?id=49306826</link><dc:creator>abidlabs</dc:creator><comments>https://news.ycombinator.com/item?id=49306826</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49306826</guid></item><item><title><![CDATA[New comment by abidlabs in "GitHub Actions and Pages are experiencing degraded availability"]]></title><description><![CDATA[
<p>It's not too hard to switch over from GitHub actions to other runners. For example, I wrote up the steps needed in order to use Hugging Face Jobs instead, which also enables GPU runners and other flavors. I use this for several of the repos I manage (such as Trackio):<p><a href="https://huggingface.co/blog/github-ci-hf-jobs" rel="nofollow">https://huggingface.co/blog/github-ci-hf-jobs</a></p>
]]></description><pubDate>Thu, 06 Aug 2026 21:53:01 +0000</pubDate><link>https://news.ycombinator.com/item?id=49203119</link><dc:creator>abidlabs</dc:creator><comments>https://news.ycombinator.com/item?id=49203119</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49203119</guid></item><item><title><![CDATA[New comment by abidlabs in "Claude Opus 5"]]></title><description><![CDATA[
<p>I was curious to see how open weight models would do on this task so I passed in a screenshot of your source of truth and here's what 2 of the best code-generation models that allow image inputs do:<p>Inkling (not too great): <a href="https://cdn-uploads.huggingface.co/production/uploads/608b8bb39d7c9519b4adae19/cxuhXRLCts_ACn4rDZ20v.png" rel="nofollow">https://cdn-uploads.huggingface.co/production/uploads/608b8b...</a><p>Kimi 2.7 (really well, esp. note that this is the predecessor model, not the latest Kimi3): <a href="https://cdn-uploads.huggingface.co/production/uploads/608b8bb39d7c9519b4adae19/kzAhr9gSXyLwfPNfE7mPR.png" rel="nofollow">https://cdn-uploads.huggingface.co/production/uploads/608b8b...</a><p>Here's how I tested them: <a href="https://huggingface.co/spaces/abidlabs/vlm-screenshot-to-webpage" rel="nofollow">https://huggingface.co/spaces/abidlabs/vlm-screenshot-to-web...</a><p><a href="https://huggingface.co/spaces/abidlabs/vlm-screenshot-to-webpage" rel="nofollow">https://huggingface.co/spaces/abidlabs/vlm-screenshot-to-web...</a></p>
]]></description><pubDate>Fri, 24 Jul 2026 22:47:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=49042556</link><dc:creator>abidlabs</dc:creator><comments>https://news.ycombinator.com/item?id=49042556</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49042556</guid></item><item><title><![CDATA[New comment by abidlabs in "Startup founders urge U.S. government not to shut off Chinese open weight AI"]]></title><description><![CDATA[
<p>Hugging Face recently added a filter directly on the models page: <a href="https://huggingface.co/models" rel="nofollow">https://huggingface.co/models</a> that lets you filter based on hardware.</p>
]]></description><pubDate>Thu, 23 Jul 2026 15:54:40 +0000</pubDate><link>https://news.ycombinator.com/item?id=49023673</link><dc:creator>abidlabs</dc:creator><comments>https://news.ycombinator.com/item?id=49023673</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49023673</guid></item><item><title><![CDATA[New comment by abidlabs in "Startup founders urge U.S. government not to shut off Chinese open weight AI"]]></title><description><![CDATA[
<p>Hugging Face recently added a filter directly on the models page: <a href="https://huggingface.co/models" rel="nofollow">https://huggingface.co/models</a> that lets you filter based on hardware.</p>
]]></description><pubDate>Thu, 23 Jul 2026 15:54:29 +0000</pubDate><link>https://news.ycombinator.com/item?id=49023668</link><dc:creator>abidlabs</dc:creator><comments>https://news.ycombinator.com/item?id=49023668</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49023668</guid></item><item><title><![CDATA[New comment by abidlabs in "OpenAI and Hugging Face address security incident during model evaluation"]]></title><description><![CDATA[
<p>If this doesn't put the nail in the coffin on the idea that we need closed-source models for the good of cybersecurity, I don't know what will</p>
]]></description><pubDate>Tue, 21 Jul 2026 21:40:57 +0000</pubDate><link>https://news.ycombinator.com/item?id=48998751</link><dc:creator>abidlabs</dc:creator><comments>https://news.ycombinator.com/item?id=48998751</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48998751</guid></item><item><title><![CDATA[New comment by abidlabs in "Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?"]]></title><description><![CDATA[
<p>Yes! <a href="https://huggingface.co/changelog/agent-trace-viewer" rel="nofollow">https://huggingface.co/changelog/agent-trace-viewer</a></p>
]]></description><pubDate>Mon, 15 Jun 2026 18:46:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=48545398</link><dc:creator>abidlabs</dc:creator><comments>https://news.ycombinator.com/item?id=48545398</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48545398</guid></item><item><title><![CDATA[New comment by abidlabs in "Statement on US government directive to suspend access to Fable 5 and Mythos 5"]]></title><description><![CDATA[
<p>Interesting to see Anthropic now <i>downplaying</i> the new vulnerabilities that Mythos discovered:<p>> We reviewed a demonstration of this specific technique being used to identify a small number of previously known, minor vulnerabilities. These vulnerabilities all appear relatively simple, and we have found that other publicly-available models are able to discover them as well without requiring a bypass</p>
]]></description><pubDate>Sat, 13 Jun 2026 01:15:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=48511298</link><dc:creator>abidlabs</dc:creator><comments>https://news.ycombinator.com/item?id=48511298</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48511298</guid></item><item><title><![CDATA[New comment by abidlabs in "Reviving Papers with Code"]]></title><description><![CDATA[
<p>Would you be interested in an RSS feed for: <a href="https://huggingface.co/papers/trending" rel="nofollow">https://huggingface.co/papers/trending</a>?</p>
]]></description><pubDate>Wed, 10 Jun 2026 17:41:07 +0000</pubDate><link>https://news.ycombinator.com/item?id=48479867</link><dc:creator>abidlabs</dc:creator><comments>https://news.ycombinator.com/item?id=48479867</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48479867</guid></item><item><title><![CDATA[New comment by abidlabs in "Reviving Papers with Code"]]></title><description><![CDATA[
<p>You could subscribe to daily papers at the top here: <a href="https://huggingface.co/papers/trending" rel="nofollow">https://huggingface.co/papers/trending</a></p>
]]></description><pubDate>Wed, 10 Jun 2026 16:50:29 +0000</pubDate><link>https://news.ycombinator.com/item?id=48479106</link><dc:creator>abidlabs</dc:creator><comments>https://news.ycombinator.com/item?id=48479106</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48479106</guid></item><item><title><![CDATA[New comment by abidlabs in "S3 Files"]]></title><description><![CDATA[
<p>Hugging Face Buckets also recently added support for mounting Buckets as a filesystem: <a href="https://huggingface.co/changelog/hf-mount" rel="nofollow">https://huggingface.co/changelog/hf-mount</a></p>
]]></description><pubDate>Tue, 07 Apr 2026 23:55:46 +0000</pubDate><link>https://news.ycombinator.com/item?id=47682869</link><dc:creator>abidlabs</dc:creator><comments>https://news.ycombinator.com/item?id=47682869</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47682869</guid></item><item><title><![CDATA[New comment by abidlabs in "Hugging Face Provides an S3 Alternative"]]></title><description><![CDATA[
<p>The most interesting thing is that charges can be potentially much less if you have duplicated data in your bucket</p>
]]></description><pubDate>Tue, 24 Mar 2026 22:54:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=47510713</link><dc:creator>abidlabs</dc:creator><comments>https://news.ycombinator.com/item?id=47510713</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47510713</guid></item><item><title><![CDATA[Hugging Face Provides an S3 Alternative]]></title><description><![CDATA[
<p>Article URL: <a href="https://huggingface.co/storage">https://huggingface.co/storage</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47510712">https://news.ycombinator.com/item?id=47510712</a></p>
<p>Points: 3</p>
<p># Comments: 1</p>
]]></description><pubDate>Tue, 24 Mar 2026 22:54:44 +0000</pubDate><link>https://huggingface.co/storage</link><dc:creator>abidlabs</dc:creator><comments>https://news.ycombinator.com/item?id=47510712</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47510712</guid></item><item><title><![CDATA[New comment by abidlabs in "OpenRouter Broadcast"]]></title><description><![CDATA[
<p>Use Hugging Face inference providers for this: <a href="https://huggingface.co/docs/inference-providers/en/index" rel="nofollow">https://huggingface.co/docs/inference-providers/en/index</a></p>
]]></description><pubDate>Thu, 11 Dec 2025 02:17:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=46226877</link><dc:creator>abidlabs</dc:creator><comments>https://news.ycombinator.com/item?id=46226877</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46226877</guid></item><item><title><![CDATA[New comment by abidlabs in "Sequoia COO quit over Shaun Maguire's comments about Islamism"]]></title><description><![CDATA[
<p><a href="https://archive.is/6DwJL" rel="nofollow">https://archive.is/6DwJL</a></p>
]]></description><pubDate>Wed, 22 Oct 2025 07:31:34 +0000</pubDate><link>https://news.ycombinator.com/item?id=45665893</link><dc:creator>abidlabs</dc:creator><comments>https://news.ycombinator.com/item?id=45665893</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45665893</guid></item><item><title><![CDATA[Show HN: Jeopardy Labs as a Static Web App]]></title><description><![CDATA[
<p>Hi folks! I love trivia and have built lots of jeopardy boards over the years with Jeopardy Labs. I recently discovered that Jeopardy Labs now requires a paid account to upload images to questions. I understand that they can charge for features at any time, since they have to pay for servers, etc. At the same time, since I already pay for Claude Code, I wondered how long it would take for me to vibe code my own version of the site. I decided to code the website so that it doesn't require any backend server at all -- all questions, answers, and metadata are stored in the URL itself.<p>Feel free to try it out, fork it, or propose any feature requests.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=44993124">https://news.ycombinator.com/item?id=44993124</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Sat, 23 Aug 2025 04:21:06 +0000</pubDate><link>https://abidlabs.github.io/staticjeopardy/</link><dc:creator>abidlabs</dc:creator><comments>https://news.ycombinator.com/item?id=44993124</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44993124</guid></item><item><title><![CDATA[New comment by abidlabs in "Open models by OpenAI"]]></title><description><![CDATA[
<p>Test it with a web UI: <a href="https://huggingface.co/spaces/abidlabs/openai-gpt-oss-120b-test" rel="nofollow">https://huggingface.co/spaces/abidlabs/openai-gpt-oss-120b-t...</a></p>
]]></description><pubDate>Tue, 05 Aug 2025 17:30:30 +0000</pubDate><link>https://news.ycombinator.com/item?id=44801228</link><dc:creator>abidlabs</dc:creator><comments>https://news.ycombinator.com/item?id=44801228</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44801228</guid></item><item><title><![CDATA[Trackio: A new experiment tracking library from Hugging Face]]></title><description><![CDATA[
<p>Article URL: <a href="https://huggingface.co/blog/trackio">https://huggingface.co/blog/trackio</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=44725285">https://news.ycombinator.com/item?id=44725285</a></p>
<p>Points: 4</p>
<p># Comments: 1</p>
]]></description><pubDate>Tue, 29 Jul 2025 16:22:36 +0000</pubDate><link>https://huggingface.co/blog/trackio</link><dc:creator>abidlabs</dc:creator><comments>https://news.ycombinator.com/item?id=44725285</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44725285</guid></item><item><title><![CDATA[New comment by abidlabs in "OpenAI Charges by the Minute, So Make the Minutes Shorter"]]></title><description><![CDATA[
<p>You could use Hugging Face's Inference API (which supports all of these API providers) directly making it easier to switch between them, e.g. look at the panel on the right on: <a href="https://huggingface.co/openai/whisper-large-v3" rel="nofollow">https://huggingface.co/openai/whisper-large-v3</a></p>
]]></description><pubDate>Wed, 25 Jun 2025 21:24:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=44381963</link><dc:creator>abidlabs</dc:creator><comments>https://news.ycombinator.com/item?id=44381963</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44381963</guid></item><item><title><![CDATA[Journey to 1M Python Developers]]></title><description><![CDATA[
<p>Article URL: <a href="https://twitter.com/abidlabs/status/1907886482150580381">https://twitter.com/abidlabs/status/1907886482150580381</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=43574872">https://news.ycombinator.com/item?id=43574872</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 03 Apr 2025 20:20:11 +0000</pubDate><link>https://twitter.com/abidlabs/status/1907886482150580381</link><dc:creator>abidlabs</dc:creator><comments>https://news.ycombinator.com/item?id=43574872</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43574872</guid></item></channel></rss>