<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: monroewalker</title><link>https://news.ycombinator.com/user?id=monroewalker</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 19 Nov 2026 21:28:16 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=monroewalker" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by monroewalker in "Claude discovers a novel enzyme system with CRISPR-like repeats"]]></title><description><![CDATA[
<p>Thank you for sharing, that provided some good context for how to interpret this<p>Post content:<p>_____<p>I wish we didn’t need these again, but here is the honest version of Anthropic’s biology announcement 
(Caveat: I haven’t worked in bioinformatics for many years.)
The good: Anthropic ran ~950 Claude agents over a large biological sequence database. Claude searched, wrote code, compared sequences and genomic neighborhoods, and found an interesting pattern that apparently had not been noticed before: a known reverse transcriptase associated with another gene and a repetitive DNA array.<p>That is cool. Automating this kind of open-ended bioinformatics search at scale is useful, and Claude may have found a lead a human would have missed.<p>But: Claude did not do a biological experiment. It searched databases and analyzed data.<p>Humans then took the candidate into the wet lab. And the wet-lab result so far is modest: they showed that the repeat array produces short RNAs.<p>We still don’t know what the system does. No function, mechanism, phenotype, targeting, defense activity, or programmability has been demonstrated.<p>This is also where the CRISPR framing gets ahead of the result. Right now, “it has some features reminiscent of known programmable systems” is a hypothesis for what to investigate next, not a discovery that it behaves like CRISPR.<p>And there is a missing baseline: bioinformatics has had tools for finding unusual gene neighborhoods and candidate systems for years. The interesting comparison is 950 Claude agents vs. an expert using the best existing computational pipelines - not Claude vs. someone manually looking through 200,000 sequences.<p>So my honest announcement would be:<p>Claude autonomously found an interesting candidate for a previously uncharacterized biological system. A small human wet-lab experiment confirmed that part of the candidate is expressed. We don’t yet know what it does.<p>That is a good result.<p>But in a regular biology lab, this isn’t the finished paper. It is the result you show at lab meeting and say: “This looks interesting. Now we need to figure out what the hell it does.”<p>Maybe that next step leads to a major discovery. But that discovery hasn’t happened yet.</p>
]]></description><pubDate>Wed, 23 Sep 2026 19:45:22 +0000</pubDate><link>https://news.ycombinator.com/item?id=49821471</link><dc:creator>monroewalker</dc:creator><comments>https://news.ycombinator.com/item?id=49821471</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49821471</guid></item><item><title><![CDATA[New comment by monroewalker in "Gemini 3.8 Live and 3.8 Live Extended Thinking"]]></title><description><![CDATA[
<p>Seems more than good enough for a live model though! I can imagine this demo being extended to be a lot nicer to play with. You can just feed the model engine analysis and it can make as high of quality moves as needed. No longer any correlation between the model's understanding of the position and the moves that would be made but I think that's still a really nice improvement when thinking about this as adding live voice interaction to existing chess vs computer functionality rather than adding chess to possible interactions with the latest live voice model.</p>
]]></description><pubDate>Tue, 15 Sep 2026 18:55:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=49717125</link><dc:creator>monroewalker</dc:creator><comments>https://news.ycombinator.com/item?id=49717125</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49717125</guid></item><item><title><![CDATA[New comment by monroewalker in "GPT-6 Astra"]]></title><description><![CDATA[
<p>Same price as Fable?</p>
]]></description><pubDate>Thu, 03 Sep 2026 20:08:12 +0000</pubDate><link>https://news.ycombinator.com/item?id=49556105</link><dc:creator>monroewalker</dc:creator><comments>https://news.ycombinator.com/item?id=49556105</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49556105</guid></item><item><title><![CDATA[New comment by monroewalker in "OpenAI and Hugging Face address security incident during model evaluation"]]></title><description><![CDATA[
<p>Great summary! I would just add that cherry on top though -- that HuggingFace tried using the top commercial models in response but couldn't because of the cybersecurity restrictions so they had to use GLM 5.2 instead<p>"When we started the log analysis, we first used frontier models behind commercial APIs. This did not work: the analysis requires submitting large volumes of real attack commands, exploit payloads, and C2 artifacts, and these requests were blocked by the providers' safety guardrails, which cannot distinguish an incident responder from an attacker. We ran the forensic analysis instead on GLM 5.2, an open-weight model, on our own infrastructure. This had a second benefit: no attacker data, and none of the credentials it referenced, left our environment."</p>
]]></description><pubDate>Tue, 21 Jul 2026 21:34:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=48998687</link><dc:creator>monroewalker</dc:creator><comments>https://news.ycombinator.com/item?id=48998687</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48998687</guid></item><item><title><![CDATA[New comment by monroewalker in "Chatto is now Open Source"]]></title><description><![CDATA[
<p>What makes it nicer to use than Slack?</p>
]]></description><pubDate>Wed, 08 Jul 2026 16:09:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=48833738</link><dc:creator>monroewalker</dc:creator><comments>https://news.ycombinator.com/item?id=48833738</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48833738</guid></item><item><title><![CDATA[New comment by monroewalker in "Debug Project"]]></title><description><![CDATA[
<p>Heh after reading that title card I thought this was going to be a mosquito based software bug analogy. I expected a description of how to write software that resulted in more "good bugs" that might facilitate finding other bugs somehow. Now I'm a little disappointed</p>
]]></description><pubDate>Tue, 02 Jun 2026 00:20:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=48364279</link><dc:creator>monroewalker</dc:creator><comments>https://news.ycombinator.com/item?id=48364279</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48364279</guid></item><item><title><![CDATA[Dord]]></title><description><![CDATA[
<p>Article URL: <a href="https://en.wikipedia.org/wiki/Dord">https://en.wikipedia.org/wiki/Dord</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47201579">https://news.ycombinator.com/item?id=47201579</a></p>
<p>Points: 7</p>
<p># Comments: 0</p>
]]></description><pubDate>Sat, 28 Feb 2026 23:22:38 +0000</pubDate><link>https://en.wikipedia.org/wiki/Dord</link><dc:creator>monroewalker</dc:creator><comments>https://news.ycombinator.com/item?id=47201579</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47201579</guid></item><item><title><![CDATA[New comment by monroewalker in "Ask HN: What are you working on? (May 2025)"]]></title><description><![CDATA[
<p>Now that Claude 4 is out, I’m making some updates to the project I’ve built primarily just with Claude Code: <a href="https://github.com/mwalkerr/BookmarkCanvas">https://github.com/mwalkerr/BookmarkCanvas</a><p>It’s just a basic IntelliJ plugin which provides an infinite canvas to add code bookmarks to. I work on a large code base and often have to take on tasks involving lots of unfamiliar areas of code and components which influence each other only through long chains of indirection. Having a visual space to lay things out, draw connections, and quickly jump back into the code has been really helpful<p>The canvas and UI is built using Java AWT since that’s what IntelliJ plugins are built on, but it occurred to me that I could just throw in a web view and use any of the existing JS libraries for working on an infinite canvas. React Flow has seemed like the best option with tldraw being what I’d fallback to.<p>But then.. if the canvas is built with web technology then there’s no reason to keep it just within an IntelliJ plugin vs just a standalone web app with the ability to contain generic content that might open files in IntelliJ or any other editor. I’m pretty sure the “knowledge database on a canvas” thing has been done a number of times already so I want to also see if there are existing open source projects that it’d be easy enough to just add a special node type to</p>
]]></description><pubDate>Sun, 25 May 2025 22:52:23 +0000</pubDate><link>https://news.ycombinator.com/item?id=44092002</link><dc:creator>monroewalker</dc:creator><comments>https://news.ycombinator.com/item?id=44092002</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44092002</guid></item><item><title><![CDATA[New comment by monroewalker in "Why I find diffusion models interesting?"]]></title><description><![CDATA[
<p>See also this recent post about Mercury-Coder from Inception Labs. There's a "diffusion effect" toggle for their chat interface but I have no idea if that's an accurate representation of the model's diffusion process or just some randomly generated characters showing what the diffusion process looks like<p><a href="https://news.ycombinator.com/item?id=43187518">https://news.ycombinator.com/item?id=43187518</a><p><a href="https://www.inceptionlabs.ai/news" rel="nofollow">https://www.inceptionlabs.ai/news</a></p>
]]></description><pubDate>Fri, 07 Mar 2025 08:05:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=43288142</link><dc:creator>monroewalker</dc:creator><comments>https://news.ycombinator.com/item?id=43288142</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43288142</guid></item><item><title><![CDATA[New comment by monroewalker in "Show HN: IntelliJ plugin for organizing bookmarks on an infinite canvas"]]></title><description><![CDATA[
<p>Just about every line of code for this was written by Claude 3.7 via Claude Code. I never gave the other AI development tools like Cursor and Aider a fair shake so I may have just been behind the times on what's possible with agentic editors, but I found Claude Code to be extremely impressive. The API costs did end up being something around $15 though and this is a really small project, so I imagine cost goes up quite a bit to do any non-trivial work on a project of a decent size<p>This was great for me though because this is something I've had in mind for a while but never considered quite useful enough to be worth the time it'd take to learn about IntelliJ plugin development + the Java AWT knowledge required to create a canvas app like this</p>
]]></description><pubDate>Mon, 03 Mar 2025 05:45:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=43238659</link><dc:creator>monroewalker</dc:creator><comments>https://news.ycombinator.com/item?id=43238659</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43238659</guid></item><item><title><![CDATA[Show HN: IntelliJ plugin for organizing bookmarks on an infinite canvas]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/mwalkerr/BookmarkCanvas">https://github.com/mwalkerr/BookmarkCanvas</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=43238631">https://news.ycombinator.com/item?id=43238631</a></p>
<p>Points: 2</p>
<p># Comments: 1</p>
]]></description><pubDate>Mon, 03 Mar 2025 05:41:19 +0000</pubDate><link>https://github.com/mwalkerr/BookmarkCanvas</link><dc:creator>monroewalker</dc:creator><comments>https://news.ycombinator.com/item?id=43238631</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43238631</guid></item><item><title><![CDATA[New comment by monroewalker in "Crossing the uncanny valley of conversational voice"]]></title><description><![CDATA[
<p>lol yeah I tried to get it to whisper too. And talk faster or slower or do accents. It seemed to be able to kind of do each of those things but only very slightly. Enough to see that there was some successful interpretation of the request but lack of flexibility to fully execute on it. OpenAI's model still has this beat on that front imo (talking quietly / slower / faster)</p>
]]></description><pubDate>Sun, 02 Mar 2025 06:43:36 +0000</pubDate><link>https://news.ycombinator.com/item?id=43228002</link><dc:creator>monroewalker</dc:creator><comments>https://news.ycombinator.com/item?id=43228002</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43228002</guid></item><item><title><![CDATA[New comment by monroewalker in "Crossing the uncanny valley of conversational voice"]]></title><description><![CDATA[
<p>Yeah after a few interactions, the repetition of the mannerisms that initially added to the sense of life-likeness started to break the illusion a bit. The "you got me" response shows up a bit too often. The creativity remains impressive though</p>
]]></description><pubDate>Sun, 02 Mar 2025 06:40:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=43227989</link><dc:creator>monroewalker</dc:creator><comments>https://news.ycombinator.com/item?id=43227989</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43227989</guid></item><item><title><![CDATA[New comment by monroewalker in "Crossing the uncanny valley of conversational voice"]]></title><description><![CDATA[
<p>This was already posted here: <a href="https://news.ycombinator.com/item?id=43221377">https://news.ycombinator.com/item?id=43221377</a> but I’m really surprised at the lack of attention this model is getting. The responsiveness and apparent personality are pretty mind blowing. It’s similar to what OpenAI had initially demoed for advanced voice mode, at least for the voice conversation portion.<p>The demo interactions are recorded, which is mentioned in their disclaimer under the demo UI. What isn't mentioned though is that they include past conversations in the context for the model on future interactions. It was pretty surprising to be greeted with something like "welcome back" and the model being able to reference what was said in previous interactions. The full disclaimer on the page for the demo is:<p>"
1. Microphone permission is required. 2. Calls are recorded for quality review but not used for ML training and are deleted within 30 days. 3. By using this demo, you are agreeing to our
"<p>edit: Actually this has been posted quite a few times already and had good visibility a couple days ago:
- <a href="https://news.ycombinator.com/item?id=43200400">https://news.ycombinator.com/item?id=43200400</a>
Others: <a href="https://hn.algolia.com/?q=sesame.com" rel="nofollow">https://hn.algolia.com/?q=sesame.com</a></p>
]]></description><pubDate>Sun, 02 Mar 2025 06:16:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=43227900</link><dc:creator>monroewalker</dc:creator><comments>https://news.ycombinator.com/item?id=43227900</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43227900</guid></item><item><title><![CDATA[Crossing the uncanny valley of conversational voice]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.sesame.com/research/crossing_the_uncanny_valley_of_voice">https://www.sesame.com/research/crossing_the_uncanny_valley_of_voice</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=43227881">https://news.ycombinator.com/item?id=43227881</a></p>
<p>Points: 402</p>
<p># Comments: 218</p>
]]></description><pubDate>Sun, 02 Mar 2025 06:13:01 +0000</pubDate><link>https://www.sesame.com/research/crossing_the_uncanny_valley_of_voice</link><dc:creator>monroewalker</dc:creator><comments>https://news.ycombinator.com/item?id=43227881</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43227881</guid></item><item><title><![CDATA[Ask HN: Why do you trust Kagi?]]></title><description><![CDATA[
<p>I frequently see high praise for Kagi here, both for the quality of the search results as well as the ostensibly customer-friendly business decisions.<p>For the people that use their search and trust the company - why? Not to say I don’t trust them or trust them less than any other company claiming to be privacy and security focused, just would like to know how others made their decision.<p>The obvious strawman argument seems to be that since they charge for search, their business model is based on subscriptions rather than monetizing search data. Nothing would stop a company from charging for search AND selling data</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=43178217">https://news.ycombinator.com/item?id=43178217</a></p>
<p>Points: 14</p>
<p># Comments: 23</p>
]]></description><pubDate>Tue, 25 Feb 2025 22:12:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=43178217</link><dc:creator>monroewalker</dc:creator><comments>https://news.ycombinator.com/item?id=43178217</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43178217</guid></item><item><title><![CDATA[New comment by monroewalker in "Ask HN: What are you working on? (February 2025)"]]></title><description><![CDATA[
<p>Do the banks offer email notifications for transactions? That could be another approach if you automate pulling info from the emails</p>
]]></description><pubDate>Mon, 24 Feb 2025 08:27:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=43157060</link><dc:creator>monroewalker</dc:creator><comments>https://news.ycombinator.com/item?id=43157060</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43157060</guid></item><item><title><![CDATA[New comment by monroewalker in "Ask HN: What are you working on? (February 2025)"]]></title><description><![CDATA[
<p>A cross-platform clipboard manager / search-and-filter tool / launcher built with Flutter that has a simple Python plugin interface.<p>Plugins can be used to add new "result actions" and new sources of entries to filter and select. Eg. recent Jira tickets, email inbox, shell history, Notion pages, etc.
The result actions are a way to easily perform common transformations on selected entries (eg. wrap in triple backticks, find and parse json, trim whitespace, ...) or kickoff some script with a selected entry as an argument.<p>Project started as a result of having to do a lot of work using Ubuntu and sorely missing Alfred and all the workflows I'd built with it. I wanted something for which I could build workflows once and have those workflows available on whatever system I'm on. Plus to be able to build some plugins that would be usable by coworkers regardless of what operating system they're using and with minimal runtime resource usage. There are some existing cross-platform solutions which could serve this purpose, like Cerebro, Ueli, Script Kit, some others.., but I wanted something lighter weight than is possible with an Electron app. Granted the current state of Epte is that it's built with Flutter + Go + Python so the final distributable and runtime memory usage are higher than is ideal.<p>Basic Windows support is almost there but there doesn't seem to be a great solution to switching to existing windows of an application instead of just re-launching it. The tool isn't intended to be as good or better than any given OS's built-in launcher so I'll probably just leave that as-is and upload the current state of the Windows build.<p><a href="https://github.com/mwalkerr/Epte">https://github.com/mwalkerr/Epte</a></p>
]]></description><pubDate>Mon, 24 Feb 2025 06:47:03 +0000</pubDate><link>https://news.ycombinator.com/item?id=43156492</link><dc:creator>monroewalker</dc:creator><comments>https://news.ycombinator.com/item?id=43156492</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43156492</guid></item><item><title><![CDATA[New comment by monroewalker in "Johnny.Decimal – A system to organise your life"]]></title><description><![CDATA[
<p>The best approach I’ve found so far is to just have a single master “event log” where I dump everything that I want to save by default. I have specific places to put things but if I can’t be bothered to decide where or am not sure it’ll just go to the event log. I’m using Notion for this where each entry is its own page in a “database” list. Adding a new page is trivial though through the site or app. I have an iOS shortcut setup too to open the entry creation</p>
]]></description><pubDate>Fri, 21 Feb 2025 19:21:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=43131738</link><dc:creator>monroewalker</dc:creator><comments>https://news.ycombinator.com/item?id=43131738</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43131738</guid></item><item><title><![CDATA[New comment by monroewalker in "Ask HN: Is anybody building an alternative transformer?"]]></title><description><![CDATA[
<p>Oh that would be awesome for that to work. Thanks for sharing</p>
]]></description><pubDate>Fri, 14 Feb 2025 21:15:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=43053142</link><dc:creator>monroewalker</dc:creator><comments>https://news.ycombinator.com/item?id=43053142</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43053142</guid></item></channel></rss>