<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: bfeynman</title><link>https://news.ycombinator.com/user?id=bfeynman</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Fri, 07 Aug 2026 00:39:58 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=bfeynman" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by bfeynman in "Launch HN: ProvenMetal (YC S26) delivers circuit boards in days instead of weeks"]]></title><description><![CDATA[
<p>This would be incredible for innovation if we can bring this back domestically.  It's very hard given lack of raw materials and the supply chain around it often also requires robust network but hopefully this spurs something.<p>This is something that takes real expertise though, kind of a moonshot for an inexperienced team unfortunately.  Would be cool if had mission driven backers otherwise will just end up being hobbyist material.  Relying on defense (bubble?) gives at least some breathing room as not actually competing against china for better prices.</p>
]]></description><pubDate>Thu, 06 Aug 2026 16:15:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=49198716</link><dc:creator>bfeynman</dc:creator><comments>https://news.ycombinator.com/item?id=49198716</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49198716</guid></item><item><title><![CDATA[New comment by bfeynman in "qm – Multiplayer agent harness for work"]]></title><description><![CDATA[
<p>Can someone give me an example where this is truly and uniquely useful?  I've seen so many of these things and I can't tell if part of it is like mostly for enabling nontechnical folks to do more things or if it's some unlock and additive value.  At end of day beneath it all things are just prompts, and then you can provide tools and context, but even then that's not even something I've found that useful to keep because context windows are still limited and bias propagations often need to be constantly corrected, especially when digital artifacts are not perfect representations of the real world.</p>
]]></description><pubDate>Sat, 01 Aug 2026 13:24:40 +0000</pubDate><link>https://news.ycombinator.com/item?id=49134237</link><dc:creator>bfeynman</dc:creator><comments>https://news.ycombinator.com/item?id=49134237</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49134237</guid></item><item><title><![CDATA[New comment by bfeynman in "Amazon accidentally spent $1.8M using Claude for a menial coding task, went"]]></title><description><![CDATA[
<p>this is not noteworthy - simple misconfiguration and over-provisioning can result in same thing, and that happens all the time.</p>
]]></description><pubDate>Thu, 30 Jul 2026 20:08:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=49115091</link><dc:creator>bfeynman</dc:creator><comments>https://news.ycombinator.com/item?id=49115091</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49115091</guid></item><item><title><![CDATA[New comment by bfeynman in "A $500 RL fine-tune of a 9B open model beat frontier models on catalog review"]]></title><description><![CDATA[
<p>is this an ad?<p>| Harvey's legal agent beats GPT-5.5 and Claude Opus 4.8 on its own rubrics, and Intercom's Fin Apex resolves more support issues at lower cost.<p>The rubric and cost argument here just casually ignores all of the other challenges and real business issues of evolving models over time</p>
]]></description><pubDate>Tue, 28 Jul 2026 15:59:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=49085879</link><dc:creator>bfeynman</dc:creator><comments>https://news.ycombinator.com/item?id=49085879</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49085879</guid></item><item><title><![CDATA[New comment by bfeynman in "DuckPGQ – A DuckDB community extension for graph workloads"]]></title><description><![CDATA[
<p>kuzudb was sunsetted.  I think for graph workloads duckdb is best bet, even though this is just a community plugin the upstream duckdb has really robust community doing a lot of heavy lifting and updates.</p>
]]></description><pubDate>Fri, 24 Jul 2026 20:19:54 +0000</pubDate><link>https://news.ycombinator.com/item?id=49041121</link><dc:creator>bfeynman</dc:creator><comments>https://news.ycombinator.com/item?id=49041121</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49041121</guid></item><item><title><![CDATA[New comment by bfeynman in "Fertility is collapsing because motherhood is zero-status"]]></title><description><![CDATA[
<p>Trying to ascribe causality on macro/global level when the interesting tidbits are certainly on the regionalized scale seems mostly useless, although somewhat there is irony in again a man writing about why he thinks women having less kids than just going around and getting actual data points that aren't capture by societal level statistics. 
I think the undeniable trend is caused by economics especially in the western world.  It's more expensive to live than ever, and kids are very expensive when you factor in cost of living and lifestyle adjustments.<p>This sort of essay is farcical in ascribing economic stability as "status" - which of course has a negative connotation of seeking status, but suppose thats on track for a man writing an essay about this.  Women( and men) need to work now because single incomes are not enough, and women biologically have larger burden in child rearing regardless.   Economic incentives for child rearing are a joke, much like most policy that ends up more as a panacea than a solution - because none of it targets the other huge correlation we see, the growing level of inequality of wealth where the top n% is accumulating more and more.  One need not look at number of lawsuits regarding women getting fired or laid off from work for needing/taking maternal leave.  In the US you often need to be tenured for a year to qualify for it.   These are all economic issues at it's core, and the tautology to it being status seeking is an damaging one in and of itsef.</p>
]]></description><pubDate>Mon, 20 Jul 2026 17:03:40 +0000</pubDate><link>https://news.ycombinator.com/item?id=48981565</link><dc:creator>bfeynman</dc:creator><comments>https://news.ycombinator.com/item?id=48981565</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48981565</guid></item><item><title><![CDATA[New comment by bfeynman in "Building Food Metadata with LLM Juries"]]></title><description><![CDATA[
<p>despite having multibillion dollar valuation and a real product and service doordashes tech blogs have always been surprisingly simplistic and borderline elementary or in this case, kind of just slop.  I remember reading their early data science ones and they were all sort of comically limited or discussing tradeoffs between outdated methods.</p>
]]></description><pubDate>Tue, 14 Jul 2026 21:49:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=48913358</link><dc:creator>bfeynman</dc:creator><comments>https://news.ycombinator.com/item?id=48913358</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48913358</guid></item><item><title><![CDATA[New comment by bfeynman in "Oya – Keep tool outputs away from the LLM to cut tokens and stop injection"]]></title><description><![CDATA[
<p>The whole point of agentic tool calling is for there to be runtime decisions made by the agent based on the outcome of a tool call.  Anything that can be serialized like this could effectively be rewritten as a single tool call which this seems (via the example) to just be a tautology of for the most part.  Otherwise you would have combinatorial explosion of all the paths if there is actual logic branching.</p>
]]></description><pubDate>Tue, 14 Jul 2026 14:35:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=48907587</link><dc:creator>bfeynman</dc:creator><comments>https://news.ycombinator.com/item?id=48907587</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48907587</guid></item><item><title><![CDATA[New comment by bfeynman in "Potential session/cache leakage between workspace instances or consumer accounts"]]></title><description><![CDATA[
<p>fwiw, this could be a bug but the submitters level of arrogance places this rather high on the dunning-kruger side of things. There are multiple other plausible explanations, but this person is probably vibe coder who believes anything an llm says (including explaining its own hallucinations)</p>
]]></description><pubDate>Sat, 04 Jul 2026 15:55:50 +0000</pubDate><link>https://news.ycombinator.com/item?id=48786308</link><dc:creator>bfeynman</dc:creator><comments>https://news.ycombinator.com/item?id=48786308</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48786308</guid></item><item><title><![CDATA[New comment by bfeynman in "Alex Karp: Frontier Models Are Not Delivering Outcomes [video]"]]></title><description><![CDATA[
<p>[flagged]</p>
]]></description><pubDate>Thu, 02 Jul 2026 14:45:32 +0000</pubDate><link>https://news.ycombinator.com/item?id=48762437</link><dc:creator>bfeynman</dc:creator><comments>https://news.ycombinator.com/item?id=48762437</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48762437</guid></item><item><title><![CDATA[New comment by bfeynman in "Anthropic's Mythos AI breached almost all NSA systems in a red-team tests"]]></title><description><![CDATA[
<p>The massive information loss from officials who do not understand tech communicating about this has lead to these outrageous claims. I am super interested into what actually the researchers found, as the summarized headline seems highly unlikely, or at least in need of a lot of disclaimers.  Especially given that mythos seemed to be more about scaling test time compute and orchestration rather than leap in intelligence.</p>
]]></description><pubDate>Mon, 22 Jun 2026 18:39:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=48634191</link><dc:creator>bfeynman</dc:creator><comments>https://news.ycombinator.com/item?id=48634191</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48634191</guid></item><item><title><![CDATA[New comment by bfeynman in "Show HN: Recall – Local project memory for Claude Code"]]></title><description><![CDATA[
<p>What I've finally come to understand is that there is a large amount of people who are now able to write and use software through claude and coding agents.  Those people have different needs than more traditional software engineers who have more knowledge because even best llms often need steering, correction, and refactoring suggestions when iterating on code and it's fine to let it lose context because exactly like you said, you tell it to read file and then have to regurgitate the understanding so you can correct or validate it before continuing.<p>For those where the code is almost entirely a black box and cannot easily recover when something goes wrong.  They are much more keen on this context management and planning because recovering from derailments is much harder (and takes longer) because its often a conversation with llm to try to recover to where they were before.</p>
]]></description><pubDate>Mon, 22 Jun 2026 02:21:00 +0000</pubDate><link>https://news.ycombinator.com/item?id=48624866</link><dc:creator>bfeynman</dc:creator><comments>https://news.ycombinator.com/item?id=48624866</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48624866</guid></item><item><title><![CDATA[New comment by bfeynman in "I built a WhatsApp clone of myself; a friend agreed on a password with it"]]></title><description><![CDATA[
<p>probably all AI slop but I find it hilarious in the blog post they actually posture like they would know how to fine tune a model to sound like them given that what they actually did is something that you could one shot with claude if you knew what you were doing.</p>
]]></description><pubDate>Fri, 19 Jun 2026 21:08:44 +0000</pubDate><link>https://news.ycombinator.com/item?id=48603268</link><dc:creator>bfeynman</dc:creator><comments>https://news.ycombinator.com/item?id=48603268</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48603268</guid></item><item><title><![CDATA[New comment by bfeynman in "We Liked Remote Work. Then We Looked at the Data."]]></title><description><![CDATA[
<p>This article and ones like it are nonsense, there is really no control group as they try to make like an absolute comparison of things instead of relative to in office work.  You don't just take pros and cons with respect to a vacuum.  I see no mention of all the pros and cons of in office work of which there are tons obviously.</p>
]]></description><pubDate>Fri, 19 Jun 2026 17:53:36 +0000</pubDate><link>https://news.ycombinator.com/item?id=48601166</link><dc:creator>bfeynman</dc:creator><comments>https://news.ycombinator.com/item?id=48601166</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48601166</guid></item><item><title><![CDATA[New comment by bfeynman in "India's surprise baby bust"]]></title><description><![CDATA[
<p>factors are not invariant under different economic levels though.  For example - if you didn't need to work you can spend all the time in the world with your kids.  Someone who has no money and relatively low mobility and has to work night shifts at a factory does not even have the option to consider staying home like that.</p>
]]></description><pubDate>Thu, 18 Jun 2026 19:07:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=48589995</link><dc:creator>bfeynman</dc:creator><comments>https://news.ycombinator.com/item?id=48589995</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48589995</guid></item><item><title><![CDATA[New comment by bfeynman in "Migrate from OpenClaw"]]></title><description><![CDATA[
<p>can someone tell me the actual market size for technophiles who I think are only people who use this stuff?  I get lost in fact that people can't really understand that end of day this is just llm calls with like sqlite facade. I see the value is the convenience only of not having to set stuff up, but everyone else claims it does all this extra stuff that is not trivial to reproduce yourself.</p>
]]></description><pubDate>Thu, 18 Jun 2026 17:42:48 +0000</pubDate><link>https://news.ycombinator.com/item?id=48588820</link><dc:creator>bfeynman</dc:creator><comments>https://news.ycombinator.com/item?id=48588820</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48588820</guid></item><item><title><![CDATA[New comment by bfeynman in "How we run Firecracker VMs inside EC2 and start browsers in less than 1s"]]></title><description><![CDATA[
<p>they kind of do.. gcp has their lambda equivalent which i believe comes with chromium preinstalled, its how major search tools like jina work, sure thre problaby somethign about session management that they probably neuter to prevent abuse though</p>
]]></description><pubDate>Wed, 17 Jun 2026 19:08:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=48575248</link><dc:creator>bfeynman</dc:creator><comments>https://news.ycombinator.com/item?id=48575248</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48575248</guid></item><item><title><![CDATA[New comment by bfeynman in "Claude Fable 5"]]></title><description><![CDATA[
<p>Given it was made by cognition (team behind devin flop) who now just got to wait out until claude and gpt5 basically do all of the work for them - not very.  When you read about it, the framework is highly subjective.  Which very quickly becomes a problem because its based on heuristics that probably change a bunch with a better code model.</p>
]]></description><pubDate>Tue, 09 Jun 2026 17:59:25 +0000</pubDate><link>https://news.ycombinator.com/item?id=48464903</link><dc:creator>bfeynman</dc:creator><comments>https://news.ycombinator.com/item?id=48464903</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48464903</guid></item><item><title><![CDATA[New comment by bfeynman in "My Agent Skill for Test-Driven Development"]]></title><description><![CDATA[
<p>In what world or frame of reference would doing TDD have "little" bearing on output quality? If you build a system around satisfying some set of requirements it seems logical that output quality would have pretty heavy correlation.</p>
]]></description><pubDate>Sat, 06 Jun 2026 02:06:50 +0000</pubDate><link>https://news.ycombinator.com/item?id=48420687</link><dc:creator>bfeynman</dc:creator><comments>https://news.ycombinator.com/item?id=48420687</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48420687</guid></item><item><title><![CDATA[New comment by bfeynman in "India's surprise baby bust"]]></title><description><![CDATA[
<p>I hate to break it to you but those are almost all economic problems in the grand scheme of things.</p>
]]></description><pubDate>Sat, 06 Jun 2026 01:51:21 +0000</pubDate><link>https://news.ycombinator.com/item?id=48420599</link><dc:creator>bfeynman</dc:creator><comments>https://news.ycombinator.com/item?id=48420599</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48420599</guid></item></channel></rss>