<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: jmogly</title><link>https://news.ycombinator.com/user?id=jmogly</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Mon, 25 May 2026 00:44:56 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=jmogly" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by jmogly in "Cloudflare to cut about 20% of its workforce"]]></title><description><![CDATA[
<p>Yes I suppose this is the bare minimum, but isn’t that just a nasty way to go about things? What about responsibility and decency, do we just not do that anymore?</p>
]]></description><pubDate>Mon, 11 May 2026 01:08:21 +0000</pubDate><link>https://news.ycombinator.com/item?id=48089932</link><dc:creator>jmogly</dc:creator><comments>https://news.ycombinator.com/item?id=48089932</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48089932</guid></item><item><title><![CDATA[New comment by jmogly in "How Kepler built verifiable AI for financial services with Claude"]]></title><description><![CDATA[
<p>How do you know that the llm is correctly translating the english queries to the verifiable primitives? It seems like it’s just pushing the problem to another layer?</p>
]]></description><pubDate>Mon, 04 May 2026 12:31:57 +0000</pubDate><link>https://news.ycombinator.com/item?id=48007878</link><dc:creator>jmogly</dc:creator><comments>https://news.ycombinator.com/item?id=48007878</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48007878</guid></item><item><title><![CDATA[New comment by jmogly in "Decisions that eroded trust in Azure – by a former Azure Core engineer"]]></title><description><![CDATA[
<p>Ah yes great point, awesome article by the way —- thought provoking, shocking, really crazy stuff. Hopefully some good comes of it, godspeed.</p>
]]></description><pubDate>Fri, 03 Apr 2026 05:24:27 +0000</pubDate><link>https://news.ycombinator.com/item?id=47623440</link><dc:creator>jmogly</dc:creator><comments>https://news.ycombinator.com/item?id=47623440</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47623440</guid></item><item><title><![CDATA[New comment by jmogly in "Decisions that eroded trust in Azure – by a former Azure Core engineer"]]></title><description><![CDATA[
<p>It is kind of a fundamental risk of IMDS, the guest vms often need some metadata about themselves, the host has it. A hardened, network gapped service running host side is acceptable, possibly the best solution. I think the issue is if your IMDS is fat and vulnerable, which this article kind of alludes to.<p>There’s also the fact that azure’s implementation doesn’t require auth so it’s very vulnerable to SSRF</p>
]]></description><pubDate>Fri, 03 Apr 2026 03:52:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=47623016</link><dc:creator>jmogly</dc:creator><comments>https://news.ycombinator.com/item?id=47623016</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47623016</guid></item><item><title><![CDATA[New comment by jmogly in "Decisions that eroded trust in Azure – by a former Azure Core engineer"]]></title><description><![CDATA[
<p>Mainly for getting managed-identity access tokens for Azure APIs. In AWS you can call it to get temporary credentials for the EC2’s attached IAM role. In both cases - you use IMDS to get tokens/creds for identity/access management.<p>Client libraries usually abstract away the need to call IMDS directly by calling it for you.</p>
]]></description><pubDate>Fri, 03 Apr 2026 03:34:12 +0000</pubDate><link>https://news.ycombinator.com/item?id=47622911</link><dc:creator>jmogly</dc:creator><comments>https://news.ycombinator.com/item?id=47622911</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47622911</guid></item><item><title><![CDATA[New comment by jmogly in "Decisions that eroded trust in Azure – by a former Azure Core engineer"]]></title><description><![CDATA[
<p>This is insane, when you say azure OpenAI, do you mean like github copilot, microsoft copilot, hitting openai’s api, or some openai llm hosted on azure offering that you hit through azure? This is some real wild west crap!</p>
]]></description><pubDate>Fri, 03 Apr 2026 02:08:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=47622502</link><dc:creator>jmogly</dc:creator><comments>https://news.ycombinator.com/item?id=47622502</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47622502</guid></item><item><title><![CDATA[New comment by jmogly in "Go hard on agents, not on your filesystem"]]></title><description><![CDATA[
<p>Haha, you can already see wheel reinventors in this thread starting to spin their reinvention wheels. Nice stuff, I run my agents in containers.</p>
]]></description><pubDate>Sat, 28 Mar 2026 12:46:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=47554097</link><dc:creator>jmogly</dc:creator><comments>https://news.ycombinator.com/item?id=47554097</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47554097</guid></item><item><title><![CDATA[New comment by jmogly in "MCP is dead; long live MCP"]]></title><description><![CDATA[
<p>OP never mentioned letting the agent run as him or use his secrets. All of the issues you mention can be solved by giving the agent it’s own set of secrets or using basic file permissions, which are table stakes.<p>Back to the MCP debate, in a world where most web apis have a schema endpoint, their own authentication and authorization mechanisms, and in many instances easy to install clients in the form of CLIs … why do we need a new protocol, a new server, a new whatever. KISS</p>
]]></description><pubDate>Sun, 15 Mar 2026 11:49:46 +0000</pubDate><link>https://news.ycombinator.com/item?id=47386500</link><dc:creator>jmogly</dc:creator><comments>https://news.ycombinator.com/item?id=47386500</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47386500</guid></item><item><title><![CDATA[New comment by jmogly in "The death of social media is the renaissance of RSS (2025)"]]></title><description><![CDATA[
<p>Chat gpt is a great name though — you “chat” with the “GPT” so its self informing (even if you dont know what a GPT is), it’s 4 syllables that roll off the tongue well together.<p>RSS, has no vowels, no information, and looks like an alphabet term you might see at the doctor’s office or in an HR onboarding form at a corpo.</p>
]]></description><pubDate>Mon, 09 Mar 2026 11:08:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=47307499</link><dc:creator>jmogly</dc:creator><comments>https://news.ycombinator.com/item?id=47307499</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47307499</guid></item><item><title><![CDATA[New comment by jmogly in "Sometimes your job is to stay the hell out of the way"]]></title><description><![CDATA[
<p>It would be like if I was expected to deliver A by the end of the quarter and instead I delivered A + B. The value gain from B was more than A. Your manager (and hopefully higher up the org) better know about B, or they will attack it as a threat.<p>Also, I’m not being paid for my time, I’m being paid to do a job. “Trading your time for money” is one of the most self defeating views on work you can have. It reduces you from a worker with agency to a detached prostitue, and is harmful to both the employer and employee.</p>
]]></description><pubDate>Sun, 01 Feb 2026 16:26:11 +0000</pubDate><link>https://news.ycombinator.com/item?id=46847258</link><dc:creator>jmogly</dc:creator><comments>https://news.ycombinator.com/item?id=46847258</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46847258</guid></item><item><title><![CDATA[New comment by jmogly in "Sometimes your job is to stay the hell out of the way"]]></title><description><![CDATA[
<p>Early in my career I would build something I thought was useful, deploy it, meet with people within the company to get people to start using it. A lot of effort for something that would have a positive impact. My manager would schedule a meeting with me, and with a look of panic open with, “why didn’t you tell me about this or why did you do this?”. I understand now that before you start something, you need to decide who you are going to give credit to, and that person needs to be made aware that they will get credit for the project. Ideally your boss’s boss’s boss. Corporate caché only exist insofar as leadership allows it to exist, you gotta play the game. Pawns don’t get to take the glory for themselves.</p>
]]></description><pubDate>Sun, 01 Feb 2026 14:18:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=46846383</link><dc:creator>jmogly</dc:creator><comments>https://news.ycombinator.com/item?id=46846383</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46846383</guid></item><item><title><![CDATA[New comment by jmogly in "Code and Let Live"]]></title><description><![CDATA[
<p>Like it, a lot. I think the future of software is going to be unimaginably dynamic. Maybe apps will not have statically defined feature sets, they will adjust themselves around what the user wants and the data it has access to. I’m not entirely sure what that looks like yet, but things like this are a step in that direction.</p>
]]></description><pubDate>Fri, 09 Jan 2026 22:13:46 +0000</pubDate><link>https://news.ycombinator.com/item?id=46560150</link><dc:creator>jmogly</dc:creator><comments>https://news.ycombinator.com/item?id=46560150</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46560150</guid></item><item><title><![CDATA[New comment by jmogly in "The future of software development is software developers"]]></title><description><![CDATA[
<p>Of course, step one is always critically think and evaluate for bad information. I think for research, I mainly use it for things that are testable/verifiable, for example I used it for a tricky proxy chain set up. I did try to use it to learn a language a few months ago which I think was counter productive for the reasons you mentioned.</p>
]]></description><pubDate>Tue, 30 Dec 2025 14:03:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=46433412</link><dc:creator>jmogly</dc:creator><comments>https://news.ycombinator.com/item?id=46433412</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46433412</guid></item><item><title><![CDATA[New comment by jmogly in "The future of software development is software developers"]]></title><description><![CDATA[
<p>I would say it varies from 0x to a modest 2x. It can help you write good code quickly, but, I only spent about 20-30% of my time writing code anyway before AI. It definitely makes debugging and research tasks much easier as well. I would confidently say my job as a senior dev has gotten a lot easier and less stressful as a result of these tools.<p>One other thing I have seen however is the 0x case, where you have given too much control to the llm, it codes both you and itself into pan’s labyrinth, and you end up having to take a weed wacker to the whole project or start from scratch.</p>
]]></description><pubDate>Mon, 29 Dec 2025 22:53:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=46426955</link><dc:creator>jmogly</dc:creator><comments>https://news.ycombinator.com/item?id=46426955</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46426955</guid></item><item><title><![CDATA[New comment by jmogly in "Critical vulnerability in LangChain – CVE-2025-68664"]]></title><description><![CDATA[
<p>I’ve been using the following pattern since gpt3, the only other thing I have changed was added another parameter for schema for structured output. People really love to overcomplicate things.<p>class AI(Protocol):<p>def call_llm(prompt: str) -> str:
…</p>
]]></description><pubDate>Sun, 28 Dec 2025 09:49:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=46409829</link><dc:creator>jmogly</dc:creator><comments>https://news.ycombinator.com/item?id=46409829</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46409829</guid></item><item><title><![CDATA[New comment by jmogly in "Critical vulnerability in LangChain – CVE-2025-68664"]]></title><description><![CDATA[
<p>100% Gemini + pydantic you don’t need a wrapper library in 2025</p>
]]></description><pubDate>Sat, 27 Dec 2025 00:32:00 +0000</pubDate><link>https://news.ycombinator.com/item?id=46397916</link><dc:creator>jmogly</dc:creator><comments>https://news.ycombinator.com/item?id=46397916</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46397916</guid></item><item><title><![CDATA[New comment by jmogly in "A Developer Accidentally Found CSAM in AI Data. Google Banned Him for It"]]></title><description><![CDATA[
<p>On one hand, I would like to say this could happen to anyone, on the other hand, what the F?? why are people passing around a dataset that contains child sexual abuse material??, and on another hand, I think this whole thing just reeks of techy-bravado, and I don’t exactly blame him. If one of the inputs of your product (OpenAI, google, microsoft, meta, X) is a dataset that you can’t even say for sure does not contain child pornography, that’s pretty alarming.</p>
]]></description><pubDate>Fri, 12 Dec 2025 04:50:32 +0000</pubDate><link>https://news.ycombinator.com/item?id=46240976</link><dc:creator>jmogly</dc:creator><comments>https://news.ycombinator.com/item?id=46240976</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46240976</guid></item><item><title><![CDATA[New comment by jmogly in "We Need to Die"]]></title><description><![CDATA[
<p>Eh I’ll take my 78, someone else can have the rest.</p>
]]></description><pubDate>Wed, 10 Dec 2025 05:15:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=46214341</link><dc:creator>jmogly</dc:creator><comments>https://news.ycombinator.com/item?id=46214341</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46214341</guid></item><item><title><![CDATA[New comment by jmogly in "Confessions of a Software Developer: No More Self-Censorship"]]></title><description><![CDATA[
<p>Lol! This is probably my sneaky number one productivity benefit from LLMs, I would never want to go back to writing shell scripts pre-llm. So many hours wasted debugging and deciphering stack overflow over the years, dropping &,$, [[]], “”,|,<> in different places hoping to get my .shitty scripts working. Like conceptually I understand shell scripting very well, but anyone nobody can argue that bash isn’t footgun central.</p>
]]></description><pubDate>Sat, 29 Nov 2025 16:51:27 +0000</pubDate><link>https://news.ycombinator.com/item?id=46088920</link><dc:creator>jmogly</dc:creator><comments>https://news.ycombinator.com/item?id=46088920</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46088920</guid></item><item><title><![CDATA[New comment by jmogly in "Running a business means contact with reality"]]></title><description><![CDATA[
<p>Some real honest and actionable advice here. I think the natural course for intelligent people that enjoy crafting things is very much in conflict with the real world. We care about the things we are building because we see them as an extension of ourselves.  Anxiously perfecting our creations in a safe place, obsessing over ever smaller details of finished portions; working on detailing while ignoring the missing half of the ship. Its an ego thing. We see these things as pieces of ourselves, we’re afraid that the world won’t accept them, and by extension us. It’s not real though; nothing and nobody is perfect, and its okay.<p>I have a deep feeling that i can “do it myself”, yet i work for companies because deep down I like the anonymity and the safety of it; at a big company we get to be part of something established, we don’t have to show our own faces to the world.</p>
]]></description><pubDate>Sat, 29 Nov 2025 16:29:57 +0000</pubDate><link>https://news.ycombinator.com/item?id=46088748</link><dc:creator>jmogly</dc:creator><comments>https://news.ycombinator.com/item?id=46088748</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46088748</guid></item></channel></rss>