Hacker News: mikejulietbravohttps://news.ycombinator.com/user?id=mikejulietbravoHacker News RSShttps://hnrss.org/hnrss v2.1.1Wed, 28 Oct 2026 17:32:28 +0000<![CDATA[New comment by mikejulietbravo in "Apple is going to raise device prices, but when?"]]>came to say this, there's almost zero history for this so unless their supply chain got meaningfully distorted I can't see why this would happen now

]]>Tue, 23 Jun 2026 13:53:36 +0000https://news.ycombinator.com/item?id=48645025mikejulietbravohttps://news.ycombinator.com/item?id=48645025https://news.ycombinator.com/item?id=48645025<![CDATA[New comment by mikejulietbravo in "The Traditional Vi"]]>text editors 5ever

]]>Tue, 23 Jun 2026 13:52:07 +0000https://news.ycombinator.com/item?id=48645000mikejulietbravohttps://news.ycombinator.com/item?id=48645000https://news.ycombinator.com/item?id=48645000<![CDATA[New comment by mikejulietbravo in "How to get GLM 5.2 to 280 tokens per second"]]>as benchmarked on AA

]]>Tue, 23 Jun 2026 13:50:36 +0000https://news.ycombinator.com/item?id=48644982mikejulietbravohttps://news.ycombinator.com/item?id=48644982https://news.ycombinator.com/item?id=48644982<![CDATA[How to get GLM 5.2 to 280 tokens per second]]>Article URL: https://www.baseten.co/blog/how-we-built-the-worlds-fastest-api-for-glm-52/

Comments URL: https://news.ycombinator.com/item?id=48644981

Points: 3

# Comments: 1

]]>Tue, 23 Jun 2026 13:50:36 +0000https://www.baseten.co/blog/how-we-built-the-worlds-fastest-api-for-glm-52/mikejulietbravohttps://news.ycombinator.com/item?id=48644981https://news.ycombinator.com/item?id=48644981<![CDATA[New comment by mikejulietbravo in "Ask HN: How do you choose a model for a task?"]]>The short answer is that it depends how well you define the boundaries of the task and the relative complexity. For example, smaller model is usually fine for something like summarization, but an "easier" coding task might still actually be quite difficult unless you eval it heavily like @paulhoule said

]]>Mon, 11 May 2026 22:55:28 +0000https://news.ycombinator.com/item?id=48101838mikejulietbravohttps://news.ycombinator.com/item?id=48101838https://news.ycombinator.com/item?id=48101838<![CDATA[New comment by mikejulietbravo in "The Math Behind TurboQuant"]]>how many mentions of silicon valley?

]]>Fri, 27 Mar 2026 00:41:45 +0000https://news.ycombinator.com/item?id=47537735mikejulietbravohttps://news.ycombinator.com/item?id=47537735https://news.ycombinator.com/item?id=47537735<![CDATA[New comment by mikejulietbravo in "Nvidia Invests $150M in AI Inference Startup Baseten"]]>seems like more than invested in other inference players

]]>Fri, 23 Jan 2026 18:48:45 +0000https://news.ycombinator.com/item?id=46736178mikejulietbravohttps://news.ycombinator.com/item?id=46736178https://news.ycombinator.com/item?id=46736178<![CDATA[New comment by mikejulietbravo in "After Babel Fish: The promise of cheap translations at the speed of the Web"]]>nuances like idioms can and will be solved. wispr flow is already solving a lot of these things via their speech-to-text interface.

as better models are introduced, figurative language, implication, cultural nuancec etc. becomes easier to reconcile.

]]>Sun, 21 Sep 2025 02:04:24 +0000https://news.ycombinator.com/item?id=45319381mikejulietbravohttps://news.ycombinator.com/item?id=45319381https://news.ycombinator.com/item?id=45319381<![CDATA[New comment by mikejulietbravo in "Hyperion: Minecraft game engine for custom events"]]>does the plugin architecture come with added overhead (assuming you add a lot of elements)?

]]>Sun, 21 Sep 2025 02:01:18 +0000https://news.ycombinator.com/item?id=45319369mikejulietbravohttps://news.ycombinator.com/item?id=45319369https://news.ycombinator.com/item?id=45319369<![CDATA[New comment by mikejulietbravo in "A brief history of threads and threading"]]>was just glad this wasn't about twitter :)

]]>Sun, 21 Sep 2025 01:59:40 +0000https://news.ycombinator.com/item?id=45319363mikejulietbravohttps://news.ycombinator.com/item?id=45319363https://news.ycombinator.com/item?id=45319363<![CDATA[New comment by mikejulietbravo in "An analysis of DeepSeek's R1-Zero and R1"]]>Awesome - we'd love to have our CEO/CTO chat with you and your team if you're interested. Shoot me a note at mike.bilodeau @ baseten.co and I'll make it happen!

]]>Wed, 29 Jan 2025 18:45:51 +0000https://news.ycombinator.com/item?id=42869310mikejulietbravohttps://news.ycombinator.com/item?id=42869310https://news.ycombinator.com/item?id=42869310<![CDATA[New comment by mikejulietbravo in "An analysis of DeepSeek's R1-Zero and R1"]]>Mike from Baseten here

We're super proud to support this work. If you're thinking of running deepseek in production, give us a shout!

]]>Wed, 29 Jan 2025 18:30:39 +0000https://news.ycombinator.com/item?id=42869108mikejulietbravohttps://news.ycombinator.com/item?id=42869108https://news.ycombinator.com/item?id=42869108<![CDATA[New comment by mikejulietbravo in "Hundred Rabbits is a small collective exploring the failability of modern tech"]]>The start of this reads like the beginning of a cult manifesto, but then transitions to a very logical solution for an important problem.

Baffling. I'm in

]]>Thu, 01 Aug 2024 17:50:58 +0000https://news.ycombinator.com/item?id=41131654mikejulietbravohttps://news.ycombinator.com/item?id=41131654https://news.ycombinator.com/item?id=41131654<![CDATA[New comment by mikejulietbravo in "Flux: Open-source text-to-image model with 12B parameters"]]>What's the tl;dr on a difference from this to SD?

]]>Thu, 01 Aug 2024 17:47:45 +0000https://news.ycombinator.com/item?id=41131623mikejulietbravohttps://news.ycombinator.com/item?id=41131623https://news.ycombinator.com/item?id=41131623<![CDATA[Show HN: Automatically Build Nvidia TRT-LLM Engines]]>Article URL: https://www.baseten.co/blog/automatic-llm-optimization-with-tensorrt-llm-engine-builder/

Comments URL: https://news.ycombinator.com/item?id=41131541

Points: 2

# Comments: 0

]]>Thu, 01 Aug 2024 17:39:06 +0000https://www.baseten.co/blog/automatic-llm-optimization-with-tensorrt-llm-engine-builder/mikejulietbravohttps://news.ycombinator.com/item?id=41131541https://news.ycombinator.com/item?id=41131541<![CDATA[Show HN: 60% higher tokens per second for 70B custom LLMs]]>We optimized Writer's Palmyra Fin and Palmyra Med for 60% higher TPS at 35% reduced cost

Comments URL: https://news.ycombinator.com/item?id=41121149

Points: 1

# Comments: 0

]]>Wed, 31 Jul 2024 17:22:57 +0000https://www.baseten.co/customers/writer/mikejulietbravohttps://news.ycombinator.com/item?id=41121149https://news.ycombinator.com/item?id=41121149<![CDATA[New comment by mikejulietbravo in "Show HN: I built an indie, browser-based MMORPG"]]>This is such a wild undertaking. I love it

]]>Thu, 27 Jun 2024 18:11:51 +0000https://news.ycombinator.com/item?id=40813349mikejulietbravohttps://news.ycombinator.com/item?id=40813349https://news.ycombinator.com/item?id=40813349<![CDATA[New comment by mikejulietbravo in "DoorDash and Pizza Arbitrage (2020)"]]>This is the biggest point. You can simply not use them. Cook your own food or walk or drive or bike to a restaurant.

There is a massive market of lazy AF people who also are terrible at personal financial management, and they are the ones complaining.

]]>Thu, 27 Jun 2024 18:07:43 +0000https://news.ycombinator.com/item?id=40813309mikejulietbravohttps://news.ycombinator.com/item?id=40813309https://news.ycombinator.com/item?id=40813309<![CDATA[New comment by mikejulietbravo in "DoorDash and Pizza Arbitrage (2020)"]]>Taxes are not the answer, let the free market figure it out

]]>Thu, 27 Jun 2024 18:05:40 +0000https://news.ycombinator.com/item?id=40813289mikejulietbravohttps://news.ycombinator.com/item?id=40813289https://news.ycombinator.com/item?id=40813289<![CDATA[New comment by mikejulietbravo in "Show HN: Dorkly – Open source feature flags"]]>I'm kind of surprised they haven't already built this into the LD core

]]>Thu, 27 Jun 2024 18:03:24 +0000https://news.ycombinator.com/item?id=40813264mikejulietbravohttps://news.ycombinator.com/item?id=40813264https://news.ycombinator.com/item?id=40813264