Hacker News: airspresso

New comment by airspresso in "OpenAI unveils its first custom chip, built by Broadcom"

airspresso — Wed, 24 Jun 2026 17:49:24 +0000

OpenAI's upcoming mega IPO

New comment by airspresso in "Magnifica Humanitas"

airspresso — Tue, 26 May 2026 09:40:40 +0000

> Time for me to go research the early history of electrification.

The Stepchange podcast has an amazing episode on The Grid [1], walking us through the arc of history of how it became the utility it is today.

[1]: https://www.stepchange.show/grid

New comment by airspresso in "Higher usage limits for Claude and a compute deal with SpaceX"

airspresso — Wed, 06 May 2026 21:46:33 +0000

> posting this sentence was part of the deal to get the compute

This 100%

New comment by airspresso in "Higher usage limits for Claude and a compute deal with SpaceX"

airspresso — Wed, 06 May 2026 21:44:06 +0000

> but given that you can actually run the models yourself on AWS Bedrock

That's not exactly how it works. Anthropic are hosting their models in AWS Bedrock as a managed service. Customers call those LLMs just like calling any other API. There's no visibility into what kind of AWS infrastructure is serving that API request.

New comment by airspresso in "Only one side will be the true successor to MS-DOS – Windows 2.x"

airspresso — Sun, 26 Apr 2026 06:42:56 +0000

Fun that it has oscillated from instant boot then to minutes-long boot a decade later back to instant boot (or resume to be fair) today.

New comment by airspresso in "Only one side will be the true successor to MS-DOS – Windows 2.x"

airspresso — Sun, 26 Apr 2026 06:41:07 +0000

I had the same confusion and closed the tab, only to discover here on HN that there's more. Open by default sounds reasonable.

New comment by airspresso in "Google releases Gemma 4 open models"

airspresso — Fri, 03 Apr 2026 06:54:10 +0000

There is a surprising amount of code needed in each of the inference frameworks (LM Studio, llama.cpp, etc) to support each new model release. For example to format the input in the right way using a chat template, to parse the output properly with the model-specific tokens the model provider decided to standardize on for their model, and more.

This particular instance was a fix to the output parsing [1] in LM Studio, described like this:

"Adds value type parsers that use <|\"|> as string delimiters instead of JSON's double quotes, and disables json-to-schema conversion for these types."

[1]: https://github.com/ggml-org/llama.cpp/pull/21326/commits/a50...

edit: formatting

New comment by airspresso in "Hypura – A storage-tier-aware LLM inference scheduler for Apple Silicon"

airspresso — Wed, 25 Mar 2026 08:22:04 +0000

I think we lost that terminology war. Open source models mean open weight. There are only a couple examples of fully open source models with open data and code, and the labs are not incentivized to go that far.

New comment by airspresso in "How BYD got EV chargers to work almost as fast as gas pumps"

airspresso — Sun, 22 Mar 2026 10:38:00 +0000

That's a good point. Charging stations benefit from being a service station too though, with amenities and a cafe etc, since people want something to do while they charge. So a gas station is a better candidate than a parking lot when decisions are made for where to place the new charging infrastructure. Lots of other factors too of course.

New comment by airspresso in "How BYD got EV chargers to work almost as fast as gas pumps"

airspresso — Sat, 21 Mar 2026 16:38:32 +0000

Yes, retooling gas stations is the way to go. Already happening in Norway where stations now show the price of kWh in addition to gas and diesel prominently on signs by the road. Charging is just a different kind of pump.

New comment by airspresso in "How BYD got EV chargers to work almost as fast as gas pumps"

airspresso — Sat, 21 Mar 2026 16:34:23 +0000

America certainly did not invent electric cars. Depending on which electric car you consider the first real one, the inventor was either French, British or German [1].

[1]: https://en.wikipedia.org/wiki/History_of_the_electric_vehicl...

New comment by airspresso in "Unsloth Studio"

airspresso — Tue, 17 Mar 2026 22:43:07 +0000

Unsloth is providing the best and most reliable libraries for finetuning LLMs. We've used it for production use-cases where I work, definitely solid.

New comment by airspresso in "How do you capture WHY engineering decisions were made, not just what?"

airspresso — Fri, 13 Mar 2026 19:55:27 +0000

Also wrestling with this challenge at the moment and curious to hear experiences from others. Even though it requires human input, the capture and the way it's updated has to get automated.

New comment by airspresso in "Speed up responses with fast mode"

airspresso — Sun, 08 Feb 2026 10:36:56 +0000

Spend time building a test harness and evaluations of whether the solution meets the requirements. Then you don't need to look at the code because those other pieces will bring the necessary guarantees and trust.

New comment by airspresso in "Speed up responses with fast mode"

airspresso — Sun, 08 Feb 2026 10:35:38 +0000

Because we all prefer it over Gemini and Codex. Anthropic knows that and needs to get as much out of it as possible while they can. Not saying the others will catch up soon. But at some point other models will be as capable as Opus and Sonnet are now, and then it's easier to let price guide the choice of provider.

New comment by airspresso in "Speed up responses with fast mode"

airspresso — Sun, 08 Feb 2026 10:31:35 +0000

Still do. Great for workloads where it's okay to bundle a bunch of requests and wait some hours (up to 24h, usually done faster) for all of them to complete.

New comment by airspresso in "Repatriate the gold': German economists advise withdrawal from US vaults"

airspresso — Sun, 25 Jan 2026 11:26:11 +0000

Thank you, was confused there for a second XD

New comment by airspresso in "Show HN: I used AI to recreate a $4000 piece of audio hardware as a plugin"

airspresso — Sun, 04 Jan 2026 20:40:07 +0000

You’re ignoring Jevons paradox. Everyone, both people and companies, will be making exponentially more software with these tools. Software that both needs to get created, debugged and updated to realize the intention of it. That’s what our time will be spent on as programmers.

New comment by airspresso in "I migrated to an almost all-EU stack and saved 500€ per year"

airspresso — Tue, 30 Dec 2025 09:54:22 +0000

Apple has a solid hardware business and massive profits from their App Store tax, they are not dependent on ad business in the way Google is. Very different incentives.

New comment by airspresso in "Kidnapped by Deutsche Bahn"

airspresso — Mon, 29 Dec 2025 18:23:55 +0000

Sounds neat but what kind of range limits would that impose on each trip? Switching from one means of transportation to another, even if both are buses, increases the total travel time significantly. Not to mention all the hassle involved for passengers.