Hacker News: lreeves

New comment by lreeves in "Epic Games to cut more than 1k jobs as Fortnite usage falls"

lreeves — Tue, 24 Mar 2026 18:56:19 +0000

I bought Battlefield 2 and it's DLC and one of the earlier Dirt games on EA Origin and it was an absolute nightmare. My games and the DLC would constantly not be authed in my account and I still have like dozens of support threads in my old mailbox trying to get things working.

At the same time Steam had polished a lot of the rough edges like this for their catalog and other publishers so there's really no excuse. I've never had to open support tickets with any other storefront because the DLC map pack for a game would stop loading while the base game kept working.

New comment by lreeves in "Something is afoot in the land of Qwen"

lreeves — Wed, 04 Mar 2026 19:54:29 +0000

In my experience Qwen3.5/Qwen3-Coder-Next perform best in their own harness, Qwen-Code. You can also crib the system prompt and tool definitions from there though. Though caveat, despite the Qwen models being the state of the art for local models they are like a year behind anything you can pay for commercially so asking for it to build a new app from scratch might be a bit much.

New comment by lreeves in "New iPad Air, powered by M4"

lreeves — Mon, 02 Mar 2026 18:26:06 +0000

Could not agree more, it's wild my AppleTVs now ask for which profile is using it but the iPad still hasn't gotten this.

New comment by lreeves in "US businesses and consumers pay 90% of tariff costs, New York Fed says"

lreeves — Thu, 12 Feb 2026 17:34:16 +0000

I mean no shit though? People calmly said this in Trump's first term where he (unsuccessfully) first tried to go tariff crazy. What does it add though? Nobody is freaking out saying "all tariffs are bad", they're saying "blanket tariffs for no/the stupidest reasons possible are bad".

New comment by lreeves in "Qwen3-VL can scan two-hour videos and pinpoint nearly every detail"

lreeves — Wed, 03 Dec 2025 12:41:38 +0000

I run the larger version of it on a Threadripper with 512GB RAM and a 32GB GPU for the non-expert layers and context, using llama.cpp. Performs great, however god forbid you try to get that much memory these days.

New comment by lreeves in "Ask HN: Who uses open LLMs and coding assistants locally? Share setup and laptop"

lreeves — Fri, 31 Oct 2025 15:13:58 +0000

I sometimes still code with a local LLM but can't imagine doing it on a laptop. I have a server that has GPUs and runs llama.cpp behind llama-swap (letting me switch between models quickly). The best local coding setup I've been able to do so far is using Aider with gpt-oss-120b.

I guess you could get a Ryzen AI Max+ with 128GB RAM to try and do that locally but non-nVidia hardware is incredibly slow for coding usage since the prompts become very large and take exponentially longer but gpt-oss is a sparse model so maybe it won't be that bad.

Also just to point it out, if you use OpenRouter with things like Aider or roocode or whatever you can also flag your account to only use providers with a zero-data retention policy if you are truly concerned about anyone training on your source code. GPT5 and Claude are infinitely better, faster and cheaper than anything I can do locally and I have a monster setup.

New comment by lreeves in "What if tariffs?"

lreeves — Sun, 26 Oct 2025 14:08:57 +0000

It's not practical when Trump sees a TV ad that enrages him and then cancels all negotiations, how are Canadian leaders supposed to proceed? There's no good faith whatsoever from him.

New comment by lreeves in "What if tariffs?"

lreeves — Sun, 26 Oct 2025 12:35:10 +0000

Exactly right. There are trade deals forming between countries that in unprecedented ways to avoid dealing with the constantly changing tariffs while one country says they'll take their ball and play alone.

New comment by lreeves in "What if tariffs?"

lreeves — Sun, 26 Oct 2025 12:21:12 +0000

In a sense you can think of it that way, as a Canadian we counter-tariff the US and that can be considered punishing us; however the US is only one country and it encouraged more free trade with every other one of our trading partners so in a game theory sense it's affecting Canadian trade negatively with one country and affecting US trade negatively with you know.. every country.

New comment by lreeves in "Doctorow: American tech cartels use apps to break the law"

lreeves — Wed, 08 Oct 2025 20:54:55 +0000

On iOS you can deny an app cellular data access which accomplishes this, as long as you don't launch it on Wifi. But yes I too wish I could deny apps internet access completely.

New comment by lreeves in "Syncthing 2.0 Released"

lreeves — Tue, 12 Aug 2025 16:44:51 +0000

Syncthing-fork is in the Play Store and works fine for me.

New comment by lreeves in "Tools: Code Is All You Need"

lreeves — Thu, 03 Jul 2025 14:43:12 +0000

The commands aren't the special sauce, it's the analytical capabilities of the LLM to view the outputs of all those commands and correlate data or whatever. You could accomplish the same by prefilling a gigantic context window with all the logs but when the commands are presented ahead of time the LLM can "decide" which one to run based on what it needs to do.

New comment by lreeves in "Ukraine destroys more than 40 military aircraft in drone attack deep in Russia"

lreeves — Mon, 02 Jun 2025 00:56:53 +0000

Electronic warfare is pretty effective against drones that are using radio waves for their communication. Earlier in the war you could see a lot of drone footage that would become washed out with static as they got closer to tanks so it's much more reliable to use spools of fiber.

New comment by lreeves in "AI Is Like a Crappy Consultant"

lreeves — Tue, 13 May 2025 13:51:52 +0000

I use o3 with architect mode for larger changes and refactors in a project. It seems very suited to the two-pass system where the (more expensive) "reasoning" LLM tells the secondary LLM all the changes.

For most of the day I use Gemini Pro 2.5 in non-architect mode (or Sonnet when Gemini is too slow) and never really run into the issue of it making the wrong changes.

I suspect the biggest trick I know is being completely on top of the context for the LLM. I am frequently using /reset after a change and re-adding only relevant files, or allowing it to suggest relevant files using the repo-map. After each successful change if I'm working on a different area of the app I then /reset. This also purges the current chat history so the LLM doesn't have all kinds of unrelated context.

New comment by lreeves in "AI Is Like a Crappy Consultant"

lreeves — Tue, 13 May 2025 13:48:58 +0000

Aider has a configuration for each supported LLM to define the best diff format for each; so for certain ones they're best at diff format, Gemini is best at a fenced-diff format, Qwen3 is best at whole file editing, etc. Aider itself examines the diff and re-runs the request when the request when the response doesn't adhere to the corresponding diff format.

Edit: Also the Aider leaderboards show the success rate for diff adherence separately, it's quite useful [1]

1 - https://aider.chat/docs/leaderboards/

New comment by lreeves in "AI Is Like a Crappy Consultant"

lreeves — Tue, 13 May 2025 13:47:51 +0000

Yeah I should have clarified that, there are more advanced IDE integrations now but I meant Cursor, Copilot etc.

New comment by lreeves in "AI Is Like a Crappy Consultant"

lreeves — Tue, 13 May 2025 13:26:58 +0000

Using Aider with o3 in architect mode, with Gemini or with Sonnet (in that order) is light years ahead of any of the IDE AI integrations. I highly recommend anyone who's interested in AI coding to use Aider with paid models. It is a night and day difference.

New comment by lreeves in "How to vibe code for free: Running Qwen3 on your Mac, using MLX"

lreeves — Thu, 01 May 2025 14:09:46 +0000

The new AMD chips in the Framework laptops would be a good candidate and I think you can get 96GB RAM in them. Also if the LLM software is idle (like llama.cpp or ollama) there is negligible extra power consumption.

New comment by lreeves in "Show HN: Lunon – Instant model switching across LLMs"

lreeves — Fri, 11 Apr 2025 22:51:58 +0000

I considered being polite but the fact OP had already chosen to not answer these actual questions makes me question why anyone would trust this site with their payment data or even personal data.

New comment by lreeves in "Show HN: Lunon – Instant model switching across LLMs"

lreeves — Fri, 11 Apr 2025 21:43:23 +0000

This seems super amateur and your privacy policy sucks compared to OpenRouter. Also it's weird you have time to respond to trivial questions but not questions like "why would I use this over the entrenched leader in this space".

No docs or info without signing up, confusing Grok and Groq, and claiming you have access to o4 models which haven't been released makes this look like an incredibly unserious offering.