Hacker News: fireant

New comment by fireant in "Real-SWE: Benchmarking AI models on private, real-world, enterprise codebases"

fireant — Sun, 13 Sep 2026 04:14:38 +0000

You cannot introspect model training by prompting the model. Whatever answer it hallucinated on your query "where do you know that from" has almost certainly very low bearing on reality.

New comment by fireant in "I-have-ADHD: A skill to stop coding agents from burying the answer"

fireant — Thu, 10 Sep 2026 04:44:48 +0000

Personally I've found the opposite useful - I mostly use OAI models with OMP harness and I have a rule instructing it to summarize if any work was omitted or if it made any surprising changes. Sometimes the agent will forget to do some piece of work or invent a new bizarre way of doing things, but quite often it is able to self reflect on this at the end of the session.

New comment by fireant in "Dwarf Fortress is getting the mother of all magic updates"

fireant — Wed, 02 Sep 2026 04:46:50 +0000

The new GUI is... not great. But the UX old UI was downright awful. There were like 5 different paradigms how to use individual screens, not just layouts, completely different ways to navigate and interact with controls.

After couple tens of hours you memorized the arcane keyboard invocations to do what you wanted, but it never felt intuitive.

New comment by fireant in "Mechanical Turk shutting down September 30"

fireant — Thu, 27 Aug 2026 10:50:19 +0000

Some doctors are known to be a hip shooters making snap decisions, but is 30s really enough time for any kind of "expertise" from a real human?

New comment by fireant in "OpenAI: GPT 5.6 Sol price reduction (until at least Nov 21)"

fireant — Mon, 24 Aug 2026 18:40:39 +0000

My understanding is that most OpenAI users are on a free tier. Secondary effect of this is that OpenAI free tier model capability (assuming Luna) is what what most users associate with frontier AI capability giving somewhat warped view to many people.

New comment by fireant in "Felony Bench"

fireant — Sat, 22 Aug 2026 05:28:00 +0000

I'm glad that we no longer live in a world where "bull goring" is such a common occurrence that it needs to be codified into law.

New comment by fireant in "Code-native generation of highly programmable 3D assets (2026)"

fireant — Wed, 19 Aug 2026 07:34:44 +0000

If all of these meshes use the same shader (which they do, its just PBR) they can be all drawn with a single multidraw indirect call.

Edit: thinking more about it, since the objects are small they could be rendered with mesh shaders achieving further perf improvements. Also fine grained decomposition helps with culling. IMO the real problem is that rendering in game engines does not map well to modern hardware. Unreal engine went full software rendering with nanite replacing the whole pipeline (which brings significant drawbacks) and everyone else is using graphics with techniques 15 years out of date which leads to this mismatch between what is possible with hardware and what is good practice with game engines.

New comment by fireant in "Linux 7.3 improves performance when running out of vRAM"

fireant — Wed, 19 Aug 2026 05:47:43 +0000

You can disable the win11 update nagging inside local group policy editor.

New comment by fireant in "GPT-5.6 Sol Pricing Cut by 50% on OpenRouter"

fireant — Wed, 19 Aug 2026 05:26:15 +0000

There are several tiers to these services, some are selling real us phone number verifications at about 0.5usd/text while others are selling virtual phone number verifications at much cheaper. From some limited experience with the former, there is rarely if ever any problems with rejections.

New comment by fireant in "How Compaction Works in Pi"

fireant — Fri, 14 Aug 2026 19:42:04 +0000

You can set different compaction strategy, currently "Summarize in place and keep the current session", "Generate handoff and continue in a new session", "Drop heavy content in place, recover via artifact", Snapcompact as mentioned

New comment by fireant in "Accelerating GPT-5.6 Sol Ultrafast"

fireant — Fri, 14 Aug 2026 09:14:01 +0000

I think that we are starting to see that API inference prices for US labs are excessive and subscription prices are closer to real costs so 200/m can be realistic longer term.

New comment by fireant in "Accelerating GPT-5.6 Sol Ultrafast"

fireant — Fri, 14 Aug 2026 05:25:14 +0000

I've been measuring waiting for tool calls/waiting for model response in my OMP with Sol 5.6 and usually it's 85%-95% of time spent waiting for model to respond, so 14x speedup in model perf would still be very significant. YMMV but speeding up tests and improving DX is somewhat well understood.

New comment by fireant in "OpenAI’s head of ethics leaves less than a year after joining"

fireant — Thu, 13 Aug 2026 12:19:43 +0000

The ethics group isn't at OpenAI to make it ethical, it is there so that it can be pointed to outsiders such as press with words "we take ethics very seriously". It is very similar in function to security group (which should be responsibility of everyone) and DEI group. Ethics head quiting has about the same importance as head of PR quiting.

New comment by fireant in "Tl;dv: Over 180k meetings left wide open"

fireant — Tue, 11 Aug 2026 04:29:04 +0000

I'm very torn on these laws. On one hand I understand the purpose, but on the other recoding phone calls and meetings is immensely useful. On Android I had an option to automatically record phone calls and it has saved my ass many times, while on IOS it's not possible at all.

New comment by fireant in "Windows 11's built-in Weather app wastes more than 1 GB of RAM"

fireant — Mon, 10 Aug 2026 04:41:23 +0000

Chromium is actually fairly efficient when shared across multiple applications. If the webview2, which is probably what the weather app uses, would not create a whole browser per application but rather just the renderer process and the rest shared system wide it would be a couple hundred megs at most.

New comment by fireant in "Windows 11's built-in Weather app wastes more than 1 GB of RAM"

fireant — Mon, 10 Aug 2026 04:30:00 +0000

Separate Renderer and GPU Process is just typical webview2/electron

New comment by fireant in "Zed DeltaDB"

fireant — Thu, 06 Aug 2026 10:52:26 +0000

Using OMP through ACP inside Zed is drastically worse experience than just running OMP inside Zed terminal. The ACP UI is dreadful and I had bunch of crashes even for first party Codex support.

New comment by fireant in "Opus 5 is currently #1 on Artificial Analysis Intelligence Leaderboard"

fireant — Sun, 26 Jul 2026 05:20:11 +0000

That index really needs harder tasks so that it's not just a benchmark of what model is cheapest

New comment by fireant in "What's the deal with all the random weekly quota resets for agents lately?"

fireant — Sun, 19 Jul 2026 08:12:53 +0000

Are you saying that because they are ending subsidies, they are giving more subsidies?

New comment by fireant in "Chatto is now open source"

fireant — Thu, 09 Jul 2026 01:42:08 +0000

Personally I've always found it funny that the widely used work software is called Slack which is very close to slacking (not working hard enough).