Hacker News: bgirard

New comment by bgirard in "The AI revolution in math has arrived"

bgirard — Tue, 14 Apr 2026 04:24:37 +0000

Last week I got together with my math alumni friend. We cracked some beers, we chatted with voice mode ChatGPT and toyed around with Collatz Conjecture and we sent some prompt to a coding agent to build visualizations and simulation. It was a lot of fun directing these agents while we bounced off ideas and the models could explore them.

I think with the right problem and the right agentic loop it’s clear to me improvements will speed up.

New comment by bgirard in "Ask HN: Any interesting niche hobbies?"

bgirard — Wed, 08 Apr 2026 19:59:18 +0000

I've been using Codex to build a repo that pulls down astronomical datasets and runs simulation to try to find explanation for the hubble tension. Having an agent to do the tedious bits and also having an LLM to bounce ideas has tough me so much about astronomy. I don't have serious hopes of finding anything new and novel but it's still a lot of fun.

New comment by bgirard in "Binary obfuscation used in AAA Games"

bgirard — Wed, 08 Apr 2026 13:22:02 +0000

I’ve noticed that LLMs can effortlessly read minified JS. How does it do with obfuscated binary code? I wonder if the days of obfuscation are numbered when the tedious job of de-obfuscation can be automated.

New comment by bgirard in "Colorado House passes bill to limit surveillance pricing and wage setting"

bgirard — Sat, 28 Mar 2026 06:28:56 +0000

Subpoenas and whistleblowing are pretty good tools.

New comment by bgirard in "Walmart: ChatGPT checkout converted 3x worse than website"

bgirard — Mon, 23 Mar 2026 15:09:33 +0000

I think they're thinking about this wrong.

I get all my groceries deliver to my doorstep via Walmart delivery pass. The thing I'm really missing is having AI curate meal planning to my family's preferences. I already feed ChatGPT my family' preferences (e.g. Kid A doesn't eat X Y Z and liked meal A B C, kid B likes ...) and ChatGPT is helping me build meal plans. With my preferences we can quickly nail down a meal plan for the week.

The slowest part of my meal planning is going through Walmart's slow site where each page load is 2-3 seconds and it takes several page load per item. Once it can translate my meal plan into a grocery checkout from Walmart I'm all set.

New comment by bgirard in "Show HN: Claude Code skills that build complete Godot games"

bgirard — Mon, 16 Mar 2026 22:13:53 +0000

I'd love to see the results of that. I think calling a single prompt iteration lifeless misses the point. It's like looking at a game that has had a few hours of development and saying it's bad. Games need iterations. Seeing your results as the first iteration is impressive. I can see follow-up prompts and custom tweaking get really good results!

Last summer I built a factorio-like automation game with older models and over time the game really started to take life.

New comment by bgirard in "Blood test boosts Alzheimer's diagnosis accuracy to 94.5%, clinical study shows"

bgirard — Tue, 24 Feb 2026 03:55:47 +0000

It's very useful to understand what you're struggling from even if it's not curable. It explains your symptoms, your experience and help you understand what you're going through. Understanding that you're suffering from something incurable is also helpful in not looking for other ineffective methods to cure a mysterious illness.

New comment by bgirard in "Nvidia and OpenAI abandon unfinished $100B deal in favour of $30B investment"

bgirard — Fri, 20 Feb 2026 17:19:10 +0000

> SpaceX has deorbiting assets on top of depreciating ones

The deorbiting part is redundant. Their satellite are just that, a depreciating asset. Their lifetime seem to be 5 to 7 years. The important claim is if the total cost, including the launch, can be recuperate over that lifetime or not.

New comment by bgirard in "Gemini 3 Deep Think"

bgirard — Fri, 13 Feb 2026 20:48:54 +0000

I've gotten pretty good results by prompting "What did you struggle on? Please update the instructions in " and "Here's your conversation , please see what you struggled with and update ".

It's hit or miss, but I've been able to have it self improve on prompts. It can spot mistakes and retain things that didn't work. Similar to how I learned games like Balatro. Playing Balatro blind, you wouldn't know which jokers are coming and have synergy together, or that X strategy is hard to pull off, or that you can retain a card to block it from appearing in shops.

If the LLM can self discover that, and build prompt files that gradually allow it to win at the highest stake, that's an interesting result. And I'd love to know which models do best at that.

New comment by bgirard in "Gemini 3 Deep Think"

bgirard — Fri, 13 Feb 2026 15:53:11 +0000

Are there benchmarks if we allow the LLM to practice and study the game?

New comment by bgirard in "The US is flirting with its first-ever population decline"

bgirard — Tue, 10 Feb 2026 20:10:55 +0000

Your experience sounds exactly like mine. My son is very autistic as well. I've had to cut off friends with families because either their didn't understand meltdown and were incredibly judgy because they were blaming my parenting for his ASD meltdowns, or others because my autistic son was a "bad influence". God forbid their (later diagnosed) kid have some exposure to a child with different neurodiversities.

That's not even going into my traumatic health care experience to getting my son help when he needed it.

So now I have all the hardships of raising a family, and I'm restricted friendship within the small ND accepting community of my area. So my support network is incredibly small and I barely get any support. It sucks.

Reading the responses to your story that are nitpicking it over your daycare experience is a perfect representation of the problems that families face.

New comment by bgirard in "Vercel's CEO offers to cover expenses of 'Jmail'"

bgirard — Tue, 10 Feb 2026 15:51:29 +0000

That's a good question. As someone bootstraping a few projects on Vercel this post has me looking over at the pricing sheet more closely.

New comment by bgirard in "Claude’s C Compiler vs. GCC"

bgirard — Mon, 09 Feb 2026 08:09:36 +0000

That's true and I fully agree. I don't think LLMs' progress in writing a toy C compiler diminishes the achievements that the GCC project did.

But also we've just witnessed LLMs go from being a glorified line auto-complete tool to it writing a C compiler in ~3 years. And I think that's something. And noting how we keep moving the goal post.

New comment by bgirard in "Claude’s C Compiler vs. GCC"

bgirard — Mon, 09 Feb 2026 06:25:42 +0000

This to me sounds a lot like the SpaceX conversation:

- Ohh look it can [write small function / do a small rocket hop] but it can't [ write a compiler / get to orbit]!

- Ohh look it can [write a toy compiler / get to orbit] but it can't [compile linux / be reusable]

- Ohh look it can [compile linux / get reusable orbital rocket] but it can't [build a compiler that rivals GCC / turn the rockets around fast enough]

There's no reason to keep building this compiler just to prove this point. But I bet it would catch up real fast to GCC with a fraction of the resources if it was guided by a few compiler engineers in the loop.

We're going to see a lot of disruption come from AI assisted development.

New comment by bgirard in "Claude Composer"

bgirard — Fri, 06 Feb 2026 21:41:08 +0000

I like how the author shared the prompt + conversation transcripts. I wish OAI / Anthropic would do that when they share content demos.

New comment by bgirard in "GPT-5.3-Codex"

bgirard — Fri, 06 Feb 2026 05:38:12 +0000

About ~$300: $200 for Claude max subscription $20 for Vercel $20 for Codex $20 for Meshy

I think these days the $200 Max subscription wouldn't be needed. I bet with these latest models you can make due with mixing two $20/mo subscriptions.

Real time was 2 weeks of watching the agents while watching TV and playing games, waiting for limit resets, etc... Very little decided focused time.

New comment by bgirard in "GPT-5.3-Codex"

bgirard — Thu, 05 Feb 2026 20:03:00 +0000

Thank you. There's a demo save to get the full feel of it quickly. There's also a 2D-ASCII and 3D render you can hotswap between. The 3D models are generated with Meshy. The entire game is 'AI slop'. I intentionally did no code reviews to see where that would get me. Some prompts were very specific but other prompts were just 'add a research of your choice'.

This was built using old versions of Codex, Gemini and Claude. I'll probably work on it more soon to try the latest models.

New comment by bgirard in "GPT-5.3-Codex"

bgirard — Thu, 05 Feb 2026 19:58:31 +0000

Doesn't feel like a useful data point without more context. For some hard bugs I'd be thrilled to wait 30 minutes for a fix, for a trivial CSS fix not so much. I've spent weeks+ of my career fix single bugs. Context is everything.

New comment by bgirard in "GPT-5.3-Codex"

bgirard — Thu, 05 Feb 2026 19:49:40 +0000

> Using the develop web game skill and preselected, generic follow-up prompts like "fix the bug" or "improve the game", GPT‑5.3-Codex iterated on the games autonomously over millions of tokens.

I wish they would share the full conversation, token counts and more. I'd like to have a better sense of how they normalize these comparisons across version. Is this a 3-prompt 10m token game? a 30-prompt 100m token game? Are both models using similar prompts/token counts?

I vibe coded a small factorio web clone [1] that got pretty far using the models from last summer. I'd love to compare against this.

[1] https://factory-gpt.vercel.app/

New comment by bgirard in "Anthropic is Down"

bgirard — Tue, 03 Feb 2026 17:24:32 +0000

The switching cost is so low that I find it's easier and better value to have two $20/mo subscription from different providers than a $200/mo subscription with the frontier model of the month. Reliability and model diversity are a bonus.