HNHacker News
TopNewBestAskShowJobs

bgirard

2,055 karma · joined October 8, 2013

submissionscomments
bgirard··on Vercel's CEO offers to cover expenses of 'Jmail'
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.
bgirard··on Claude’s C Compiler vs. GCC
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.

bgirard··on Claude’s C Compiler vs. GCC
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]

- <Denial despite the insane rate of progress>

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.

bgirard··on Claude Composer
I like how the author shared the prompt + conversation transcripts. I wish OAI / Anthropic would do that when they share content demos.
bgirard··on GPT-5.3-Codex
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.

bgirard··on GPT-5.3-Codex
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.

bgirard··on GPT-5.3-Codex
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.
bgirard··on GPT-5.3-Codex
> 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/

bgirard··on Anthropic is Down
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.
bgirard··on Claude Code daily benchmarks for degradation tracking
> malicious

It doesn't have to be malicious. If my workflow is to send a prompt once and hopefully accept the result, then degradation matters a lot. If degradation is causing me to silently get worse code output on some of my commits it matters to me.

I care about -expected- performance when picking which model to use, not optimal benchmark performance.

bgirard··on Amazon cuts 16k jobs
Revenue per corporate employee are both ~1.5m/corp employee. I think it really comes down to how the company is managed and culture.
bgirard··on TikTok users can't upload anti-ICE videos. The company blames tech issues
When you have a personality disorder like NPD, you'll believe to your core that every criticism of you is a lie.

When you're in an abusive relationship they say intentions don't matter, only impact does. Because victims often focus on the intentions of their abuser and stay in the cycle of abuse.

Let me repeat it, intentions don't matter, only impact does.

bgirard··on Canada slashes 100% tariffs on Chinese EVs to 6%
~25 years isn't the average when you account for accidents, rust, and useful economic life of a car. We had 200+ car crashes due to weather in a single day this week in Waterloo, Ontario.
bgirard··on Opus 4.5 is not the normal AI agent experience that I have had thus far
It's not from a few prompts, you're right. But if you layer on some follow-up prompts to add proper test suits, run some QA, etc... then the quality gets better.

I predict in 2026 we're going to see agents get better at running their own QA, and also get better at not just disabling failing tests. We'll continue to see advancements that will improve quality.

bgirard··on All of Apple's services are abysmal
Yea. When my girlfriend and I travel I use Google Maps and she uses Apple Maps. And it's a running joke at this point that if we're struggling to get somewhere, she'll pull up Apple Maps and get us unstuck and bug me to switch. I think it comes down to minor UI polish that makes Apple Maps more intuitive with transit and cardinal directions but I've never done a full comparison.
bgirard··on You can now play Grand Theft Auto Vice City in the browser
Wow, crazy to see this childhood classic load and run seamlessly in my browser. Better than on my old hot wheels pc.
bgirard··on Gemini 3 Flash: Frontier intelligence built for speed
I used to think this way. But I moved to AGENTS.md. Now I use the different UI as a mental context separation. Codex is working on Feature A, Gemini on feature B, Claude on Feature C. It has become a feature.
bgirard··on Gemini 3 Flash: Frontier intelligence built for speed
Why wouldn't you switch? The cost to switch is near zero for me. Some tools have built in model selectors. Direct CLI/IDE plug-ins practically the same UI.
bgirard··on Meta's new A.I. superstars are chafing against the rest of the company
What's your definition of a novel idea? How do you measure that?

I've had a 15 year+ successful career as a SWE so far. I don't think I've had a single idea so novel that today's LLM could not have come up with it.

bgirard··on 23,746 Patients Died on Waitlists in Past Year
This includes people on a waitlist for hip operations. Are those life-threatening?
bgirard··on In New York City, congestion pricing leads to marked drop in pollution
Right. It finds an economic optimum limited to what people are willing to pay and their perceived value from that. That optimum doesn't naturally weight more complex factors like for the trade-off for the smog generated from your travel.
bgirard··on In New York City, congestion pricing leads to marked drop in pollution
That's a straw man. I didn't say personal vehicles.
bgirard··on In New York City, congestion pricing leads to marked drop in pollution
Not surprising. The real question is how do we measure the opportunity cost of these measures? Is it a net gain? You could, at the extreme, ban all motor vehicles but the opportunity cost would outweigh the benefits.
bgirard··on OpenAI declares 'code red' as Google catches up in AI race
It's a fun trope to repeat but that's not what OpenAI is doing. I get a ton of value from ChatGPT and Codex from my subscription. As long as the inference is not done at a lost this analogy doesn't hold. They're not paying me to use it. They are generating output that is very valuable to me. Much more than my subscription cost.

I've been able to help setup cross app automation for my partner's business, remodel my house, plan a trip of Japan and assist with the cultural barrier, vibe code apps, technical support and so much more.

bgirard··on DoGE "cut muscle, not fat"; 26K experts rehired after brutal cuts
This is one of many frequent reminders: In some environments, how you brand and market your work (Mush with a chainsaw cutting spending comes to mind) is often more important than the work you do. Most wont bother to look at the actual results of your work.
bgirard··on Michael Burry a.k.a. "Big Short",discloses $1.1B bet against Nvidia&Palantir
Is there anything more concrete than that? Large wins on their own aren't meaningful if they aren't good risk adjusted trades or repeatable. I've made big wins but I don't consider myself a good trader.
bgirard··on Michael Burry a.k.a. "Big Short",discloses $1.1B bet against Nvidia&Palantir
I'm legitimately curious what his overall performance is. Are those just cherry picked trades?
bgirard··on Using AI to negotiate a $195k hospital bill down to $33k
> Another was a code that was inpatient only and because it was an emergency he had never been admitted.

The threads says this was 4 hours of work and they billed for things that weren't even used.

bgirard··on Using AI to negotiate a $195k hospital bill down to $33k
I used AI to deal with customer support when a company tried to assign me the rental contract from the previous owner. ChatGPT correctly quoted the relevant Ontario Consumer Protection Act sections that applied. I just did quick verifications to make sure it wasn't hallucinating (it didn't). They tried to push back, but I had ChatGPT write a few responses standing first and they relented after a few exchanges.
bgirard··on [dead]
That makes sense. But then the idea of a simultaneous failure preventing, say AWS and GCP/Azure, from restarting due to accidental circular dependencies in the init sequence needed to reboot the two competing cloud infrastructure is interesting.
← PreviousPage 2 of 14Next →