HNHacker News
TopNewBestAskShowJobs

mcintyre1994

6,336 karma · joined January 30, 2013

submissionscomments
mcintyre1994··on Mistral's Shieldstral: 3B open-weights model for multimodal moderation
> filter for “offensive” content, and boost it or collate it into a newsletter/email blast for people of culture.

I think that's the main service that xAI provide for X.

mcintyre1994··on Apple is getting this wrong
I don’t really understand this, Apple obviously wants to force discovery and publishing stuff seems like it’d just widen the net there.
mcintyre1994··on Octane – React's programming model, compiled
Their llms.txt spells it all out: https://octanejs.dev/llms.txt

But it doesn't have the repeating yourself/over-emphasising that you sometimes see in LLM instructions when someone is trying to fight the model's default assumptions

mcintyre1994··on Octane – React’s programming model, compiled
Which is ironic because the author works at OpenAI!
mcintyre1994··on Adding Go's Defer to the TypeScript Compiler
JS has the using keyword for this: https://developer.mozilla.org/en-US/docs/Web/JavaScript/Refe...
mcintyre1994··on Seedance 2.5
This seems extraordinarily good to me, compared to what I've seen before. Their washing machine advert example seems like it's as good as anything else on social media. I'm shocked by the quality and the coherence they're able to maintain, I assume it's really good at using those reference images they mention in their prompts. I think the only one that's noticeably bad is the concert hall, where the first few seconds show almost empty stalls and then toward the end it shows a full audience, and that audience also looks a bit off.
mcintyre1994··on Stacked PRs are now live on GitHub
The issue you’d have then is the CI might not be green after the 4th commit but it is after the 5th. A single PR will hide that, so you’d need a way to run the CI on the subset of commits you want to extract. It’s also much easier to isolate those blocking comments on the 5th commit if it’s in its own PR and not mixed with all the review comments on the other ones.

I don’t really see it as diverging much from the underlying git tool TBH - it’s still just git branches pointing at each other.

mcintyre1994··on Agent Skill to Force Docs in ASD-STE100 Simplified Technical English
They acknowledge this, but I really dislike whatever style they're using for the readme:

> Yes, this README breaks half of them. Marketing is explicitly out of STE scope. The skill knows that and stays in the docs.

> Where it refuses to go: marketing copy, blog voice, brand writing. Flat on purpose.

(Each sentence there has an emoji that HN cuts out)

mcintyre1994··on Opus 5 is currently #1 on Artificial Analysis Intelligence Leaderboard
I don’t know that individuals can really be expected to use a new model enough to develop a proper opinion though. If I try a new model, and it doesn’t seem as good as the one I’m using, I’m just going to stop using it. That’s not enough data to give anyone else a useful view on it, but it’s enough for me to make my mind up.

Especially because I’m probably trying it at work, and I can’t really justify using the company’s enterprise plan to develop my understanding of a model that I don’t think is going to be the one I use for my work.

mcintyre1994··on Nvidia, Microsoft, Meta warn against overregulating open-weight models
I suspect that whatever Musk has agreed to spend on the midterms in exchange for those sweetheart deals the SpaceX IPO got will make that look absolutely comical, but we’ll see.
mcintyre1994··on Launching Health in ChatGPT to US Users
I find this weird too! When you say something that prompts them that you’re talking about the current time, they’ll go and fetch it and use that to understand time frames which makes sense. But if you’ve been talking about something tomorrow, and then tomorrow comes and you go back to that chat, they don’t understand that now it’s today/right now.
mcintyre1994··on Stripe and Advent have made a joint offer to acquire PayPal – sources
> Let's jump out of the middle of checkout and go to a page which looks like they're trying to phish your bank account to continue, and by the way, you can just skip it.

Any idea why they implemented it like that?

In the UK you either get a text from your bank with transaction details and a code to approve it. Or the better ones you just open their app and tap approve.

mcintyre1994··on Show HN: Clawk – Give coding agents a disposable Linux VM, not your laptop
Fly.io’s sprites.dev is a similar idea but on their hardware and you get a public/private domain to run a server too, I’ve found it pretty good.
mcintyre1994··on Apple sues OpenAI, accuses ex-employees of stealing trade secrets
Same, the main network I see bots on is X and there’s a really obvious bot attack on them there since the fight with the DoD.
mcintyre1994··on Is The Economist Always Wrong?
> We asked it [GPT-5.5] to assess whether each leader had made a falsifiable claim about the future as part of its main thesis. About 1,400 did. We then extracted those predictions, and asked the AI to mark out of ten both how contrarian the leader’s outlook was at the time and how accurate the prediction turned out to be. We ran those queries several times and took an average.

I understand why it wouldn’t be feasible for a human to do this, but I’m quite sceptical about an AI assessing how accurate predictions turned out to be/how contrarian they were at the time. It seems like that would depend a lot on what sources it chooses, be liable to hallucination or getting poisoned by bad sources, etc. They don’t mention whether they used independent queries for each prediction either, or whether it was doing multiple sequentially.

Given that LLMs can’t really distinguish prompt from instructions etc, I’m sceptical that they can reason particularly well about things like how contrarian a view was at a particular point in time.

mcintyre1994··on Superpowers 6
I think I’ve mostly found superpowers helpful, especially for TDD. It’s cool from this blog (and their GitHub) that they’ve verified it in various ways too. One issue is that I’ll sometimes see it wanting to write a whole doc for a follow on feature with a similar structure and have to tell it to just use the last one again.

The most annoying thing is that it always pauses before implementing to ask if I want it to use Subagents (which it always recommends) or not.

mcintyre1994··on Claude's AskUserQuestion: "No response after 60s – continued without an answer"
I’ve definitely sometimes had situations where this would make sense, and also where Claude asks a question not using this tool and it’d make sense to just keep going.

But this does seem like the wrong default to me. I’ve found if I tell Claude I’m AFK and just keep going, it’ll do that reliably. And it’s good at debriefing me afterward on what decisions it made that it would have asked me about.

mcintyre1994··on Rocketlab acquires Iridium
I have a really dumb prediction that at some point he’ll name one of the public companies X, presumably either SpaceX or a merged company. The dumbest people in the world would say he’s turned Twitter into a $2tn company and he’d find that hilarious.
mcintyre1994··on Tidal AI Policy
Assuming you already pay for 'verification' on X, you just need to get more followers/impressions and then you'll start being paid based on your impressions. If you know/follow anyone with the 'verified' checkmark who has a lot of followers, they'll be getting paid for impressions.
mcintyre1994··on GLM 5.2 beats Claude in our benchmarks
It’d be restrictions on Americans and American companies, and probably also pressure on America’s allies.
mcintyre1994··on A way to exclude sensitive files issue still open for OpenAI Codex
OnePassword can do something like this where you put references to a path there instead of the key material, and then you wrap the invoke command with their CLI and it replaces them. So your local env file never has anything sensitive. A malicious agent could still exfiltrate if you give it access to debug tools on the running code though.
mcintyre1994··on U.S. government will decide who gets to use GPT-5.6
It's quite funny to think about the reaction this would be getting from people like David Sacks, if it was literally anybody except Trump.
mcintyre1994··on Apple to skip high-end M6 Mac chips in favor of AI-focused M7 line
Companies are spending even more than that if they’re using the $200 subscription worth of tokens on the enterprise plans too.
mcintyre1994··on Anthropic says Alibaba illicitly extracted Claude AI model capabilities
Supposedly the details of the ‘jailbreak’ are that you give it insecure code and say “fix this code”, and it does, and then you ask it for test scripts and that’s effectively an exploit against the unfixed code.

If true then I have no idea how anyone’s going to release a useful model that doesn’t have the same jailbreak. https://www.theregister.com/security/2026/06/15/feds-freaked...

mcintyre1994··on Crypto in 2026: Oh, This Is the Bad Place
I doubt there's enough evidence to make that claim yet, but I think 24/7 trading could do that.
mcintyre1994··on Crypto in 2026: Oh, This Is the Bad Place
I do agree that there's a huge amount of fraud and scams, and obviously that's only got worse since the President of the US started being part of that ecosystem.

But at the same time there is also finally real finance happening on-chain too. Backpack launched a SpaceX token at IPO that can be moved between on-chain and your brokerage. I think Coinbase announced their on-chain equity offering will have the same capability. Just yesterday Bailie Gifford launched a tokenised fund where the actual register of record is on-chain. I still think crypto has significant potential as financial rails, and that does seem to be being explored by real financial players now too.

mcintyre1994··on GLM 5.2 vs. Opus
I guess the idea is that you probably can, or will be able to, find a host that you trust at least as much as you trust Anthropic.
mcintyre1994··on When I reject AI code even if it works
I find the same. Someone posted this benchmark here: https://petergpt.github.io/bullshit-benchmark/viewer/index.v...

It measures whether models push back on bullshit prompts or just go along with it, and Claude models are all the top performers.

mcintyre1994··on Cell-based architecture for resilient payment systems
A few years ago someone kept signing up for loads of bank accounts/credit cards in my name, with my address. I’m not sure what the point of it was. But while everyone else happily sent cards and stacks of welcome paperwork to me, Amex were the only one that contacted me and told me they’d detected something weird in the signup. They gave me some helpful advice to resolve that situation too.
mcintyre1994··on SpaceX to buy Cursor for $60B
I feel like it has to eventually become X. Just because he’d find it funny for the stupidest people in the world to post about how he’s turned Twitter into a $2t or whatever company.
← PreviousPage 3 of 34Next →