Hacker Newsnew | past | comments | ask | show | jobs | submit | tezza's commentslogin

If you like this offbeat humour, I humbly recommend https://vole.wtf/

This site has a plethora (nice word that) of curios

They even have a sandwich themed micro-site dedicated to crisp sandwiches: https://vole.wtf/crisp-sandwich-day/


As mentioned the other day [1], a couple of HNers including me are getting LLMS to modify Amiga games from the binary.

I’ve added websocket and webrtc networking to Lotus Turbo Challenge II

and I’m in the middle of adding 8x1 player multiplayer… it originally only supported 2x2 over serial link

[1] (me, tezza) https://news.ycombinator.com/item?id=50537075

&

(Kurtz79) https://news.ycombinator.com/item?id=50545239


Same, ios iphone 17

I review LLMS, and 6.1 sol is fantastic.

What kind of stuff were you throwing at it and where was it letting you down?

So what have __I__ been doing with it, then?

I’ve got 6.1-sol to take an Amiga driving game binary and add networked car driving into a web enabled Amiga emulator… that’s interpreting machine code, Amiga architecture and then making meaningful changes.

So yeah, 6.1-sol is good.


Yeah, I think people saying "model X sucks" should really specify their use case, otherwise is really not useful to other people. I have been using it for personal projects (mostly game development) and for data analysis and automation at work, and it has been fine. I switched to Claude/Opus as my main driver after 5.5 (keeping an OpenAI Plus sub) and it has also been fine, a smidge better, maybe.

People working on large codebases, and on live, production software or harder problems might have a different experience.

Speaking as a fellow Amiga enthusiast, I had it fix a visual glitch to a game of my childhood that I initially thought it was an emulator issue but it turns out it was in the original game.

It took Sol 6.1 just 10 minutes to idenfify it, fix it and deliver a working patched image.


My experience with personal / greenfield projects has been good.

Where it falls down is on the boring stuff - writing tight PRs for features / changes in large production codebases (data area in my case). Without a lot of handholding, tendency is towards 'bolting on' new code resulting in overcomplexity & missing obvious opprtunities for simplificatation.


Thanks for sharing. I do extensive direct comparisons, and use both Anthropic and OpenAI tools in anger on large professional codebases.

I think you are correct, OpenAI tools need more handholding.

However, I think that is actually intentional from OpenAI... they stick to what you the POH ask them and deliver what you ask. They embellish less. Anthropic tools by contrast embellish a lot, and they're very good too.

Perhaps start explicitly asking the OpenAI tools to embellish or think outside the box. That may unlock that experience and results you prefer. If you already did this, would you mind sharing more detail on what effect that had (or not) for your workload?


Hitser is an awesome game... cannot recommend it highly enough.

Suitable for all ages... and if you're an expert, it's still tough

Which came first?:

Supertramp - Give A Little Bit

.

The Trammps - Disco Inferno


Put it through my standard benchmark, a six step explainer... yes, in 3D.

Very fast.

Makes mistakes. Corrects the mistakes quickly with direction.

Google Argon 4: https://share.gemini.google/T9r6tr2dDaTE

I didn't have time to make it into a full blog post yet. Here is a previous one.

https://generative-ai.review/2026/07/kimi-k3-rush-test-vs-cl...


For comparison here is the OpenAI Astra 6.

Astra 6 is significantly better than Google Argon 4 and a lot better than Claude Fable

https://generative-ai.review/2026/10/catchup-openai-astra-6-...

(edited thanks to tekacs)


Astra 6, you mean? 5.6 didn't have an Astra release, right?


Baby can be ALLERGIC to the mother’s breast milk

Baby can have unfixable latching problems (as commented elsewhere)

Breasts may not produce enough milk even with pumping

Nipples and Breasts can get infected and seriously endanger the mother


I've done a side by side comparison of the two new models across all quality levels. Versus all the previous models

https://generative-ai.review/2026/09/rush-openai-image-gen-2...

right, off to bed now


Clamiga should be treated immediately with a large dose of Clatari S.T.


I suspect some Clankertosh LLM came up with the name Clamiga.


Almost every commit in the github repository is generated by claude code, so this may be correct.


Even well meaning bodies like TFL (Transport for London) have cookie warnings that impede the actual access of the website.

Need to look up a bus time? Full screen cookie consent with accept buttons drawn OFF THE SCREEN.


They obviously aren't well-meaning if they're endlessly tracking everything you do


Sloppy, non-privacy-preserving "analytics" set up by some communications intern ≠ malice. They can mean well and still do a poor job. True privacy on the internet is notoriously hard.


Sorry, no. Code doesn't magically go from the intern's workstation to live. If the chain of incompetence is that long, then the most generous read is that they don't care


Could've been as simple as installing and configuring some off-the-shelf "analytics" and "cookie banner" plugins for their content management system. Unfortunately, the chain of incompetence is that long, because these orgs do not attract talent that understands these things.


I don't think you can handwave responsibility like that, even if your theoretical were true it's still the responsibility of the org.


More likely it was designed by some firm that put the cookie banner there because "that is just what you do in current year"


One of our sites that don't use any kind of tracking or cookies other then a site preference cookie, got so many complaints that we had to put up a cookie banner that simply says "we do not use any tracking cookies"...


Who complained what?


Users complained that we were non-compliant with EU regulations due to the missing cookie banner.

Because of the legal wording of these support tickets, the support team would often raise them to dev or legal as well, and since this is a non-revenue driving part of our business (the reason we don't track in the first place) we decided to just put up a cookie banner explaining why we don't need a cookie banner.


Yes and my "peanut allergy friendly" cookies say "may contain peanuts" because that's just what you do


Literally the point is that sites are showing the banner by default practice even when they are not tracking. You understand this!

Your kind comes into every one of these threads and says some version of "well if they weren't tracking then they'd have nothing to worry about and no need to show a banner", but that is so obviously not true to anyone who uses the web. You absolutely do not need to defend a law that is not working.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: