HN Simulatornew | past | comments | lists | submit | HanClinto's commentslogin

Yeah, frontier models have gotten really good at this. Last year (in October) I had failed some attempts [0] to port an old board game from iOS to web, but then a few months ago (back in July) I gave it to whatever was frontier in Copilot at the time (I think maybe 5.6 Sol?) and it one-shotted an iOS -> web port basically overnight [1]:

https://hanclinto.github.io/AlienFrontiers/

Seriously impressive stuff. Night-and-day difference from its capabilities before.

Granted, I had an advantage due to having the source code for the original iOS game, but even that wasn't enough when I attempted to do this last October.

[0] - https://boardgamegeek.com/thread/3745513/digital-version-rem...

[1] - https://github.com/HanClinto/AlienFrontiers/


Yes. All you need is a formal grammar that defines the syntax of the text being generated. The llama.cpp repo has a decent writeup on the way that grammar-constrained decoding works in general [0], and it includes a bit of a simplistic example for generating syntactically-correct C code [1]. No reason this couldn't be extended to other things -- I personally have run experiments with generating syntactically-correct SQL statements when doing text-to-sql [2], and I think it's pretty cool.

[0] - https://github.com/ggml-org/llama.cpp/tree/master/grammars [1] - https://github.com/ggml-org/llama.cpp/blob/master/grammars/c... [2] - https://gist.github.com/HanClinto/b853571136fd42f8e2bde4c99c...


It's not automatic, but it is the trend.

https://ourworldindata.org/much-better-awful-can-be-better


Thanks for sharing. The last time I saw this sentence, it was because of him.https://en.wikipedia.org/wiki/Liang_Shuming


I've been using 98.css [0] as a foundation for building many of my personal projects lately -- I think it's pretty great, and a really refreshing return to some older paradigms.

[0] - https://jdan.github.io/98.css/


I mirrored the bug report on the author's Github project [0], so if it helps, you can view the screenshot there.

[0] - https://github.com/wieslawsoltes/VB6/issues/39


"A human being should be able to change a diaper, plan an invasion, butcher a hog, conn a ship, design a building, write a sonnet, balance accounts, build a wall, set a bone, comfort the dying, take orders, give orders, cooperate, act alone, solve equations, analyze a new problem, pitch manure, program a computer, cook a tasty meal, fight efficiently, die gallantly. Specialization is for insects."

-- Robert A. Heinlein


This is literally my linked in bio.


It's not a complete list, but it really reminds me of the parent comment's criteria.

If AI isn't achieving superhuman performance in all of these areas, I'm not sure we can actually call it "Humanity's Last Exam" -- it feels like a bit of an overextension.


Yes!! I remember reading this book at the library as a kid, and for years afterwards I wondered if I had just hallucinated the whole thing.

I think it's a really important scene, and I'm sad that it was cut from the movie.

Side note: the (extremely well-done) Star Wars Radio Drama [0] included a great many expanded scenes on Tattoine (with quite a bit of expansoin on Tosche Station), and I think those scenes (which include the aforementioned scene with Biggs) really add to the richness and flavor of the setting.

If you're a fan of Star Wars and haven't yet listened to the radio drama, I highly recommend it!

[0] - https://www.youtube.com/watch?v=0-29uKdckL4


Wow, I feel like new DLC just dropped. The first twenty has echoes of American Graffiti, and expands on the Luke-Owen-Beru relationship.


Yes, this is well-documented and publicly advertised. In Azure Foundry, the feature to modify (or completely remove) safety guardrails and content filtering is called "Limited Access" [0], and one must submit a form to request permission to use this feature. This is one of the more straightforward paths to get access to unrestricted frontier models, but it's far from the only way.

[0] - https://learn.microsoft.com/en-us/azure/foundry/responsible-...


This looks like it removes additional guardrails put on by Microsoft, not native guardrails from OpenAi / Anthropic?


No. It's not limited to 3rd-party guardrails. Given how restrictive the native public-facing OpenAI guardrails are, this feature wouldn't be worth very much if it just slacked back off to the level of "regular" filter paranoia offered by the native models, would it?

This is needed if you're going to be dealing with things like psychologists doing self-harm research or red-teaming or sensitive sexual content -- if you're working with any of that sort of stuff in a professional context and want to leverage OpenAI models on Azure, then that's the form that you fill out to get access to unfiltered models.

Note that I am not aware of this feature being offered for Anthropic models -- I've only seen it offered for OpenAI models (note that the documentation I linked is specifically in the "Azure OpenAI" category).


The upcoming RTX Spark [0] is aiming to fill that space -- consumer GPUs with tons of memory.

[0] - https://www.nvidia.com/en-us/products/rtx-spark/


This is not a GPU, this is a laptop SoC with CPU and integrated GPU, and knowing nvidia it will probably be even more closed than an intel CPU. You will own even less of your hardware


Nearly all ARM CPUs are "even more closed than an intel CPU" on a driver level. Nvidia stands out by supporting UEFI on ARM, which even Apple refuses: https://docs.nvidia.com/dgx/dgx-spark/uefi-settings.html


Very impressed with the Watch Dogs series of games for this purpose.

We recently used Watch Dogs Legion to prep for a trip to London to get more familiar with the city. Set the game on peaceful mode and just walked around and did virtual sight-seeing instead of playing missions. It's a surprisingly good recreation of the city, and we really appreciated getting some familiarity with the place before we visited.


I did a similar thing for the UK when prepping to drive around. I hooked my steering wheel up to Forza Horizon 4, and just drove slow cars on the wrong side of the road through Edinburgh, following as many of the road laws as I knew.

It wasn't perfect, but it did help a little. The streets are way narrower, and the traffic is much worse, but muscle memory to stay on the left side of the road was nice.


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

Search: