Hacker News: toxicFork

New comment by toxicFork in "Show HN: Get notified when sites update their terms of service"

toxicFork — Wed, 09 Aug 2023 18:39:44 +0000

The service can show a diff, pass it through an LLM into a bite sized email

New comment by toxicFork in "Show HN: PC Builder AI"

toxicFork — Wed, 09 Aug 2023 17:49:55 +0000

That's a security measure to prevent AI building other AI.

New comment by toxicFork in "Unity Weta Tools"

toxicFork — Wed, 09 Aug 2023 17:07:21 +0000

I confirm that timoni does work at Unity, I'd trust their word.

New comment by toxicFork in "Friendly Captcha – GDPR-Compliant Bot Protection"

toxicFork — Tue, 08 Aug 2023 18:35:24 +0000

> Friendly Captcha generates a unique crypto puzzle for each visitor. As soon as the user starts filling a form it starts getting solved automatically. Solving it will usually take a few seconds. By the time the user is ready to submit, the puzzle is probably already solved.

What makes this NOT work on a bot machine?

New comment by toxicFork in "Show HN: ChainForge, a visual tool for prompt engineering and LLM evaluation"

toxicFork — Mon, 07 Aug 2023 22:57:10 +0000

AFAIK it's finding out what prompts to use for what LLM to get the answer your want

E.g. this

> Compare response quality across prompt permutations, across models, and across model settings to choose the best prompt and model for your use case.

New comment by toxicFork in "FreeWilly 1 and 2, two new open-access LLMs"

toxicFork — Sat, 22 Jul 2023 08:18:15 +0000

Allegedly, GPT4 itself is an ensemble of models anyway, right?

New comment by toxicFork in "Forget Spotify for news – let's fix the real problem (2017)"

toxicFork — Sun, 16 Jul 2023 20:41:28 +0000

This sounds a lot like the Brave browser model. I am unsure how well the company is doing, and how well the users who opted in to receive BATs are doing, though.

New comment by toxicFork in "GPT-Prompt-Engineer"

toxicFork — Tue, 11 Jul 2023 12:00:55 +0000

Well, you could keep everything else in the project and put yourself or a human as the "does this result feel better than the other one" decision maker

New comment by toxicFork in "GPT-Prompt-Engineer"

toxicFork — Tue, 11 Jul 2023 11:52:43 +0000

A neat feature would be able to switch between autoranking and manual ranking.

New comment by toxicFork in "GPT-4 details leaked?"

toxicFork — Tue, 11 Jul 2023 07:31:03 +0000

The thing, dude, the thing, is over!

New comment by toxicFork in "Threads.net"

toxicFork — Thu, 06 Jul 2023 13:42:02 +0000

This is Meta's Twitter clone, seeded with Instagram accounts.

New comment by toxicFork in "AMD AI Software Solved – MI300X Pricing, Perf, PyTorch, FlashAttention, Triton"

toxicFork — Fri, 30 Jun 2023 18:29:55 +0000

GPT4 please port my CUDA to work on AMD

New comment by toxicFork in "North Korean market prices suggest serious food shortages"

toxicFork — Sat, 24 Jun 2023 17:20:53 +0000

Do you mean why they don't let it die?

New comment by toxicFork in "Eating microwave popcorn increases the level of PFAS in body (2022)"

toxicFork — Fri, 23 Jun 2023 10:07:45 +0000

I thought at first that the existing patients are getting better and looking younger thanks to the chemicals, rather than the new patients being younger than the previous ones.

New comment by toxicFork in "Eating microwave popcorn increases the level of PFAS in body (2022)"

toxicFork — Fri, 23 Jun 2023 10:05:49 +0000

When you pick the kernels for the sacrifice they have to accept their fate and the others have to accept the tribute. It's just their tradition.

New comment by toxicFork in "Ask HN: Why does Apple refuse to add window snapping to macOS?"

toxicFork — Sun, 18 Jun 2023 09:06:39 +0000

Are they paid apps? Perhaps that's why. This way Apple can get a cut from the DLC.

New comment by toxicFork in "Ask HN: Why does Apple refuse to add window snapping to macOS?"

toxicFork — Sat, 17 Jun 2023 18:20:18 +0000

Another reason for "patents are awful"

New comment by toxicFork in "Show HN: I made an open-source Notion-style WYSYWIG editor"

toxicFork — Fri, 16 Jun 2023 22:44:00 +0000

What you submit yields what I get

New comment by toxicFork in "Bay Area woman is on a crusade to prove Yelp reviews can’t be trusted"

toxicFork — Thu, 15 Jun 2023 03:37:35 +0000

It could just be the recommended marketing practice by the local small business school. Right after "Rent a week on the ad spot by the bus station" could be "buy a few fake reviews on yelp".

New comment by toxicFork in "Chat Notebooks"

toxicFork — Sat, 10 Jun 2023 08:03:44 +0000

https://github.com/WolframResearch/Chatbook/blob/ba3e783602f... should help answer some of those - I am on a mobile device so hard to write much, but, OpenAI 3.5 at least