Hacker News: jp0001

New comment by jp0001 in "Your Website Is Not for You"

jp0001 — Fri, 01 May 2026 14:35:52 +0000

That website was not for me.

New comment by jp0001 in "US special forces soldier arrested after allegedly winning $400k on Maduro raid"

jp0001 — Sat, 25 Apr 2026 14:45:25 +0000

Count 1 and 2 makes sense. A good lawyer can get 3-5 thrown out in a plea deal.

New comment by jp0001 in "You don't want long-lived keys"

jp0001 — Sat, 25 Apr 2026 14:42:17 +0000

I'm still having problems trusting my compiler.

New comment by jp0001 in "I cancelled Claude: Token issues, declining quality, and poor support"

jp0001 — Sat, 25 Apr 2026 13:45:41 +0000

Max x20 user here. As long as Opus 4.6 is available and they fix Opus 4.7, I'll stay with Anthropic. Tho, I'd imagine in 5 years we'll have Opus 4.6 equivalent performance available in an at home consumer model.

New comment by jp0001 in "Claude Opus 4.7"

jp0001 — Thu, 16 Apr 2026 16:09:30 +0000

It's easier to produce vulnerable code than it is to use the same Model to make sure there are no vulnerabilities.

New comment by jp0001 in "Claude Opus 4.7"

jp0001 — Thu, 16 Apr 2026 16:07:31 +0000

WTF. `Opus 4.7 is the first such model: its cyber capabilities are not as advanced as those of Mythos Preview (indeed, during its training we experimented with efforts to differentially reduce these capabilities). We are releasing Opus 4.7 with safeguards that automatically detect and block requests that indicate prohibited or high-risk cybersecurity uses. `

Seriously? You're degrading Opus 4.7 Cybersecurity performance on purpose. Absolute shit.

New comment by jp0001 in "Cybersecurity looks like proof of work now"

jp0001 — Wed, 15 Apr 2026 21:06:06 +0000

I'm starting to think that Opus and Mythos are the same model (or collection of models) whereas Mythos has better backend workflows than Opus 4.6. I have not used Mythos, but at work I have a 5 figure monthly token budget to find vulnerabilities in closed-source code. I'm interested in mythos and will use it when it's available, but for now I'm trying to reverse engineer how I can get the same output with Opus 4.6 and the answer to me is more tokens.

New comment by jp0001 in "SQLite in Production: Lessons from Running a Store on a Single File"

jp0001 — Tue, 07 Apr 2026 17:44:15 +0000

I took three weeks off from tech, read books from last century, and travelled Europe. Coming back, reading LLM generated content and code feels like nails on a chalkboard. Taste, it does not have taste.

New comment by jp0001 in "Cell Service for the Fairly Paranoid"

jp0001 — Wed, 25 Feb 2026 07:58:13 +0000

Hold on. Cell towers still know where the device is. If a group of people in an area have stable ismi’s and one person’s ismi is rotating daily, it doesn’t take a genius to figure out who’s now using cape. Using it for travel makes sense, but again being a device that doesn’t a have an owner is, as the kids say, sus.

New comment by jp0001 in "This is not the future"

jp0001 — Tue, 16 Dec 2025 15:31:47 +0000

Mobile device updates are the worst for aging parents. These devices are getting more complex to use not easier, you shouldn't have to upend your life once a year because UX design choices forces you to miss what you think is important, how to find it, or disable/enable features you don't want or used to have.

New comment by jp0001 in "Amazon has mostly sat out the AI talent war"

jp0001 — Mon, 01 Sep 2025 20:03:29 +0000

Eh, looks at my aws bedrock bill, I think they are doing alright.

New comment by jp0001 in "Try and"

jp0001 — Sun, 10 Aug 2025 15:30:28 +0000

Every time I read something like this, I remember that there is truly no correct way to say something - all that matters is that your intended audience understands it, eventually.

New comment by jp0001 in "GrimWidget – to help with my screen time use"

jp0001 — Fri, 08 Aug 2025 14:10:50 +0000

You don’t think LLMs should get paid for their labor? /s

GrimWidget – to help with my screen time use

jp0001 — Fri, 08 Aug 2025 13:48:36 +0000

Article URL: https://apps.apple.com/us/app/grimwidget/id6749561824

Comments URL: https://news.ycombinator.com/item?id=44836910

Points: 1

# Comments: 2

New comment by jp0001 in "MCP is eating the world"

jp0001 — Wed, 25 Jun 2025 03:08:00 +0000

So sick of this. LLMs are just a new paradigm on search.

Old Google: I don’t know the answer, but here are some links that might help you - with ads.

LLMs: I confidently know the answer, but I could be wrong and frequently am. No ads yet, but they are coming.

New comment by jp0001 in "XBOW, an autonomous penetration tester, has reached the top spot on HackerOne"

jp0001 — Wed, 25 Jun 2025 02:59:33 +0000

I want to know how much they made in bounties versus how much they spent on compute.

The thing about bug bounties, the only way to win is to not play the game.

New comment by jp0001 in "I used o3 to find a remote zeroday in the Linux SMB implementation"

jp0001 — Mon, 26 May 2025 14:22:04 +0000

Correct. Dynamic runtime interactions will always be a hard problem as it’s hard to see in static code even for humans.

New comment by jp0001 in "I used o3 to find a remote zeroday in the Linux SMB implementation"

jp0001 — Sun, 25 May 2025 10:20:44 +0000

We followed a very similar approach at work, created a test harness and tested all the models available in AWS bedrock and the OpenAI. We created our own code challenges not available on the Internet for training with vulnerable and non-vulnerable inline snippets and more contextual multi-file bugs. We also used 100 tests per challenge - I wanted to do 1000 test per challenge but realized that these models are not even close to 2 Sigma in accuracy! Overall we found very similar results. But, we were also able to increase accuracy using additional methods - which comes as additional costs. The issue I see overall is that we found is when dealing with large codebases you'll need to put blinders on the LLMs to shorten context windows so that hallucinated results are less likely to happen. The worst thing would be to follow red herrings - perhaps in 5 years we'll have models used for more engineering specific tasks that can be rated with Six Sigma accuracy if posed with the same questions and problems sets.

New comment by jp0001 in "TSMC execs allegedly dismissed OpenAI CEO Sam Altman as 'podcasting bro'"

jp0001 — Fri, 27 Sep 2024 12:23:52 +0000

Well, he’s not their direct customer.

New comment by jp0001 in "Obituary for a quiet life (2023)"

jp0001 — Sun, 14 Apr 2024 13:50:43 +0000

Amazing writing. Reminds me of my grandfather.

I’ve thought about it this way, you have four options in life: - not rich, not famous - not rich, famous - rich, famous - rich, not famous

The last one is the best, IMO. And by rich, I mean to not need for anything. And that means having your ego in check. The worst thing I’ve ever witnessed is a literal 100+ millionaire with no peace, still trying to impress people of their wealth and self importance.