Hacker News: sharperguy

New comment by sharperguy in "The last six months in LLMs in five minutes"

sharperguy — Tue, 19 May 2026 10:04:44 +0000

Much of the recent improvement in models is in being trained specifically to make use of the tools the harnesses give them.

New comment by sharperguy in "New Nginx Exploit"

sharperguy — Thu, 14 May 2026 22:16:45 +0000

I've switched to using traefik from caddy. For simple use cases it's a little more verbose in the configuration, but for more involved things like multiple load balancing backends, rewriting paths and headers and so on I've found it really good.

New comment by sharperguy in "Agents need control flow, not more prompts"

sharperguy — Thu, 07 May 2026 21:52:22 +0000

So I wonder, if a more powerful agent harness could have the agent basically write and exectute its own deteministic code, which when executed, spawns sub agents for each of the subtasks?

So far we've seen agents spawn subagents directly, but that still means leaving the final flow control to the non-deterministic orchestrator model, and so your case is a perfect example of where it would probably fail.

New comment by sharperguy in "Fedora is now the default Linux recommendation, and Ubuntu did this to itself"

sharperguy — Wed, 06 May 2026 12:22:29 +0000

Both Arch and Nix solve this by making it very easy to write packages that work around the compatibility issues. When I used to use ubuntu and mint it was a lot more common to run into these types of issues.

New comment by sharperguy in "Agent Skills"

sharperguy — Wed, 06 May 2026 07:16:41 +0000

Nobody is arguing it's guaranteed. This is why you never give an LLM access to any essential infrastructure. Make sure everything it does can be undone. Double check when guarantees are required.

New comment by sharperguy in "Agent Skills"

sharperguy — Tue, 05 May 2026 11:07:08 +0000

Skills are often invoked imperatively by the user. In cases where they are intended to be used directly by the LLM, it would be included somewhere else in the context. E.g:

``` After implementing the feature, read the testing skill for instructions on how to test. ```

New comment by sharperguy in "An AI agent deleted our production database. The agent's confession is below"

sharperguy — Mon, 27 Apr 2026 10:15:02 +0000

The personification seems to be at the training level. When I ask an LLM why it did something destructive, the ideal response would be a matter of fact evaluation of the mistakes that I myself have made in setting up the agent and it's environment, and how to prevent it from happening again. Instead the model itself has been trained to apologize and list exactly what it did wrong without any suggestions of how to actually prevent it in the future.

New comment by sharperguy in "Who is Satoshi Nakamoto? My quest to unmask Bitcoin's creator"

sharperguy — Thu, 09 Apr 2026 12:50:26 +0000

Water? You mean like out of the toilet?

New comment by sharperguy in "The team behind a pro-Iran, Lego-themed viral-video campaign"

sharperguy — Tue, 07 Apr 2026 06:56:34 +0000

A serious existential threat to the country from a targetable state actor.

New comment by sharperguy in "Eight years of wanting, three months of building with AI"

sharperguy — Sun, 05 Apr 2026 17:49:01 +0000

It's actually common for human-written projects to go through an initial R&D phase where the first prototypes turn into spaghetti code and require a full rewrite. I haven't been through this myself with LLMs, but I wonder to what extent they could analyse the codebase, propose and then implement a better architecture based on the initial version.

New comment by sharperguy in "I tried to prove I'm not AI. My aunt wasn't convinced"

sharperguy — Wed, 25 Mar 2026 12:34:47 +0000

only proves you're not a corporate model rather than locally running model that's been trained to allow saying that

New comment by sharperguy in "Blocking Internet Archive Won't Stop AI, but Will Erase Web's Historical Record"

sharperguy — Sat, 21 Mar 2026 15:24:12 +0000

You can have cryptographically signed data caches without the need for a blockchain. What a blockchain can add is the ability to say that a particular piece of data must have existed before a given date, by including the hash of that data somewhere in the chain.

New comment by sharperguy in "System76 on Age Verification Laws"

sharperguy — Fri, 06 Mar 2026 12:27:33 +0000

The same politicians who claim to support the free market will do deals like ttis with corporate oligopolies to cement their position into eternity.

New comment by sharperguy in "Motorola GrapheneOS devices will be bootloader unlockable/relockable"

sharperguy — Wed, 04 Mar 2026 14:33:23 +0000

they used to publish a buildable AOSP tree for the device which is no longer the case

New comment by sharperguy in "Microgpt"

sharperguy — Sun, 01 Mar 2026 10:20:39 +0000

Still, it might be interesting information to have access to, as someone running the model? Normally we are reading the output trying to build an intuition for the kinds of patterns it outputs when it's hallucinating vs creating something that happens to align with reality. Adding in this could just help with that even when it isn't always correlated to reality itself.

New comment by sharperguy in "The Age Verification Trap: Verifying age undermines everyone's data protection"

sharperguy — Tue, 24 Feb 2026 11:24:30 +0000

Part of the issue with phones is that they are already controlled by the Google/Apple duopoly, and hence heavily optimized for constant distraction and addiction. These laws only cement that duopoly and provide fewer means to build more friendly platforms.

New comment by sharperguy in "Loops is a federated, open-source TikTok"

sharperguy — Mon, 23 Feb 2026 11:22:27 +0000

I've been hearing talk for years about a "web of trust" system, that could filter spam simply by having users vouch for eachother and filtering out anyone not vouched for. However, I haven't seen a function system based on this model yet.

Personally I'd love to add in something like the old slashdot comment model, where people would mark content as "helpful", "funny", "insightful", "controversial" etc, and based on how much you trust the people labeling it, you could have things filtered out, or brought forward.

New comment by sharperguy in "Anthropic officially bans using subscription auth for third party use"

sharperguy — Thu, 19 Feb 2026 11:10:16 +0000

I would even call it mid 2020s. I think in a couple years people's attention spans will be so short they won't even finish reading comments.

New comment by sharperguy in "Fix the iOS keyboard before the timer hits zero or I'm switching back to Android"

sharperguy — Sat, 14 Feb 2026 15:45:20 +0000

As a European it's hard for me to comprehend the influence that iMessage has on the US.

New comment by sharperguy in "Fix the iOS keyboard before the timer hits zero or I'm switching back to Android"

sharperguy — Sat, 14 Feb 2026 14:06:45 +0000

"But I came crawling back to iOS because I'm weak and the orange iPhone was pretty and the Pixel 10 was boring and I caved to the blue bubble pressure. But the keyboard on this beautiful phone is worse than ever. "

I don't understand. What could Apple possibly have that is better than a working device?