Hackers' Pub

Syntax	Description	Examples
`"` keyword `"`	Finds the string within quotes, including spaces. Case-insensitive. (Escape quotes inside with `\"`)	`"Hackers' Pub"`
`from:` handle	Finds content written by the specified user.	`from:hongminhee` `from:hongminhee@hollo.social`
`lang:` ISO 639-1	Finds content written in the specified language.	`lang:en`
`#` tag	Finds content with the specified tag. Case-insensitive.	`#HackersPub`
condition condition	Finds content that satisfies both conditions on either side of the space (logical AND).	`"Hackers' Pub" lang:en`
condition `OR` condition	Finds content that satisfies at least one of the conditions on either side of the OR operator (logical OR).	`#HackersPub OR "Hackers' Pub" lang:en`
`(` condition `)`	Combines the operators within the parentheses first.	`(#HackersPub OR "Hackers' Pub" OR "Hackers Pub") lang:en`

Simon Willison @simon@fedi.simonwillison.net

11/24/2025, 7:48:03 PM

Public

I had access over the weekend but with hindsight didn't do a great job of evaluation because I used it for real work: Most of the sqlite-utils 4 alpha release was written with help from Opus

I learned that production coding like that doesn't help identify new model strengths!

Simon Willison @simon@fedi.simonwillison.net

11/24/2025, 8:59:45 PM

Public

Updated my post with this section about their improved protection against prompt injection attacks - definitely better, but the problem is that if an attacker gets 10 tries they'll still succeed 1/3rd of the time!
https://simonwillison.net/2025/Nov/24/claude-opus/#still-susceptible-to-prompt-injection

Still susceptible to prompt injection #

From the safety section of Anthropic’s announcement post:

With Opus 4.5, we’ve made substantial progress in robustness against prompt injection attacks, which smuggle in deceptive instructions to fool the model into harmful behavior. Opus 4.5 is harder to trick with prompt injection than any other frontier model in the industry:

Bar chart titled "Susceptibility to prompt-injection style attacks"

On the one hand this looks great, it’s a clear improvement over previous models and the competition.

What does the chart actually tell us though? It tells us that single attempts at prompt injection still work 1/20 times, and if an attacker can try ten different attacks that success rate goes up to 1/3!

I still don’t think training models not to fall for prompt injection is the way forward here. We continue to need to design our applications

If you have a fediverse account, you can quote this note from your own instance. Search https://fedi.simonwillison.net/users/simon/statuses/115606682696928335 on your instance and quote it. (Note that quoting is not supported in Mastodon.)