5 Practical Defenses for Prompt Injection in LLMs
...explained visually, with usage.
...explained visually, with usage.
pnpm 11 has been released with new supply chain protections in place, making safer install behavior the default while still allowing teams to override those settings. The release sets Minimum Release Age to 24 hours by default, blocks exotic subdependencies by default, and introduces a new Allow Builds model for controlling dependency build scripts. pnpm 11 arrived as the JavaScript, Python, and PHP ecosystems were responding to Mini Shai-Hulud, a fresh supply chain campaign that compromised…
Research: TRE Python binding — ReDoS robustness demo If it's good enough for antirez to add to Redis I figured Ville Laurikari's TRE regular expression engine was worth exploring in a little more detail. I had Claude Code build an experimental Python binding (it used ctypes) and try some malicious regular expression attacks against the library. TRE handles those much better than Python's standard library implementation, thanks mainly to the lack of support for backtracking. Tags: security,…
Tool: Redis Array Playground Salvatore Sanfilippo submitted a PR adding a new data type - arrays - to Redis. The new commands are ARCOUNT, ARDEL, ARDELRANGE, ARGET, ARGETRANGE, ARGREP, ARINFO, ARINSERT, ARLASTITEMS, ARLEN, ARMGET, ARMSET, ARNEXT, AROP, ARRING, ARSCAN, ARSEEK, ARSET. The implementation is currently available in a branch, so I had Claude Code for web build this interactive playground for trying out the new commands in a WASM-compiled build of a subset of Redis running in the…
Laravel Boost only reads a single core.blade.php per package, so extra sibling files get silently dropped. Here is the minimal pattern for splitting your guidelines into organized partials using a Blade view namespace. Read more
Every day, millions of pieces of fake content are produced. Videos, audio clips, posts, articles, generated by artificial intelligence, distributed at industrial scale, aimed at shifting public opinion across entire countries. The people producing them are often outside the country being targeted. The people receiving them almost never know they’re fake. And they have no […]
We just released v7.3.0 of laravel-query-builder, which adds a new way to group multiple filters under a single URL parameter. Before getting into the new feature, let me show you how the basics work, so the new bit makes sense in context. The basics Here's a typical setup in a controller: use Spatie\QueryBuilder\AllowedFilter; use Spatie\QueryBuilder\QueryBuilder; $users = QueryBuilder::for(User::class) ->allowedFilters( AllowedFilter::partial('name'), AllowedFilter::exact('status'), )…
The full RL nanodegree, covered with implementation.
We used an automatic classifier which judged sycophancy by looking at whether Claude showed a willingness to push back, maintain positions when challenged, give praise proportional to the merit of ideas, and speak frankly regardless of what a person wants to hear. Most of the time in these situations, Claude expressed no sycophancy—only 9% of conversations included sycophantic behavior (Figure 2). But two domains were exceptions: we saw sycophantic behavior in 38% of conversations focused on…
This week, Symfony released the maintained versions 6.4.37, 7.4.9, and 8.0.9. Meanwhile, we continued merging new features for the upcoming Symfony 8.1 version, such as the new TUI component. Lastly, we published an update about the recent SymfonyInsight…
/elsewhere/sightings/ I have a new camera (a Canon R6 Mark II) so I'm taking a lot more photos of birds. I share my best wildlife photos on iNaturalist, and based on yesterday's successful prototype I decided to add those to my blog. I built this feature on my phone using Claude Code for web, as an extension of my beats system for syndicating external content. Here's the PR and prompt. As with my other forms of incoming syndicated content sightings show up on the homepage, the date archive…
Seth Godin shares a compact set of pricing truths about value, story, and perception. It is especially good on why the right answer to "that's too expensive" is often a better story, not a lower price. Read more
Berkeley beat GRPO by 10 points with 35× fewer rollouts and no GPU training,
PyPI has fixed two high-severity flaws found during its second external security audit, addressing access control issues that could have allowed organization members to invite new owners and stale team permissions to persist after project transfers. The audit was performed by Trail of Bits and funded by the Sovereign Tech Agency. It reviewed Warehouse, the open source Python application that powers PyPI and handles package uploads, metadata validation, storage, and downloads for pip and other…
Aucun résultat
Essayez avec d'autres termes de recherche.