Apple unveils M5 Pro and M5 Max chips with new ‘Fusion Architecture’
The chips are engineered around Apple's new Fusion Architecture, an advanced design that merges two dies into a single, high-performance system on a chip (SoC).
TechBrief — تازهترین اخبار فناوری
آخرین خبرها
Apple’s new Studio Display XDR adds a Mini LED upgrade
After a few years between updates, Apple has two new 5K monitor options, ranging from expensive to very expensive, with the 27-inch 5K Studio Display and Studio Display XDR. Both have 5,120 x 2,880 resolutions and 12MP Center Stage cameras embedded inside - we'll be eager to see how much better those are this time […]
The 6G, modular, robot phones of the future
Year after year, we mostly know what to expect from our smartphone upgrades. Galaxy, iPhone, Pixel, or whatever else, everything seems to get slightly better (and occasionally more expensive) without many surprises in store. That's not to say there are no new ideas left in smartphones, though. You just have to know where to look. […]
Apple announces M5 MacBook Air and updated MacBook Pro
Apple is launching an upgraded MacBook Air featuring the M5 chip along with new MacBook Pro models featuring the M5 Pro and M5 Max. Announced on Tuesday, the new Macs will all be available for pre-order starting March 4th with availability in stores starting March 11th. In addition to the M5 chip, the new MacBook […]
Xiaomi, unlike Google and Samsung, thinks camera hardware comes first
When it launched the 17 and 17 Ultra in Europe on Saturday, Xiaomi bucked an industry trend: it didn't really talk about AI all that much. And it really didn't talk about AI when it showed off the two phones' cameras, including a special edition 17 Ultra co-created with Leica. According to Angus Ng, the […]
Blue Prince headlines Nintendo’s lineup of Switch 2 indie games
Following a Direct in February and a Pokémon-focused event last week, Nintendo returned today with a showcase focused on indie games. And it ended with a big one: the absorbing, room-shifting puzzle game Blue Prince is launching on the Switch 2. Even better, it'll be available later today. The rest of the titles revealed during […]
Launch HN: Cekura (YC F24) – Testing and monitoring for voice and chat AI agents
Hey HN - we're Tarush, Sidhant, and Shashij from Cekura (https://www.cekura.ai). We've been running voice agent simulation for 1.5 years, and recently extended the same infrastructure to chat. Teams use Cekura to simulate real user conversations, stress-test prompts and LLM behavior, and catch regressions before they hit production.
The core problem: you can't manually QA an AI agent. When you ship a new prompt, swap a model, or add a tool, how do you know the agent still behaves correctly across the thousands of ways users might interact with it? Most teams resort to manual spot-checking (doesn't scale), waiting for users to complain (too late), or brittle scripted tests.
Our answer is simulation: synthetic users interact with your agent the way real users do, and LLM-based judges evaluate whether it responded correctly - across the full conversational arc, not just single turns. Three things make this actually work: Scenario generation + real conversation import - Our scenario generation agent bootstraps your test suite from a description of your agent. But real users find paths no generator anticipates, so we also ingest your production conversations and automatically extract test cases from them. Your coverage evolves as your users do.
Mock tool platform - Agents call tools. Running simulations against real APIs is slow and flaky. Our mock tool platform lets you define tool schemas, behavior, and return values so simulations exercise tool selection and decision-making without touching production systems.
Deterministic, structured test cases - LLMs are stochastic. A CI test that passes "most of the time" is useless. Rather than free-form prompts, our evaluators are defined as structured conditional action trees: explicit conditions that trigger specific responses, with support for fixed messages when word-for-word precision matters. This means the synthetic user behaves consistently across runs - same branching logic, same inputs - so a failure is a real regression, not noise.
Cekura also monitors your live agent traffic. The obvious alternative here is a tracing platform like Langfuse or LangSmith - and they're great tools for debugging individual LLM calls. But conversational agents have a different failure mode: the bug isn't in any single turn, it's in how turns relate to each other. Take a verification flow that requires name, date of birth, and phone number before proceeding - if the agent skips asking for DOB and moves on anyway, every individual turn looks fine in isolation. The failure only becomes visible when you evaluate the full session as a unit. Cekura is built around this from the ground up. Where tracing platforms evaluate turn by turn, Cekura evaluates the full session. Imagine a banking agent where the user fails verification in step 1, but the agent hallucinates and proceeds anyway. A turn-based evaluator sees step 3 (address confirmation) and marks it green - the right question was asked. Cekura's judge sees the full transcript and flags the session as failed because verification never succeeded.
Try us out at https://www.cekura.ai - 7-day free trial, no credit card required. Paid plans from $30/month.
We also put together a product video if you'd like to see it in action: https://www.youtube.com/watch?v=n8FFKv1-nMw. The first minute dives into quick onboarding - and if you want to jump straight to the results, skip to 8:40.
Curious what the HN community is doing - how are you testing behavioral regressions in your agents? What failure modes have hurt you most? Happy to dig in below!
Comments URL: https://news.ycombinator.com/item?id=47232903
Points: 6
# Comments: 1
Apple launches M5 Pro and M5 Max chips
Apple has just announced two new processors: the M5 Pro and M5 Max. The new chips will power the MacBook Pro it revealed on Tuesday, offering an 18-core CPU and a new "Fusion Architecture" that integrates two 3nm dies into a single system-on-a-chip (SoC). The CPU's 18-core setup includes six "super" cores and 12 new […]
I'm reluctant to verify my identity or age for any online services
Comments URL: https://news.ycombinator.com/item?id=47232768
Points: 5
# Comments: 1
Don't Become an Engineering Manager
Article URL: https://newsletter.manager.dev/p/dont-become-an-engineering-manager
Comments URL: https://news.ycombinator.com/item?id=47232727
Points: 3
# Comments: 0