121
Building Effective "Agents"
Practical guidance from Anthropic on building reliable AI agents, from simple composable patterns to fully autonomous systems.
Most cited
Posts that commenters keep linking to, ranked by how many different people have cited them in Hacker News comments. 532 posts.
122
Llama.ttf: A font which is also an LLM
llama.ttf is a font file which is also a large language model and an inference engine for that model.
123
Accountability sinks
In The Unaccountability Machine, Dan Davies argues that organizations form “accountability sinks,” structures that absorb or obscure the consequences of a decision such that no one can be held dire...
124
Don't build your castle in other people's kingdoms (2021)
In the past couple of months a couple of big social media sites have changed their terms or introduced suspicious paid plans and it has caught content creators off guard.
125
Kagi search reached 20k paying members
Update: We shipped the t-shirts. -- Dear Kagi community, Today, we’re happy and proud to have reached 20,000 paying members, including over 1,500 families all over the world, in our community. We have come a very...
126
Facing reality about the EU is a core requirement for good management
Writing at the end of the world, from Hveragerði, Iceland
127
Dear friend, you have built a Kubernetes
Mac's Tech Blog
128
Free data transfer out to internet when moving out of AWS
You told us one of the primary reasons to adopt Amazon Web Services (AWS) is the broad choice of services we offer, enabling you to innovate, build, deploy, and monitor your workloads. AWS has continuously expanded its services to support virtually any cloud workload. It now offers over 200 fully featured services for…
129
The Swift compiler is slow due to how types are inferred
How a 10 year old design choice for Swift’s type checker still haunts us to this day
130
Physical Intelligence's first generalist policy AI can finally do your laundry
Our first generalist policy, π0, a prototype model that combines large-scale multi-task and multi-robot data collection with a new network architecture to enable the most capable and dexterous generalist robot policy to date.
131
UTC, Tai, and Unix Time (2001)
TAI times are identified by year, month, day, hour, minute, and second. There are exactly 86400 TAI seconds in every TAI day. TAI days are labelled by the Gregorian calendar.
132
What's Next for Kagi?
Two years ago, on June 1st, 2022, Kagi introduced a search engine that challenged the ad-supported version of the web. Kagi Search instead works for you, the user, and not an advertiser paying for your attention....
133
The power of two random choices
In many large-scale web services, multiple layers of stateless and stateful services are seperated by load balancers. Load balancing can be done with dedicated hardware, with dedicated software load balancers, using DNS trickery or through a load-balancing mechanism in the client. In large systems, the resources and…
134
135
Pelicans on a bicycle
I decided to roll out my own LLM benchmark: how well can different models render an SVG of a pelican riding a bicycle? I chose that because a) I like …
136
Airfoil
Interactive article explaining the physics of an airfoil and what makes airplanes fly
137
Apple announces changes to iOS, Safari, and the App Store in the European Union
Apple announced changes to iOS, Safari, and the App Store impacting developers’ apps in the EU to comply with the DMA.
138
Anyone can access deleted and private repository data on GitHub
You can access data from deleted forks, deleted repositories and even private repositories on GitHub. And it is available forever. This is known by GitHub, and intentionally designed that way.
139
Computer use, a new Claude 3.5 Sonnet, and Claude 3.5 Haiku
A refreshed, more powerful Claude 3.5 Sonnet, Claude 3.5 Haiku, and a new experimental AI capability: computer use.
140
Anatomy of a credit card rewards program
Credit card rewards are mostly funded out of interchange, a fee paid by businesses to accept cards.
141
Yes, social media is a cause of the epidemic of teenage mental illness
Two major problems with a review in Nature
142
Passkeys: A shattered dream
Firstyear's blog
143
Too much efficiency makes everything worse (2022)
This blog is intended to be a place to share ideas and results that are too weird, incomplete, or off-topic to turn into an academic paper, but that I think may be important. Let me know what you think! Contact links to the left.
144
The Lunacy of Artemis
Introduction A Note on Apollo I. The Rocket II. The Capsule III. The Orbit IV. Gateway V. The Lander VI. Refueling VII. Conclusion Notes
145
I Lost Faith in Kagi
Issues with Kagi's AI focus, finances and leadership
146
Font with Built-In Syntax Highlighting
An experiment in javascript-free syntax highlighting, made possible by opentype contextual alternates and COLR table
147
AlphaGeometry: An Olympiad-level AI system for geometry
Our AI system surpasses the state-of-the-art approach for geometry problems, advancing AI reasoning in mathematics
148
JPEG XL and the Pareto Front
Full details on libjxl v. 0.10 and how it affects jpeg xl lossless compression using Pareto Front for a closer analysis.
149
Redis adopts dual source-available licensing
Developers love Redis. Unlock the full potential of the Redis database with Redis Enterprise and start building blazing fast apps.
150
A comparison of Rust’s borrow checker to the one in C#
OK, so C# doesn’t share the Rust concept of “borrowing,” so it wouldn’t technically be correct to call this “borrow checking,” but in practice when people talk about “Rust’s borrow checker” they’re talking about all of the static analysis Rust does to ensure memory safety, for which I think this qualifies.