1111
AI agent benchmarks are broken
Benchmarks are foundational to evaluating the strengths and limitations of AI systems, guiding both research and industry development.
New
The latest blog posts to take off on Hacker News. 3,091 posts.
1112
Grok: Searching X for "From:Elonmusk (Israel or Palestine or Hamas or Gaza)"
If you ask the new Grok 4 for opinions on controversial questions, it will sometimes run a search to find out Elon Musk’s stance before providing you with an answer. …
1113
AI coding tools can reduce productivity
Study Shows That Even Experienced Developers Dramatically Overestimate Gains
1114
Grok 4
Released last night, Grok 4 is now available via both API and a paid subscription for end-users. Update: If you ask it about controversial topics it will sometimes search X …
1115
Is Gemini 2.5 good at bounding boxes?
Can Gemini 2.5 replace CNN for object detection?
1116
Why LLMs Can't Write Q/Kdb+: Writing Code Right-to-Left
In my previous post I showed how LLMs struggle with coding in q/kdb+; having immediate feedback loops using the q-MCP server does help a…
1117
Adding a feature because ChatGPT incorrectly thinks it exists
At Soundslice, our sheet music scanner digitizes music from photographs, so you can listen, edit and practice. We continually improve the system, and I keep an eye on the error logs to see which images are getting poor results.
1118
I used o3 to profile myself from my saved Pocket links
Welp, Pocket shuts down tomorrow despite our pleas for it to stay. While migrating1 all of my saved articles, I noticed that I’ve got almost 900 saved articles spanning nearly 7 years. That’s a goldmine of stuff-I-like data! Some quick analysis using xsv2: 𝄢 unzip pocket.zip && xsv headers part_000000.csv 1 title 2…
1119
A non-anthropomorphized view of LLMs
In many discussions where questions of "alignment" or "AI safety" crop up, I am baffled by seriously intelligent people imbuing almost magic...
1120
I don't think AGI is right around the corner
Continual learning is a huge bottleneck
1121
Whistleblower: Huawei cloned Qwen and DeepSeek models, claimed as own
A now-deleted report by HonestAGI on GitHub showed a high number of similarities between Huawei’s Pangu and Qwen 2.5.
1122
Building a Mac app with Claude code
How I built Context—a native macOS SwiftUI app for debugging MCP servers—almost entirely with Claude Code, and what I learned about building with AI coding agents.
1123
The force-feeding of AI features on an unwilling public
This isn't innovation, it's tyranny
1124
Are we the baddies?
I signed up for Hinge. Holy shit with the boosts.
1125
Optimizing Tool Selection for LLM Workflows with Differentiable Programming
How local, learnable routers can reduce token overhead, lower costs, and bring structure back to agentic workflows.
1126
Problems the AI industry is not addressing adequately
As a supporter, I would love not to feel this way
1127
Nvidia won, we all lost
Since the disastrous launch of the RTX 50 series, NVIDIA has been unable to escape negative headlines: scalper bots are snatching GPUs away from consumers before official sales even begin, power connectors continue to melt, with no fix in sight, marketing is becoming increasingly deceptive, GPUs are missing processing…
1128
Prompting LLMs is not engineering
prompt engineering is nothing but an attempt to reverse-engineer a non-deterministic black box for which any of the parameters below are unknown: - training set - weights - constraints on the model - layers between you and the model that transform both your input and the model's output that can change at any time …
1129
1130
Data on AI-related Show HN posts
The idea for this article didn't exist in my brain before this morning. But there I was, scrolling the New page and even more tired of all the AI-related Show HN posts than usual. I was confident that their numbers were multiplying and wanted proof. Exactly how much more AI crap is on my lawn compared to last year?
1131
Tools: Code Is All You Need
The solution to agentic flows was code all along.
1132
1133
Building a Personal AI Factory
Multiple parallel Claude-Code sessions power a self-improving AI factory where agents write, review, and refine code.
1134
HN Slop: AI startup ideas generated from Hacker News
Fresh AI generated startup ideas from the current Hacker News front page. Powered by Claude.
1135
Spending Too Much Money on a Coding Agent
On making use of large thinking models.
1136
Context Engineering for Agents
Patterns for managing agent context.
1137
About AI Evals
A guide to AI and LLM evals for engineers and product managers. Learn how to test AI systems, analyze failures, and improve retrieval, agents, and AI products.
1138
The new skill in AI is not prompting, it's context engineering
Context Engineering is the new skill in AI. It is about providing the right information and tools, in the right format, at the right time.
1139
There are no new ideas in AI, only new datasets
LLMs were invented in four major developments... all of which were datasets
1140
We accidentally solved robotics by watching 1M hours of YouTube
the existential crisis we all share imagine this: you've just spent $640 billion training the chonkiest language model known to humanity (lol) and decide...