1321
Top posts
Every blog post that took off on Hacker News, ranked by the votes of its best submission. 1,523 posts.
1322
Stop using natural language interfaces
Natural language is a wonderful interface, but just because we suddenly can doesn't mean we always should.
1323
I turned Markdown into a protocol for generative UI
An AI assistant that builds reactive UIs mid-conversation — forms, streaming data, callbacks — using markdown code fences and a mount() UI primitive.
1324
If AI coding is lowering your code quality, you're not managing quality right
One common take on the coding agents that I see goes something like this: “Sure, AI helps you output more code, but won’t the quality suffer?”
1325
AI is destroying my CS degree
I am a computer science student. I got a scholarship to study computer science and AI last year and I love it! It's something that I wanted to do since I was...
1326
Expertise in the age of AI
Junior engineers are expensive, both in salary and seniors engineers’ time. This cost was partially recouped through code contributions, but today, it’s more effective to directly maximize the output of your senior engineers. The hiring market reflects this trend: senior engineers have an easy time finding jobs, while…
1327
Running local LLMs offline on a ten-hour flight
Update, 29 April 2026 This post was picked up on Hacker News and crossed 100 comments. I love that this sparks emotions. As always, there is a fair mix of reactions, which is exactly what you would expect from HN. Scroll to the bottom for extra responses to some of the comments. … Cloud Next was intense. I wrote the…
1328
Changes to Sourcehut's terms of service regarding LLMs
sourcehut is a network of useful open source tools for software project maintainers and collaborators, including git repos, bug tracking, continuous integration, and mailing lists.
1329
Making LLM Training Faster with Unsloth and NVIDIA
Learn how NVIDIA helped Unsloth to make fine-tuning AI models 20% faster with explanations and diagrams.
1330
1331
After the AI Crash
Everything I read about the AI industry leads me to think there will be an AI crash. Consider the following: Unsustainable Capital Expenses. It’s hard to imagine there can ever be enough revenue to…
1332
AI didn't simplify software engineering: It just made bad engineering easier
AI tools lower the barrier to producing code, not to building reliable systems. The hard part — maintaining alignment between specifications, tests, and implementation — has not gone away. Expertise still matters.
1333
AI Is Breaking This Thing We Call Trust
AI-generated work can look finished without being understood. That uncertainty erodes trust, slows reviews, and leaves colleagues doing the missing work.
1334
Backprop Alternative: Augmented Lagrangian Predictive Coding
A local alternative to backpropagation. PC-ALM trains residual MLPs up to 1000 layers, nearly matching backprop's performance despite using only layer-local dynamics. PC-ALM equips each layer with a feedback control dynamical system that distributes and propagates supervision credit throughout a network.
1335
1336
Arithmetic Without Numbers – How LLMs Do Math
What happens inside an LLM when it tries to calculate with nothing but matrices.
1337
Agora-1: The Multi-Agent World Model
Agora-1, a multi-agent world model, enables multiple participants—human or AI—to share and interact within the same world simulation in real-time.
1338
Our approach to age prediction
ChatGPT is rolling out age prediction to estimate if accounts are under or over 18, applying safeguards for teens and refining accuracy over time.
1339
Anger, Anxiety and Agency
Who is the AI villain we should be angry at?
1340
When AI Costs More Than the Engineer
Anthropic spends 2.3x payroll on compute. Top software firms spend 0.4x. Three scenarios for where the rest of the market lands by 2029.
1341
1342
Will I ever own a zettaflop?
As the eleventh hour dawns all the pieces start to fall into place. I lived my life knowing this would happen, yet when it is I may be just as unprepared as anyone else. As any self driving car maker knows, predicting doesn’t mean you can act.
1343
Rolling your own serverless OCR in 40 lines of code
Parsing a statistics textbook with Deepseek OCR on Modal
1344
The U.S. Census Bureau and "Super Intelligence"
I was reminded today of AI Adoption Rate Trending Down for Large Companies, a chart produced by Apollo Global Management in September 2025, which appeared to show a slowdown in …
1345
Local Indexing to reduce tool calling and token usage
Pensieve for developers: a local MCP server that gives Claude Code, Codex and Cursor your context. A thread for every piece of work. Free and open source, for Mac.
1346
Gemma-4-26B-A4B with 39-69% less thinking at same accuracy
This is the fifth model in the ThinkingCap series. We reduced how much Google's gemma-4-26B-A4B-it thinks, without compromising the quality of its answers.
1347
There is no posttraining data commons
The LLM revolution ran on a pretraining commons that humanity built for other reasons. Posttraining consumes tasks, not documents, and no such commons exists. If the open models community wants...
1348
The assistant axis: situating and stabilizing the character of LLMs
Who is the Assistant? We investigate the character that most modern language models inhabit when interacting with users.
1349
Claude Duet is the first personal-assistant-type harness that feels useful
Look, I really didn’t want to like Duet. I don’t want to be an Anthropic fanboy and it annoys me when they do things better than the competition. But they have done it again.
1350
Intelligence Is Not the Main Bottleneck
Confessions of a naive hamster: why the smartest people in the room keep missing that intelligence is often not the main bottleneck in the real world