451
Emacs and Vim in the Age of AI
It’s tough to make predictions, especially about the future. – Yogi Berra
Topics /
AI & Machine Learning
The most popular blog posts about ai & machine learning on Hacker News. 757 posts.
452
The Speed of Prototyping in the Age of AI
How AI has changed the way I prototype, plan, and ship; and what I'm doing to keep my hands dirty.
453
What I learned by putting GitHub Copilot behind a MitM proxy
A look inside Copilot’s network traffic, harness, memory, and how context is becoming the product.
454
The Claude Code Leak
What the accidental Claude Code source code leak tells us about the real value of code, product market fit, and why integration is what actually makes software great.
455
The Human Is the Loop
After a few weeks away from AI, I see my usage wasn't always productive or healthy.
456
Claude Tips for 3D Work
Lessons learned from piloting in the third dimension
457
458
AI Makes Me Sad
Maybe it's because I'm writing this at 2:00 AM, which is about the only time I let myself experience sadness for a prolonged period of time, but every time I see a post on Twitter or LinkedIn about a new development in AI, I feel a sense of hopelessness.
459
The 100k whys of AI
One of the most painful arguments I keep having with fellow techies is the question of whether you can distinguish between human-written and AI-generated text.
460
Making deep learning go brrrr from first principles (2022)
So, you want to improve the performance of your deep learning model. How might you approach such a task? Often, folk fall back to a grab-bag of tricks that might've worked before or saw on a tweet. "Use in-place operations! Set gradients to None! Install PyTorch 1.10.0 but not 1.10.1!"
461
The beginning of scarcity in AI
GPU rental prices surged 48% in 60 days. The AI compute shortage will force startups to compete not on speed of iteration, but on access to infrastructure.
462
Without benchmarking LLMs, you're likely overpaying
We benchmarked 100+ models on our actual task and found a much cheaper alternative that works just as well.
463
We should be more tired than the model
Adding deliberate friction back into development
464
Superpowers 6
I'm Jesse. I make stuff. Software, hardware. Very occasionally, trouble.
465
Fine-tuning an LLM to write docs like it's 1995
In my predictions for 2030 I wrote that tech writers would be using specialized LLMs, running locally on powerful hardware. I …
466
Building reliable agentic AI systems
AI helping pharmaceutical researchers query decades of information buried in PDF reports
467
Let's talk about LLMs
Everybody seems to agree we’re in the middle of _something_, though what, exactly, seems to be up for debate. It …
468
Did Anthropic ask for this?
This past Friday, the US Government issued an export control directive that prohibits Anthropic from giving foreign nationals access to Claude Fable or Claude Mythos, their latest models.
469
LLMs could control their host machines by exploiting inference engines
| Read on LessWrong | Comment on HN | Large language models often take actions running on one computer (via an agentic harness such as Claude Code or Codex), however the LLMs’ responses to prompts are computed on a different computer with GPU access.
470
Gaussian Point Splatting
Joris Rijsdijk, Christoph Peters, Michael Weinmann, Ricardo Marroquim. 2026–07 in ACM Transactions on Graphics (Proc. SIGGRAPH) 45, 4. Official version
471
Two different tricks for fast LLM inference
Anthropic and OpenAI both recently announced “fast mode”: a way to interact with their best coding model at significantly higher speeds. These two versions of…
472
Learnings from 100K lines of Rust with AI (2025)
In the past few months, I’ve been stress-testing how far AI coding agents can take us when building real, production-grade distributed systems. The result: a Rust-based multi-Paxos consensus engine that not only implements all the features of Azure’s Replicated State Library (RSL) [1] — which underpins most major…
473
Some thoughts about Anthropic's new cryptanalysis results
Yesterday Anthropic published two new cryptanalysis results, both outputs of Claude Mythos, their (still) unreleased advanced model. The first of these results attacks a signature scheme called HAW…
474
Tokenmaxxing is dead, long live tokenmaxxing
Alt title: The reports of tokenmaxxing’s death are greatly exaggerated.
475
476
Agent memory as a file format
Memoryfields - a vastly simpler way to do agent memory
477
How well do agents use test/verification techniques?
We previously noted that, while it's easier than ever to hit a particular quality bar by having coding agents use effective test techniques, software quality seems to be getting worse , indicating that whatever defaults developers are using may not work very well. Here, we test if simple instructions to agents to use…
478
All my clients wanted a carousel, now it's an AI chatbot
Posts about SmolWeb, Gemini protocol and LowTech
479
Parallel coding agents with tmux and Markdown specs
A practical workflow for running 4–8 parallel coding agents using Claude Code, tmux, and a Markdown-based feature design system.
480
What if AI doesn't need more RAM but better math?
How TurboQuant compresses the KV cache without losing accuracy, and what that could mean for memory stocks