treefry

The benchmark scores are not exciting. I understand Google is playing a catch up game right now, but still wish to see some overwhelming improvements.

Nevermind. Switching to Opus 5.5.

From my experience with complex coding tasks (AI infra), I don't think these open weight models are close.

From my experience, there are mainly 3 burnout reasons. 1. Multi-tasking is the top one. I usually have to frequently switch between 3 to 5 agent windows which are on different things. It's extremely exhausting when each round takes a few minutes. Before coding agent era, I believe most developers had chance to spend 2+ hours focusing on one thing. Now coding agents have increased my spectrum on the tech stack, but the bandwidth to do deep work isn't increased. 2. Agents are good at getting things running without crash, but do not guarantee to produce correct code. This is quite different from human experts with fundamental knowledge. 3. I also get frustrated when reviewing piles of AI generated low quality PRs. My attention is a limited resource. I don't waste too much energy on other people's work, but if I don't spend more effort, the entire project is corrupted quickly by reckless AI generated code without human author's careful thoughts and designs. Working with people who have less due diligence in mind is painful, working with them in coding agent era is 10x painful because they produce 10x shit. It's a team culture challenge that cannot be easily enforced.

Unless you self host, zero data retention cannot be guaranteed.

Same here. Don't understand why Github hasn't supported this until now. I'm tired of reviewing PRs with thousands of lines of changes, which are getting worse nowadays with vibe coding.

Are they likely to take a new strategy that they no longer open source their largest and strongest models?

Right. Yesterday I tried a simple task that just adds Required[] notation to all class fields. After making the change on one field, Cursor allows me to press tabs and update all other fields. VSCode doesn't understand what I was trying to do after the first operation, which is surprisingly bad (no improvement after months). Also I'm not in favor of the conversational experience of claude code or other CLIs for such trivial task. I'd be happy to know what else can provide a better user experience than Cursor.

Disclaimer: I get enterprise level subscriptions to these services via my employer. I personally don't pay for them and never consider their cost, if that matters.

Yeah a lot of functions broke since around 19:40 UTC.

Looks like 64GB or more

I tried to set up Dart runtime and run cli on a Linux server. Then I realized that it just prints a message and quits. Maybe it's better to directly tell user cli isn't implemented yet.

They cannot manufacture such advanced chip even if they have circuit design.

The problem is Y is more uniform but X is not. Good drivers make significantly fewer mistakes than the average. For these people, using software potentially increases risk by order of magnitudes.

Not surprising as Moore's law had stopped applying to CPU. Assuming each year CPU gets 20% improvement, from 2012 to 2021 the latest cpu is 5x more powerful than the old one. Considering 30% performance loss for converting x86 instructions to ARM, 4x is a reasonable number.

Traffic to Pornhub went up by 10%