mstank

Do you think American companies will secretly distill frontier models to build open weight ones?

They obviously know how unpopular this is, or else they wouldn't be releasing on a Friday night. This is so unimaginably disruptive, I wonder who inside the administration is suggesting this.

Is it just me or is this happening way more frequently in the last 4 or 5 months? Coincidently around the same time the models got a lot more capable?

I think the opposite is true. To dethrone the top tech company, you need to be able to spend much less than them, at higher efficiency and faster growth. Google didn’t catch up to Microsoft and Apple by spending more, they caught up by developing business lines and flywheels that were much more capital efficient.

If it’s a spending game, the incumbent has a huge advantage.

I always found it I eat them consistently, they would make me less gassy. But only after a couple of weeks.

Glad to see Searle's Chinese Room mentioned early on in the paper. "Syntax is not sufficient for semantics," no matter how much compute we throw at the problem.

My very amateur view is that until the underlying compute architecture and substrate resembles artificial biology more than silicon, we wont get there.

The latest advances in AI have given me even more appreciation of biology and evolution. It's incredible what the human brain can do with about 20 watts of power, barely enough to power a lightbulb, in comparison to what it takes to run even our most basic LLM models.

That happens to me all the time. My current working theory is when their servers are hammered there is a queueing system that invisible to end-users.

While I applaud her and wish her well — writing like this reminds me of a couple of things.

First my aging father insisting on navigating using his unfortunately fading memory instead of Google maps. Some people just won’t pick up technology out of habit or spite, even if it hinders them.

Second, a quote I read here that I’ll paraphrase “you can be the best marathon runner in the world and still lose a race to a guy on a bike.” Know the race you’re racing. It often changes.

I think it’s valid and commendable to keep the old ways alive, but also potentially dangerous to not realize they’re old ways.

Is this just to encourage off-peak usage to get the most out of hardware investments?

Am I the only one that read this as "DeathClaw"?

I’m working on Green Tea. A open source note app built on Pi agent framework. Basically gives you the power of a coding agent harness for knowledge work in an electron app.

No accounts required, all data is yours and lives on your computer.

Check it out: https://greentea.app

VPS + Dokploy gives you just as much functionality with an additional performance boost. Hostinger has great prices and a one-click setup. Good for dozens of small projects.

Haven't been able to run any actions for the last 30 mins... also had two in progress that were cancelled. Are there any good OSS ways to self-host gh compatible runners?

Couldn't a human just use an LLM browser extension / script to answer that quickly? This is a really interesting non-trivial problem.

The pendulum is swinging back slightly, but I wouldn’t pronounce it dead just yet.

We are seeing a decline of American hegemony, accelerated by this current regime. And the ascendancy of a non-democratic superpower.

However, the largest chunk of GDP and growth still sits firmly in democratic countries and very consequential American elections are happening this year, and in 2028.

The real question is, will Europe find its spine?

This is awesome, great work! There’s a huge audience for something like this based on the popularity of Kerbal Space Program.

Biggest low-hanging fruit UI improvement would be mobile responsiveness. It was a bit challenging testing on my phone.

This would be so cool… community contributed games with ratings and themes. So much potential for a platform like this. Great work!

In this case I think it came from the very top down — Benioff has been very bullish on AI and they’ve pretty much re-branded behind their Agent Force offerings.

Also probably a part of their go-to-market strategy. If they can prove it internally they can sell it externally.

Have you ever tried meditation? Does a great job scratching that ‘boredom’ itch…

Valve... please do Github Actions next

If you use the vscode extension you can click to view the sub-agent prompts and see all tool calls.

All that matters if the florists are happy with it -- extrapolate that to humanity as you wish.

Exactly this... I think there will be a golden age of excel replacement SaaS solutions with highly customized UX and workflows for vertical use cases. But, at the same time a lot more competition. Regardless, it will be great for users / companies with these specific problems.

In my experience, the golden age of indie software is about to begin. LLMs and coding agents will make building vertical and niche software much more cost effective.

In the last 3 months, I’ve built and launched a SaaS app to help my sister manage her florist business, and already have other paying customers. Without LLMs, this would have never been feasible because of dev time and/or costs.

Why eat up the context with an MCP when a ./docs/plans folder does the same?

In my experience this was an issue 6-8 months ago. Ever since Sonnet 4 I haven’t had any issues with instruction following.

Biggest step-change has been being able to one-shot file refactors (using the planning framework I mentioned above). 6 months ago refactoring was a very delicate dance and now it feels like it’s pretty much streamlined.

Exactly this. I clear the old plans every few weeks.

For really big features or plans I’ll ask the agent to create linear issue tickets to track progress for each phase over multiple sessions. Only MCP I have loaded is usually linear but looking for a good way to transition it to a skill.

As the models have progressively improved (able to handle more complex code bases, longer files, etc) I’ve started using this simple framework on repeat which seems to work pretty well at one shorting complex fixes or new features.

[Research] ask the agent to explain current functionality as a way to load the right files into context.

[Plan] ask the agent to brainstorm the best practices way to implement a new feature or refactor. Brainstorm seems to be a keyword that triggers a better questioning loop for the agent. Ask it to write a detailed implementation plan to an md file.

[clear] completely clear the context of the agent —- better results than just compacting the conversation.

[execute plan] ask the agent to review the specific plan again, sometimes it will ask additional questions which repeats the planning phase again. This loads only the plan into context and then have it implement the plan.

[review & test] clear the context again and ask it to review the plan to make sure everything was implemented. This is where I add any unit or integration tests if needed. Also run test suites, type checks, lint, etc.

With this loop I’ve often had it run for 20-30 minutes straight and end up with usable results. It’s become a game of context management and creating a solid testing feedback loop instead of trying to purely one-shot issues.

Did some early qualitative testing on this. Definitely seems easier for Claude to handle than playwright MCP servers for one-off web dev QA tasks. Not really built for e2e testing though and lacks the GUI features of cursors latest browser integration.

Also seems quite a bit slower (needs more loops) do to general web tasks strictly through the browser extension compared to other browser native AI-assistant extensions.

Overall —- great step in the right direction. Looks like this will be table stakes for every coding agent (cli or VS Code plugin, browser extension [or native browser])

Is there a good list of major health issues associated with space flight?

Would be interesting to see what still needs to be solved for multi-year stays.