tra3

Fascinating! Thank you for the links.

Never been, but the titular burning man installation comes to mind.

> Similarly, I always provided a safety net where students can make mistakes and resubmit a limited number of assignments to regain lost points (a core recommendation of specifications grading and grading for equity to focus on learning outcomes, not the process), but we felt that this process was abused with AI: first submit a generated assignment solution without thinking and only look at the issues raised in grading for a resubmission (the typical story of externalizing the cost of AI use).

This is how we do PRs now.

I think it's worth more scrutiny today, rather than less. Your claude code can barf out "a rewrite" but is it any good? So far the answer is "no" (see anthropic's C compiler, or a more recent port of bun).

Software is still the best specification for existing behavior..

Like taking a train or a plane or a bus? Like having to purchase a vehicle? Like having phone companies know which cell tower you're connected to?

It's a valid point you're making, but we can legislate against the abuse you're implying. We've got privacy laws for a reason.

Love LLMs gonna keep using them. It feels like your suggested approach is expensive, in terms of tokens. I feel (second time I say this) that when I steer the process I get pretty good results vs my coworkers that let the LLMs run away. I do have data on our token usage, not much in terms of quality of the delivery.

I keep thinking about the c compiler implementation that anthropic shared earlier in the year that had all the requirements you mention and arguably wasn’t that great.

Wait, what? With plan on, I at least get the illusion of being in control.

What’s the best way to sandbox Claude on macOS without it being a huge hassle?

This goes against the agentic yolo approach tho.

All I can think of is

GET /ignore-all-previous-instructions.

How do you protect against that?

I'm embracing the AI future we live in. It should be possible to build great software with AI. AI is good at code generation, but not testing. That's the other part of the equation we seem to be forgetting.

With the first and only commit 2 hours ago, the author of this project didn't let it "bake". They didn't exercise it locally to see what issues it might have, and I have a hard time believing the very first iteration of this software is perfect. With how easy it is to prompt/push anything, I'm not interested in engaging with anything that hasn't aged a bit.

At this point I tried a few of these that I could run locally and they weren’t useful. I end up manually managing context. It’s somewhat annoying, and I’m sure there’s an elegant solution out there.

I’m not even willing to try this one, I already ship my data to Anthropic I’m not keen to introduce another actor.

Perhaps "Using spaced repetition systems to see through a piece of mathematics " [1] might be of interest for you. I have read author's "Augmenting Long-term Memory" [2] and have incorporated a lot of his advice into my Anki practice.

For me, it's quick access recipes (breakfast pancakes for kids), what was the name of the glacier that we hiked to last year, behavioral prompts etc.

1: https://cognitivemedium.com/srs-mathematics

2: https://augmentingcognition.com/ltm.html

One of the oldest open source projects in the existence?

It makes building custom UI workflows so easy, I think it’s both obvious and flies under the radar.

I would love to see an analysis of how valve's openness and goodwill affects their bottom line. Intuitively it should be a net positive for them, but there gotta be upfront costs, otherwise everyone would be doing it too.

Maybe this one? https://media.ccc.de/v/39c3-breaking-bots-cheating-at-blue-t...

Hoping op will confirm.

I will settle for a slightly larger iPhone that unfolds into a iPad mini.

I've been dragging my feet on upgrading my M1 Air, guess now I'm just going to wait a bit longer. Truth be told, it's still sufficient for web dev but I figured at ~5 years old I should upgrade it..

I’m not familiar with this, but what does “solved” mean in this case? Guaranteed inability to compromise systems?

Plot twist, it was artisanally typed in emacs.

Question for the wifi experts in this thread...

What's a good off the shelf multipoint wifi system these days? I have Amazon's Eero right now and it's ok.

I'd love to go back to my linksys wrt54 roots but that's not in the cards currently..

I say this as someone who's found LLMs incredibly beneficial.

Is this a way to increase token burn?

I thought we covered this with Claude's C compiler. What changed?

When every prompt produces a thousand line PR, you’re not very far from another million line monolith.

I’m a little more hopeful than the author though. I feel like it’s possible to manage the process so that does not happen.

Maybe Nov.el could be an inspiration: https://depp.brause.cc/nov.el/

There's definitely a way to use Claude code that is token conscious.

I've tried throwing unsupervised agentic software factory workflows against the wall, and they burned through my tokens like nobody's business but didn't produce much.

Supervised, human-in-the-loop process on the other hand is much more productive but doesn't consume nearly as much. Maybe that's why everyone's pushing agentic approaches so much.

Ya'll should checkout https://everynoise.com/. Similar in spirit.

Just read the update:

> 2024-01-05 status update: With my 2023-12-04 layoff from Spotify I lost the internal data-access required for ongoing updates to many parts of this site. Most of this, as a result, is now a static snapshot of what, for now, will be the final state from the site's 10-year history and evolution..

what a shame. I didn't realize the author worked for Spotify. Guess it makes sense. Spotify should've acquired it from the author or made a deal with him to keep it live since all the links lead to Spotify anyway.

You’re exactly right..that’s how I end up learning tech stuff. It’s not working very well with modelling though. I’ve set my sights too high, the projects are too involved

This is gorgeous. I really need to hunker down and learn 3d modeling. It unlocks so many options from cnc to 3d printing.

You bring up a good point -- I have the same issue with mouse keys. I wonder how the track point gets around this. Is the tracepoint "progressive" in that it allows various speeds depends on deflection from center?

Yes, of course. I’ve accidentally fallen down the split keyboard rabbit hole and now I can’t get out. UHK seems like it’s got everything that I might ever need but I’m going to stick with my Aliexpress Corne for a bit longer before I take the plunge.

Ultimate hacking keyboard has modules that include a track point, touchpad or a trackball. I’ve been eyeing it for a while: https://uhk.io/

Kanata has mouse emulation so you can drive a mouse using arrow keys: https://github.com/jtroo/kanata/blob/main/docs/config.adoc#m...