taylorfinley

Came here to flag the same beat. It's wild to me Terrance Tao has to pay to talk to chatgpt, you would think it would be the other way around!

This is a really cool project. Is there any way to contribute data?

Hawaii's artifacts have been displaced far and wide, The British museum alone has a stunning collection that usually sits in a basement, e.g. a small sample of their collection documented here:

https://www.artoftheancestors.com/blog/hawaii-british-museum

Let me share a couple demos, with the caveat that this project is very much still a beta. There's a bug report/feature request button in-app, so if you notice anything egregious feel free to reach out there.

[0] Building a hubless bucky ball dome. It's a bit deceptively-simple, because the agent only has to call the procedure with the right values. That's an intended flywheel: agents and users can save procedures to a community library, and future agents can discover and invoke the pre-existing procedures, instead of re-deriving them. They can copy and edit the procedure as needed, so it basically becomes a RAG library for carpentry procedures written in the project's DSL.

[1] A sawhorse, re-implemented by Opus 4.8 from plans published by Home Depot. Now saved as a procedure so you can drop a sawhorse anywhere you need one.

[2] A small shed with stick frame walls and a lean-to roof.

[3] The Picture frame prompt mentioned in my first comment.

Quick note: I recently broke the smart de-duplication for step-by-step playback, so it will show every single cut, one by one. Hit "stop" and then click the final frame in the timeline to see just the finished state.

[0] https://sawdust.diy/share/b0de719c-0e9f-4f4f-9282-085c521163... (bucky ball dome)

[1] https://sawdust.diy/share/45557307-0f78-4b5b-bf0e-eae77a9853... (sawhorse)

[2] https://sawdust.diy/share/cbb591fc-5511-40d9-8ccd-0d9f8c10be... (shed)

[3] https://sawdust.diy/share/ba109216-8849-49e3-ae9c-5a15982d24... (polygonal frames)

It's a woodworking simulator. There are tools (tape measure, pencil, miter saw, table saw, jigsaw, drill, router) and wood stocks (2x4s, plywood).

There is a chat window and human UI similar to SketchUp. You can task the agent with using the tools and assembling the project, or do it yourself. It outputs real cad files, plans, and a build guide video.

Qwen 3.6 has been great because it's multimodal and good at tool calling. As it builds it can get screenshots and all that. The basic output is an operation list with real measurements and bevel/angle settings and the like.

I've been using Qwen3.6-Plus in my carpentry-simulator agent harness. That model performs pretty well, but not at Opus 4.7 levels. I will try 3.7 Plus when the pricing is announced and report back.

I use Qwen3.6-A3B locally on my Strix halo for testing simple prompts like "make the largest polygonal picture frames you can, each from a single 8 foot 2x4. Start with 3 sided and go up from there, lay them all out in a 9 by 9 grid."

It's a cheap (off-grid solar power, so ~free) way to sharpen the harness: if less-than-SOTA models can succeed then the tool surface is clear. Bumping up to 3.6 Pro has been a nice middle step closer to the frontier models without spending an arm and a leg on credits.

I had a similar experience recently while helping my 5 year old daughter vibe code a sandcastle-themed tower defense game (https://sandcastles.finley.lol).

I ended up thinking it might be easier to generate rigged models, animate them, and capture from an iso perspective, then do some kind of pixel art style transfer on the masked sprite sheet. Eventually I realized my kid didn't really care too much about the visuals so I didn't get too far with it.

Don't have too much fun with this: https://en.wikipedia.org/wiki/EICAR_test_file

Surely they are testing their optimizations against common benchmarks internally? I bet the "real world task" degradation is larger by some multiple than it appears when measured through a benchmark that is part of the target.

I've noticed this and thought about it as well, I have a few suspicions:

Theory 1: Some increasingly-large split of inference compute is moving over to serving the new model for internal users (or partners that are trialing the next models). This results in less compute but the same increasing demand for the previous model. Providers may respond by using quantizations or distillations, compressing k/v store, tweaking parameters, and/or changing system prompts to try to use fewer tokens.

Theory 2: Internal evals are obviously done using full strength models with internally-optimized system prompts. When models are shipped into production the system prompt will inherently need changes. Each time a problematic issue rises to the attention of the team, there is a solid chance it results in a new sentence or two added to the system prompt. These grow over time as bad shit happens with the model in the real world. But it doesn't even need to be a harmful case or bad bugged behavior of the model, even newer models with enhanced capabilities (e.g. mythos) may get protected against in prompts used in agent harnesses (CC) or as system prompts, resulting in a more and more complex system prompt. This has something like "cognitive burden" for the model, which diverges further and further from the eval.

I can see a market for virtual copies of incredibly unpopular CEOs, but I don't think Mark would like how people would likely choose to use these digital effigies.

I've actually switched back to the web chat UI and copying Python files for much of my work because CC has been so nerfed.

I've seen this frequently also

Right? Just add this to .bashrc:

alias yt-pl='yt-dlp -o "%(channel)s/%(playlist_title)s/%(title)s.%(ext)s" -a playlists.txt'

For both of these scenarios, it seems to happen when the context limit is getting full and the context is summarized. I've found it usually works to respond with the right file, i.e. "great, let's apply those changes in @path/to/file", but it may also be a good time to return to an earlier conversation point by editing one of your previous messages. You might edit the message that got you the response with changes not linked to a specific file, including the file path in that prompt will usually get you back on track.

probably skips the step where you say "take a look at path/to/file" and the model converts that to a tool call

Are you trying to be cute? These were clearly stolen, a century passing doesn't make it any less a shameful crime.

I can't help but feel like this is a satirical send up of "tech bros solve farming," except it's not satire.

I am a software engineer, I also runs a small family farm. I have 3d printers and laser cutters and lots of aluminum extrusion and raspberry pis... but I keep those things indoors, away from the dirt, sun, and rain. I can't imagine a real farmer using a contraption like this. Tools have to be reliable to last. I have to replace my solid steel shovels every few years because they wear out, how is this supposed to work?

approximately 500 test cases were successfully converted, executed, and passed.

How many of these passing tests are still actually testing anything? Do they test the tests?

So the YC board found out Altman would be CEO of a for-profit OpenAI when it was publicly announced, just like the OpenAI board found out about ChatGPT when it was publicly announced. Thanks for the clarification!

My buddy was working on exactly the same project around then in Austin tx. He was trying to make it as a web app with access to location permissions, where the page's background color would change for each individual pixel in the virtual display. Concertgoers would visit the url and their phone would become a pixel in the screen. He was trying to figure out how to get better location resolution when we talked about it, sounds like you guys had similar ideas and both discovered the implementation was trickier than it initially seemed it would be. I wonder how many other folks worked on that idea around that time?

Don't want to ask you your name or location to preserve privacy, but do you happen to live near what used to be a really cool coffee shop, and do you have an awesome garage with a plasma cutter? If so I think you told me about this project a decade ago while we built a little backyard forge!

Note that statement says nothing about whether they will be allowed to participate in liquidity events

On top of that, IMO the vast majority of their value as a brand comes from the community that develops for and with the platform. See every review for the alternative SBC market (Orange Pi, Bana Pi, etc.) "Sure it's better/cheaper but they don't have the huge community..."

So, if they IPO, will they first be distributing equity to the community? Or are they just cash-grabbing a retirement play?

Yet another excuse to classify all the media on your device to show you more relevant ads?

Can anyone recommend one of the foss gallery apps available on f-droid?

I had a pair of $100 Anker ANC headphones physically break on me but didn't have the box to return them in, and the Ankers were out of stock. For some reason Walmart's returns department's solution was for me to find a different headset with the exact same price to swap. The only matching set was a Razer Barracuda X, and oh boy were they terrible. I have never hated a consumer product so much in my entire life.

These ANC headphones didn't support Bluetooth at all, while other models with the same name did. In 2024, for $100, a wireless headset that only functions with the included dongle?! I made peace with it and got used to swapping the dongle to each device I use. Because of the poor dongle design it couldn't fit in my phone without removing the phone's case, so I listened to podcasts with my case off. Within the first two days the dongle just completely stopped working. Complete garbage. Not only that but the audio quality was horrible, the microphone sounded like a rotary phone, they were huge and bulky and hot to wear. When I contacted support asking for a new dongle they emailed me back the same template six times from three different representatives as if I hadn't answered all of their questions each time, and they wanted me to send the entire headset back to get a replacement.

I left the experience thinking "Wow, this garbage company must hate their customers." Even after all that, I didn't realize they hated their customers enough to install bitcoin miners on their mouse drivers or to sell them fake N95 masks. The punishment here doesn't even come close to justice, if anyone got sick the executives in charge of bringing those masks to market should be held criminally liable.

I should definitely hope so! Though I think the name would cause a stir in local circles even without any legal actions. Tech companies in general are deeply unpopular here (see: Larry Ellison, Mark Zuckerburg, and Marc Benioff buying up big chunks of land, AirBnB and digital nomads driving up rental prices so high such that more native Hawaiians now live on the mainland than in Hawai`i, and perceived lack of cultural respect from projects like the Thirty Meter Telescope leading to major protests).

The other thing is that words have a lot of power in the cultural frame, even just the concept of aloha being something that could be "unleashed" is likely to offend.

All to say nothing off the palpable fear people have here of robots taking hospitality industry jobs like housekeeping (which are unionized in many hotels out here, and are actually one of the few low-barrier-to-entry jobs out here that can support a reasonable quality of life)

I'm sure I'll get a ton of downvotes for bringing up cultural sensitivity and pointing out these concerns -- I don't mean to imply they're all 100% rational nor that no one should say "aloha" unless they're Hawaiian, but if anyone at DeepMind had a Hawaiian cultural frame I think they likely would have flagged these concerns and recommended a different name.

I wonder if this unfortunate naming choice will cause a stir similar to: https://kawaiola.news/cover/aloha-not-for-sale-cultural-in-a...

Sorry, what about that would be dumb? Attempted reuse is exactly what would be prevented by scanning the barcode and seeing it had already been used.

This is exactly why gift cards have scratch-off material covering their secret keys, otherwise folks would just take a picture of the next card in the stack, wait for it to be funded, and then use it before the recipient does.

edit: And would you look at that, you can buy stamp sheets on Amazon.co.uk, and users have helpfully submitted a bunch of photos with barcodes visible.

The barcode in the article decodes to "JGB S11221017031011395940006622112101 BC046285E760466C01" if anyone fancies having a crack at making a stamp keygen.

I don't know how common this is, but for me pickles (and their juice) trigger intense disgust and involuntary gagging. If pickles were on the cutting board or touched the knife, I will not be able to enjoy the sandwich. When ordering a sandwich I'll always ask for no pickles on the sandwich or the plate/take out container. It seems I'm an edge case this system doesn't anticipate, I wonder how they handle pickle-averse customers?