james2doyle

There are actually quite a few elements failing the Lighthouse accessibility audit.

This page also has 26 emdashes on it. For a page that isn’t an article, that seems pretty high.

Been using this and GLM 5.2 back and forth. I like the speed of Hy3. Also seems very happy to follow instructions. Still haven’t found any open models that follow instructions as good as Mimo v2 pro though

What if your measure is cost? Or zero-data-retention? Or diversity of inference providers?

On those measures it is better.

Yeah sounds like maybe you got stuck in a loop? If you’re a big Deepseek fan, check out their Codewhale harness. It is actually really slick and you can use your OpenRouter account with it.

You can use any model you want but it is really tailored to work well with the Deepseek duo

Tokens and speed are a factor but does it require less back and forth to get things right? Being "fast and cheap but wrong" still has a cost that an otherwise "expensive and slow" exchange does not

I can’t get any tool calls working. Seems to use a `<longcat_tool_call>` wrapper which the current harnesses I’m using don’t support

Oh, usually when that is announced the stealth model updates to the unmasked one. They did that with "Ling 2.6 flash" which was elephant-alpha. I guess we may see an update today then

Do they still have that issue where it will randomly spit out a string of emojis when using voice to text?

We sound similar. I have found that the voice to text can often just randomly start spitting out emojis. Did you find that?

There are some demo spaces using this. This one seems the best (paint your own mask) but it failed on all the images I tried: https://huggingface.co/spaces/multimodalart/Moebius

Like this? https://huggingface.co/spaces/multimodalart/Moebius

Had to disagree with that. However, I don't think you can discount how much Anthropic has been banging the drum about how AI is dangerous (specifically theirs) and an existential threat, etc. etc.

The rollout of Mythos was clearly manufactured to stoke the fears of companies that didn’t have access to it. They also bragged (for Fable) about how they "ran an external bug bounty that produced no universal jailbreaks in over 1,000 hours of testing" only for it be circumvented almost immediately.

So them standing on the high horse and saying it is _so powerful, yet so safe_ only to have that blow up in their face just made it that much easier to make an excuse to do this. Again, not disagreeing, but they made themselves the tall poppy here.

Just last week you could distill using other users responses! Handy!

I think the stronger incentive is undermining/undercutting the Western AI companies. Given what we have seen, any model can be used/convinced to do harm so that is just part of the game

Yeah, so true. There is no moat to your competitors using the exact same tools and prompts to generate their apps and services. Companies should be hiring/retaining creative thinkers that give them that human edge rather than laying people off under the guise of "improved efficiency"

How’s that meme go? "We are 2/3 years into being 6 months away from AI taking all white collar jobs".

The criticism goes both ways. The word "fixed", in Ed terms, can be translated to "become a viable business that justifies the spend".

In regards to AI video, I think the fact that Sora is no long around is an indicator. And there is seemingly no real appetite for AI video outside of memes, jokes, and misinformation, probably indicates that the prediction around AI video has come true.

Absolutely. Even these days, Uber really only has one or two viable competitors. With any 3rd one in a far distant 3rd. Meanwhile, swapping which AI I’m using is as easy as clicking a dropdown. Hardly comparable to a physical car ride.

Maybe I’m a wierdo but I actually like the Brave version of their Search + AI solution: https://search.brave.com/ask

After switching between Perplexity, Phind, and a couple others, it seems like the best balance for my use.

You can always just use the regular Brave search. It does seem to include an AI summary by default, but you can turn that off: https://search.brave.com/settings#:~:text=Make%20AI%2Dpowere...

I find it is grounded in facts (based on the results) more and doesn’t typically make stuff up. I am usually using it for things I am more well versed in (web dev) so I have a baseline knowledge to draw from.

I’ve used djlint on a liquid project and it worked well. It supports twig too: https://djlint.com/docs/languages/twig/

They also have an online demo/playground so you can at least give it a shot to see if it works.

I’ve used the twiggy LSP before and there seems to be a few VS code extensions for it: https://marketplace.visualstudio.com/items?itemName=moetelo.... and https://marketplace.visualstudio.com/items?itemName=Stanisla...

I’m always surprised by how performant the Cohere models are. They output quick. I tested out the BF16 and it seems pretty good. I tried out the FP8 one and it did seem a bit dumber. Curious to see how this ranks in benchmarks

Maybe look at https://void.cloud/ (Edit: sorry, meant https://viteplus.dev/, not Void cloud)

They are not a runtime, but they do seem to be interested in wrapping a lot of tools with simple top-level commands

There seems to be a "neuter" fork out there that disables a bunch of stuff: https://github.com/GarethCott/warp#whats-different-from-upst...

Looks like there is a "neuter" fork out there: https://github.com/GarethCott/warp#whats-different-from-upst...

There have been a number of people leaving them because of that bait and switch it seems. That 20% turned out to be something closer to 2% or even 1%

I noticed that too. I’ve been using cmux (based on ghostty, has a more basic UI) and have been happy with it: https://cmux.com/

I feel similar. I have been using cmux over the last few weeks: https://cmux.com/

Seems to fit a good balance for the way I want to use my terminal

You’re paying the subsidized cost. Those margins will shrink once the real bill comes due. I really think everyone will look back at this time as the golden area of cheap AI. We are already seeing the costs (and restrictions/limits) creep up with the Western models.

In the next round of ChatGPT advertisements, if they don’t use AI generated images, then that means they don’t believe in their own product right?

I think "better" is doing a lot of heavy lifting in this argument. Better how?

Is an AI generated photo of your app/site going to be more accurate than a screenshot? Or is an AI generated image of your product going to convey the quality of it more than a photo would?

I think Sora also showed that the novelty of generating just "content" is pretty fleeting.

I would be interested to see if any of the next round of ChatGPT advertisements use AI generated images. Because if not, they don’t even believe in their own product.

You should check out "model collapse". It seems that an abundance of content, that is more and more AI generated these days, may not be a viable option. There is also a vast amount of data that is increasingly going private or behind paywalls