mosselman

When I tell Claude or open code using Kimi or codex to fix something on my raspberry pi, they all go to ssh right away.

I found that most things that are “features” in harnesses and tools that don’t relate to UI and UX in those harnesses themselves can be done through skills or just prompts.

A nice features of Claude’s is the remote control through the mobile app. That isn’t just a skill.

You are describing 'the blame should be on Windows'.

The consequence of Windows having the blame is that one should not buy it.

This is so cryptic that I wouldn't even know if for or against would mean for or against 'chat control'

This is an incredibly good idea. 90 days is too short to feel the effects of some things though. Better make it a year.

The downside is "lets try giving everyone basic income of $100k/week". But apart from that great!

I think Anthropic has been really successful in their branding of Mythos as something, mythical.

I never heard anyone contemplating "why people are so sure we'd get freely available GPT-4 level+ models".

Mythos is just another advancement in AI model capability. If we start pretending like it isn't, we are setting ourselves up for paying far more than is reasonable and accepting the frame that we should not in fact have free access to open models with the same capabilities.

This is just marketing.

I can't wait for some similar big steps in open weight models.

Update since the side thread blew up.

There is some difference in how OpenAI and Anthropic handle 'max_tokens'. The OpenAI way raises errors in Anthropic for example.

I will look at confirming this a bit more in depth once we've taken our RubyLLM based adapter in production and see if I can make some contribution.

Thanks for all the work! It is incredibly impressive and I never meant any disrespect.

Thanks for the discourse. I never meant it to be disparagement nor do I think it really was.

I checked and it turns out I remembered correctly that setting effort and some of its settings are not portable between providers.

There are some different settings that each provider uses and in order for it to be portable, you have to force some defaults on provider A when using a setting that is almost only supported in provider B.

In our implementation we decided to drop a certain setting when using OpenAI in one case and we decided we can just force some other setting when using Anthropic. But this 'solution', might not be what others expect.

When you build an open-source library you can go this opinionated route and force these settings, or you might go the config route and force people to explicitly handle per-provider differences. I will have a look at what I am able to do in terms of a contribution and then in the PR Carmine can decide what they like.

We had already implemented tool_calls in our own database and have a system that executes them and creates our conversation array, etc. So we wanted to leverage the providers that RubyLLM supports without having to change the tool execution in our platform.

Hi! Valid challenge, I am probably misremembering. We were playing with various 'one-interface to all providers' solutions and I might have mixed up RubyLLM there. Sorry for that.

I will have a deep dive into which things I felt we needed to adapt per provider.

I didn't mean to imply that you have to solve all of our wants of course.

One thing we did do was monkey-patch the spot where tool_calls are performed by RubyLLM. We had our own mechanism for that and were able to skip RubyLLM's and still extract the tool calls and run them through our own tool harness. That all worked beautifully. I don't know if that type of stuff is something you want PRs on or that you want to keep steering towards the route that does everything within RubyLLM classes. Happy to contribute some of that.

It is quite nice, but not as nice as you'd want. You still have to set platform specifics when running completions when you want to tune things like temperature, effort, max tokens, etc.

what a nonsense, generated, article.

For context: GLM 5.1 ran the same task and reached 7.3x. Kimi K2.6 reached 5x. DeepSeek V4 Pro reached 3.3x. The models that stopped early did so because they issued no tool calls for five consecutive rounds, they concluded they couldn’t make further progress and stopped. Qwen3.7-Max didn’t stop.

By this reasoning I could release a model that lacks all the basic optimisations. Have it optimise itself for hours to reach 20x the throughput and then claim that the model is superior to the others?

I am not saying that is what happened here, but the reporting is abysmal.

So all that needs to happen now is that The Doors will do another tour and I am in!

They aren't I saw my own avatar.

I am super impressed by this. The landing page is GREAT, it really shows you what it can do and I tried creating a polypad and it works just as well as the landing page makes it seem.

I would have loved to have this when I was in school and I can imagine it is a great tool for teachers. I am going to let my kids play around with this.

In rereading my comment it sounds like some sort of lame ad, which I can assure you it isn't. I am just excited about it.

How come I see my own github avatar in the designed editor along with others? I assume people also visiting the builder? Not very cool if I may say so.

You even traveled in time to deliver us this benchmark.

I really like this benchmarking. Have you evaluated the judge benchmark somehow? I'd love to setup my own similar benchmark.

I would like to second this solid advice.

I have a very nice grinder: a solis caffissima digital coffee grinder. It is available under a different brand name in the US I think.

I make filter coffee with a very basic earthenware filter holder with melitta high quality yet very normal filters and sometimes I mix it up with an aeropress which offers a different type of taste because of the low acidity way of making coffee. I just drip the coffee into a nice thermos so I can make 4 cups in one go and just pour from the thermos.

My coffee is much nicer than I get in most places, both professional and at homes and it doesn’t cost me a lot in effort, money and, very importantly, workspace footprint.

Espresso machines require a lot of space and maintenance and trouble to make.

Having said all this, I am quite intrigued about all the stories about the negative effects of coffee. I just thought it was about influencing sleep, but I had never thought about the memory and mood effects. I will study this some more in the coming months.

Does this have a unified API? In playing around with some of these, including unified libraries to work with various providers, I've found you are, at some point, still forced to do provider-specific works for things such as setting temperatures, setting reasoning effort, setting tool choice modes, etc.

What I'd like is for a proxy or library to provide a truly unified API where it will really let me integrate once and then never have to bother with provider quirks myself.

Also, are you also planning on doing an open-source rug pull like so many projects out there, including litellm?

Just look at the second file in the list then I guess.

This post is about exploring code, not documentation. Nobody is going to warn you about the README unless it is super outdated.

You should be concerned about a government issuing these ridiculous and dangerous controls on what you can do in society. Not whether, within that dystopia it is fair to submit in one way or another.

Also, kids understand perfectly well that different parents have different rules.

I don’t think the government or Apple should be responsible for protecting you from mopey teenagers by blocking free internet access for everyone just so that it “is fair”. Are you even hearing yourself?

So if someone kicks you in the nuts (apt for your username) you shouldn’t be mad because some other person 10000km away got shot?

No, a new keyboard is between 12 and 50 euros depending on where you get it, the video is the missing piece.

Someone posted a video on how to slam out the rivets with a screwdriver.

I use the Claude Chrome extension for this. Works wonderfully. It lets Claude click through features itself, etc.

512GB at Mediamarkt. The 1TB is 1950 euros and the 256GB costs 1500 euros

This phone costs 1700 euros here... 1700 (Netherlands)! That is the price of a gaming laptop!

Everything has become so incredibly expensive it just isn't fun to buy anything anymore.

My iPhone 11's FaceID broke a few weeks ago and despite that I think I will just stick with it with today's phone prices.

Very fun. You have hidden the controls on the video, is it because you want it to be more of a game and prevent people, normies at least, from seeking through the video or is it for some other reason?

I've been working on my local server mocking tool Decoy: https://decoy-app.com/

I've built it earlier and also did a Show HN, now I am going through some of the steps that get recommended to me such as creating Product Hunt launches, etc. But I am struggling a bit with the concept of PH. What is the audience? People into new apps? It all feels a bit desperate to be honest and this app is just a hobby side project, I am not.

So if anyone knows of a good way to get some attention to my useful fun tool, please let me know.

I feel like the audience of the file is more for me the reader rather than the LLM.

Add this file to your AI assistant's system prompt or context to help it avoid common AI writing patterns.

So if I put this into my LLM's conversation it is like I am instructing it to put this into its AI assistant's system prompt, so the AI assistant's AI assistant.

The alternative is to say:

"Here is a list of common AI tropes for you to avoid"

All tropes are described for me to understand what that AIs do wrong:

Overuse of "quietly" and similar adverbs to convey subtle importance or understated power.

But this in fact instructs the assistant to start overusing the word 'quietly' rather than stop overusing it.

This is then counteracted a bit with the 'avoid the following...' but this means the file is full of contradictions.

Instead you'd need to say:

"Don't overuse 'quietly', use ... instead"

So while this is a great idea and list, I feel the execution is muddled by the explanation of what it is. I'd separate the presentation to us the user of assistants and the intended consumer, the actual assistants.

I've had claude rewrite it and put it in this gist:

https://gist.github.com/abuisman/05c766310cae4725914cd414639...

Fair question. The reason I built Decoy is that I wanted a good looking native macOS app. I hadn't really considered Mockoon to be honest, but looking at it now I can see a few differences that might be worthwhile in choosing between the two.

Decoy is 10 MB vs Mockoon's 329 MB and looks and feels differently because it is a native vs cross platform app.

Mockoon seems to have lots of great features such as online mocks and proxies for which you can pay their monthly fee or you could have a lighter weight app that does one thing well natively for a one time fee purchase.

I also notice that Mockoon calls home even when I don't have an account, probably for some sort of tracking. There is no tracking in Decoy.

So overal I think it is about lightness of the applications and UX.