tymonPartyLate

This post is clearly an ad disguised as a technical article, but Conductor is a fantastic tool, so I'd like to post some questions regardless. How can they have product-market fit if this is a free product? How can they know the customers' willingness to pay for it there are no payments? Or has it been tested? How can this be worth a $ 22M series A if its a UX layer on top of Claude that can be easily copied by Anthropic?

I try to see this like F1 racing. Building a browser or a C compiler with agent swarms is disconnected from the reality of normal software projects. In normal projects the requirements are not full understood upfront and you learn and adapt and change as you make progress. But the innovations from professional racing result in better cars for everyone. We'll probably get better dev tools and better coding agents thanks to those experiments.

The worst crime for me is liquid glass on the apple watch. All the menus are now lagging on the watch ultra gen2. Where previously it was smooth to interact with, the random lags now make it annoying and inconvenient to interact with. (I need to focus my attention on the Ui state instead of following an automatic procedure from muscle memory)

The battery sometimes randomly drains within less than a day. There are absolutely no benefits of the new visual effects.

The watch was my favorite apple device because it helps me to reduce screen time on the phone. Now it is a source of anger.

The biggest threats to innovation are the giants with the deepest pockets. Only 5% of chatgpt traffic is paid, 95% is given for free. Gemini cli for developers has a generous free tier. It is easy to get Gemini credits for free for startups. They can afford to dump for a long time until the smaller players starve. How do you compete with that as a small lab? How do you get users when bigger models are free? At least the chinese labs are scrappy and determined. They are the small David IMO.

If you want reliable Wifi at home, get yourself Ubiquity access points and throw away TP-Link. The issue is not the protocol. After many years of unplugging and plugging back in my TP-link router I know that they are cursed.

Interesting tech choices. I am also always on the hunt for React alternatives. But the lack of type safety and static analysis usually leads to brittle templates. Stuff that could be expressed in verifiable code, is compressed in annotations and some custom markup. You need to manually re-test all templates when you make any change in the models. How do you deal with that?

Btw, very cool project. Deployments for simple projects are a huge time sink.

I did just that and I ended up horribly regretting it. The project had to be coded in Rust, which I kind of understand but never worked with. Drunk on AI hype, I gave it step by step tasks and watched it produce the code. The first warning sign was that the code never compiled at the first attempt, but I ignored this, being mesmerized by the magic of the experience. Long story short, it gave me quick initial results despite my language handicap. But the project quickly turned into an overly complex, hard to navigate, brittle mess. I ended up reading the Rust in Action book and spending two weeks cleaning and simplifying the code. I had to learn how to configure the entire tool chain, understand various cargo deps and the ecosystem, setup ci/cd from scratch, .... There is no way around that.

It was Claude Code Opus 4.1 instead of Codex but IMO the differences are negligible.

We used to have private bridges and private roads, and that was an expensive travel situation for everyone. Now, internet search is kind of like a bridge that leads clients to businesses and Google is deciding on the tolls. Government-controlled Internet search would definitely be horrible. But I'm thinking if there is a path towards more competitiveness in this landscape, maybe the ISPs could somehow provide free search as part of the Internet service fee? Can we have more specialized, niche search engines? Can governments be asked to break up the Google search monopoly?

Thanks for sharing, I'll copy your rules :)

I just realized that Opus 4 is the first model that produced "beautiful" code for me. Code that is simple, easy to read, not polluted with comments, no unnecessary crap, just pretty, clean and functional. I had my first "wow" moment with it in a while. That being said it occasionally does something absolutely stupid. Like completely dumb. And when I ask it "why did you do this stupid thing", it replies "oh yeah, you're right, this is super wrong, here is an actual working, smart solution" (proceeds to create brilliant code)

I do not understand how those machines work.

This is actually not true. I'm getting traffic from ChatGpt and Perplexity to my website which is fairly new, just launched a few months ago. Our pages rarely rank in the top 4, but the AI answer engines mange to find them anyways. And I'm talking about traffic with UTM params / referrals from chatgpt, not their scraper bots.

I asked it once to simplify code it had written and it refused. The code it wrote was ok but unnecessary in my view.

Claude 3.7: > I understand the desire to simplify, but using a text array for .... might create more problems than it solves. Here's why I recommend keeping the relational approach: ( list of okay reasons ) > However, I strongly agree with adding ..... to the model. Let's implement that change.

I was kind of shocked by the display of opinions. HAL vibes.

Haha. Hopefully you’re right and solving the ARC puzzle translates to solving all of physics. I just remain skeptical about the OpenAI hype. They have a track record of exaggerating the significance of their releases and their impact on humanity.

Isn’t this like a brute force approach? Given it costs $ 3000 per task, thats like 600 GPU hours (h100 at Azure) In that amount of time the model can generate millions of chains of thoughts and then spend hours reviewing them or even testing them out one by one. Kind of like trying until something sticks and that happens to solve 80% of ARC. I feel like reasoning works differently in my brain. ;)

We rely on a multi-layered validation approach, where multiple independent sources must confirm any given data point before it’s presented. Aravind described this well on the Lex Fridman podcast. Behind every green dot is a chain of LLM prompts, reviewers, and “critics” ensuring accuracy. On top of that, user feedback and browsing patterns continuously refine the system’s weighting, so recommendations get better over time. We’re also working on a feature to show which tools your competitors are using. I think this will be really great.

Sure, Perplexity can present a simple table, just like it can list hotels, but you’d still visit Expedia to finalize your booking. There’s more to making informed decisions than just seeing a list of options. Right now, we’re focusing on surfacing deeper insights: detailed features, aggregated review summaries, and company health. Our goal is to go beyond a basic search and provide all the data points you need :)

Hi HN, In my previous role as a CTO at an Uber-like scaleup, I had to manage and evaluate around 60 different SaaS subscriptions. It was painful. As software engineers, we’re often asked to help select all sorts of software—payroll, payment processors, marketing automation, CX tools, call center software—tasks really meant for domain experts. This problem is universal, affecting businesses of all sizes. The SaaS landscape, unfortunately, is drowning in marketing fluff, biased paid reviews, and general noise.

So I built an AI to cut through it. Under the hood, we classify 4 million reviews to extract real signal. We use GraphRAG and a chain of LLMs to ensure quality. Similar to Perplexity, multiple independent sources must confirm each piece of information before we trust it.

Like Garry Tan (YC) suggests, chat interfaces might not be the future. Users prefer familiar UX, and the next evolution of the internet should be intelligent sites delivering personalized content. You’ll still get the benefits of LLMs—just in a more digestible format.

We started by tackling comparisons first. No two SaaS tools are the same, each with unique features and target markets. Our comparison engine alone can save you hours of research. Next, we plan to add a product discovery module to guide you to the perfect tool.

I believe that until AGI is widespread, business will continue as usual. Vertical AI agents will need to integrate with familiar SaaS products—how else can they coordinate work? Even AIs will need Trello, Gmail, Slack, Your CRM and the existing boring toolbox. Meanwhile, the amount of new software hitting the market will soar, making comparison and distribution harder than ever.

We’re VC-backed, and our guiding principle—our “don’t be evil” policy—is to provide unbiased software recommendations. Our long-term vision is to offer premium buyer features and competitive intelligence. Eventually, we’d love to integrate with AI providers for seamless migration, integration, and customization support.

Some examples: Linear / Trello https://gralio.ai/compare/Trello-vs-Linear Notion / Clickup https://gralio.ai/compare/Notion-vs-ClickUp Gusto / Rippling https://gralio.ai/compare/Gusto-2-vs-Rippling Webflow / Retool https://gralio.ai/compare/Retool-vs-Webflow

Let me know what you think!

Cody plugin is a great alternative if you prefer Jetbrains IDEs. I've tried cursor several times and the AI integration is fantastic, but the plugin quality is low, navigation and refactorings are worse for me and I'm struggling to configure it the way I like :(

Clicking sends a websocket message to the backend. Which then responds with a state update message which updates the frontend react components. rhe round trip would probably take the same time with rest APIs, but you would have the ability to add some loading indicators or hints, because you'd have full control over client side rendering. You don't have that when using pynecone. It's a tradeof

It's a beautiful project and close to the Holy grail of fullstack software development (a single framework for building modern Web apps).

But, be advised that it's not production ready and quite unstable yet.

this week my deploy script was broken because version 0.1.26 was un-released. Which broke my docker file build with pinned dependencies.

The file upload component was changed a few times so my UI with file uploads silently stopped working.

I had some issues when state binding input components. Which lead to the backspace key no longer working inside a text box.

The websocket state updates can make the ui feel sluggish.

Despite all that, I love this framework and will continue tinkering with it. It hope it can grow to maturity before people lose interest!

This is fantastic, congratulations! I tried it on some AWS related issues I was googling at work and it gave me the correct answers right away. I hope you can find a reasonable way to monetise. Kagi search was not enough of a value add to me to be worth 9$ per month. But I'd happily pay for usage based pricing for a specialised tool like this.

I'm currently tinkering on a customer support bot with langchain and gpt3. The bot can answer questions about services and their terms, it can use tools to make bookings and perform some taks like scheduling appointments, in a conversational manner. It's becoming clear to me that subtle changes in the prompt can lead to bullshit answers and gpt making up facts, despite being specifically told not to do so. If the prompt reaches some complexity threshold, the output quality goes down visibly. I learned that I have to split the bot into subtasks, each having different, smaller, prompts. So, yeah, I believe prompt engineering can be a thing. At least for a while, until the models become smarter at understanding what we want from them :)