Adrig

The Goal was such a fun read, the solution is always evident in hindsight but I found myself having small "aha" moments over and over.

Yes this works surprisingly well. Just a bit sad we have to block everything coming in by default

Haha yes HN is definitely one of the few untouched gems of the internet. Perfect for tech-related articles, less so for culture, science, politics and global news

I don't follow closely all these benchmarks but I would love to have some idea of the status of models for these specific use cases. Average intelligence is close for each mainstream models, but on writing, design, coding, search, there is still some gaps.

Even if it's not benchmark, a vibe test from a trusted professionnal with a close use case to mine would suffice.

Your point about ecosystem is true, I just switched main main provider from OpenAI to Anthropic because they continue to prove they have a good concrete vision about AI

I don't know about life-changing but to me there are two major benefits that get me really interested:

- Augmenting CLI with specific knowledge and processes: I love the ability to work on my files, but I can only call a smart generalist to do the work. With skills if I want, say, a design review, I can write the process, what I'm looking for, and design principles I want to highlight rather than the average of every blog post about UX. I created custom gems/projects before (with PDFs of all my notes), but I couldn't replicate that on CLIs.

- Great way to build your library of prompts and build on it: In my org everyone is experimenting with AI but it's hard to document and share good processes and tools. With this, the copywriters can work on a "tone of voice" skill, the UX writers can extend it with an "Interface microcopy" skill, and I can add both to my "design review" agent.

As a designer I'm following the space quite closely. In the not-so-distant future, we might skip most visual software and work directly with code. Especially if we have cool transitional solutions like this

I'm still wondering about how this approach would work when conceptualizing flows, systems, or more complex interfaces

There's also a regulatory component. No way hidden ads will be allowed in major markets like the EU.

I could see a sponsored section in the middle of the reply where the LLM just tells of these vendors align with what the user is looking for

I'm not sure about that. Reports have shown that models from China or Mistral can achieve 80% or more of OpenAI's performance for a fraction of the cost.

If you're tucked in right behind the absolute frontier models, the economics change completely

Good point, turns out I was using aliases wrong! It works with spacebar and makes it as easy to use as flow once you set it up.

F is not set as an alias by default tho

Nope, sorry. My main use case is app launch, finding settings, and some scripts. I don't use file search that much.

Small point for Flow here again, because you just have to use the prefix doc: to search through your files, whereas on Raycast, you need to set up an alias and enter the extension. Both have file preview

I'm currently trying both Raycast windows (beta) and Flow Launcher. I've never really used this kind of launcher before (just the highly frustrating Windows main search feature).

- Raycast has a nice UI that can expand to work well with extensions

- Flow is faster to use. With Raycast you often need to enter an extension to finish your action. To launch a scrip on Flow I just type "r [shortcut] -> enter" while Raycast is "quicklinks -> enter -> [shortcut] -> enter. [edit, with minimal setup using aliases, you can have similar speed. See __jonas comment below]

- Performance-wise, Raycast was often eating my RAM, but a dev mentioned it's expected in the beta, they'll fix it for the launch. Otherwise, both feel snappy

- Both seem to have enough community support and extensions

- I never really tried the AI features, I don't know if it's the right place for me to augment my workflow w/ it

Curious about the experience of others with these tools or similar ones

My mom recently praised the brave AI summary of a webpage so who knows, the usage might be higher than we think.

I want to love Mistral but never really used their products. What are they good enough for / great at?

I finally made DDG my main search engine because I use Perplexity for anything substantial. It works quite well

Not comfortable at all, but when you have serious medical issues this is the least of your problems.

For work, I assume everything is used for corporate espionage, so it depends on the sensitivity of the data. If my employers / clients authorize a tool it becomes their problem.

I'm a layman but it seemed to me that the industry is going towards robust foundational models on which we plug tools, databases, and processes to expand their capabilities.

In this setup OSS models could be more than enough and capture the market but I don't see where the value would be to a multitude of specialized models we have to train.

Their free plan might be just what I need. Thanks, I'll have a look

Thanks!

Since this isn't available yet on Windows, what would be the glue & duct tape alternative? Record audio and dump it in chatGPT? Or do you need to create some kind of automation with n8n / Zapier? I don't have that many meetings but it could be nice to have

It's definitely a difficult time to deal with these issues, especially when the world appears so unstable. But we eventually have to face the music one way or another. Best of luck!

I've dealt with chronic illnesses for the past 10+ years now. It's such a hard path.

I recently found out after a violent burn-out that a significant cause was chronic stress and its psychosomatic symptoms. It made me have a hard look at the topic, and I'm gradually adjusting to solve the issue.

If I get better, I'm tempted to do as OP and spend more time working on this issue for others. It seems so much more impactful than grinding the tech / startup life.

Two instances of crypto kidnapping happened recently in France just a few weeks apart. The first was the father of a crypto milionnaire who was rescued after a few days, missing a finger. The second is the daughter of a crypto CEO who fended off a kidnapping in broad daylight in the center of Paris, while she was with her husband and baby. Insane stuff.

This will only go worse and harder to protect from. Most of the instances I heard about were carried by "amateurs", which makes all this quite unpredictable.

This is about strengthening their own ecosystem (glasses, whatsapp), not attracting power users from competitors

Here's are a few you might enjoy! Living artists only to give them a little boost

Photography:

- Hideaki Hamada https://hideakihamada.com/works/?tab=grid

- Henri Prestes https://www.instagram.com/henrifilm/

- Liam Wong https://www.instagram.com/liamwong/

- lllonilll https://www.instagram.com/lllonilll/

- Trung Bao https://www.instagram.com/trungbaotr/

- Clémentine Ecobichon https://www.instagram.com/clementine_art_gallery/

Digital / generative art:

- Slap Comp https://www.instagram.com/slapcomp/

- Oprisco https://www.instagram.com/oprisco/

- michael murdock https://www.instagram.com/mjmurdoc/

Bonus, artists & illustrators:

- seongryul https://www.instagram.com/sseongryul/

- huihuabiji https://www.instagram.com/yaozh.i/

- Kris Ancog https://www.instagram.com/krisancog/

- August Sandström https://www.instagram.com/august.artwork/

- daisukerichard https://www.instagram.com/daisukerichard/

- Viktoria Prischedko https://www.instagram.com/viktoriaprischedko/

- Thomas Wells Schaller https://www.instagram.com/thomaswschaller/

- Little Thunder https://www.instagram.com/littlethunder/

It's sad to see him leaning into the rage bait..

I've followed him for years. He's always interesting to read since he's successful while being contrarian on many things about business and tech, but he's turning into a mini Elon Musk talking about "mind virus", "libtards" and "soyboys".

Why can't the internet go back to people talking about what they know? I'm tired to everything being politicized

To my knowledge, this feature / model is the only one without any relevant competitor. Why is that? It seems to open a ton of use cases to me.

This is where my expertise ends as a designer, sorry!

What I meant about small design system is also true on the code side, since a proper design system is this design / code mirroring.

This is where js frameworks help a lot since you can create components with properties and nest them, but that's about all I know about FE-eng

Design principles:

— Don't reinvent the building blocks of UI. It's mostly a designer problem than a dev problem but I often see folks reinventing navigation, buttons, or forms when the standard pattern would work fine. There is a high UX cost to breaking existing patterns.

— Think in flows, not screens. Gather the context for the starting point, the objective of your feature and create the path between them. I like using the job to be done framework for this

— Speaking of frameworks and tools, simple is almost always the best. Don't buy into a complex process designers came up to legitimate their job. Find out what to build and how to build it. Use reference, user interviews, data analysis, existing patterns and you'll be more than fine

Large components:

— Look into design systems, it's a whole topic. My advice for 90% of software companies is to have a small but robust design system with the basics well documented (typography, spacing, colors, basics UI components). Then jam with it depending on your needs. Extensive design systems require a dedicated designer and dev to maintain. More often than not, they end up as pure chaos without them.

Resources:

I have a ton, I put them all in a Notion list, feel free to check https://impasto.notion.site/Adrien-s-list

Meta has insane distribution. Even if they don't match the best AI integration in a couple of months, they can push it to 1 billion people in days when it hits.

Same thing for AR/VR, they can afford to invest massively in different plans, use cases and form factors. Fitness, work, social, metaverse, gaming, hardware... It's a collection of bets and in this day an age, one great product-market fit can scale into billions of revenue.

In a recent interview Zuck stated that he was surprised by how well the RayBans worked. It's also a great synergy with this new wave of AIs. Because they invested so much they might well get ahead in this race

It's a classic, but Influence by Cialdini lived up to its expectations for me