Felix Beccar

Tech CFO/Ops. Failed standup comedian. Very few followers

[Felix Beccar @felixbeccar]

Found old box with a letter to Apple when I was 14 ❤️. I actually never got a reply — maybe now in times of social media, @Apple? 😀 If only I had bought a couple of shares 🤦‍♂️ #applefan

[Felix Beccar @felixbeccar]

@sudanalytics_ @MikeChouhy tu tema! 🤣

[Felix Beccar @felixbeccar]

@AnthropicAI I know you guys are kind of busy but any chance you can fix this little thing? it's killing me everyday...

[Felix Beccar @felixbeccar]

@Microsoft @Azure to make things easier, you have 3 different admin portals: azure, powerplatform and M365

[Felix Beccar @felixbeccar]

someone at @Microsoft @Azure ever tried the flow of buying Copilot Studio PAYG licenses ... like ... ever?!? Its literally impossible

[Felix Beccar @felixbeccar]

These days using @ChatGPTapp feels like using a Windows PC vs using @claudeai feels like being on a Mac 😍

[Felix Beccar @felixbeccar]

@martinvars @abhijitwt there is still a lot of opportunity in many verticals… Aaron explains it well imho

https://t.co/5CG9W9xUuy

[Aaron Levie @levie]

This chart is a good reminder of how much opportunity there is in AI agents right now.

There will be plenty of horizontal opportunities for agents, but equally many workflows that need deep domain expertise to actually make the user successful at automating the unique processes in their vertical.

The template is to build agentic software that taps into proprietary data, handles the workflow in a way that bridges the user and the agent collaboration effectively, and has a deep domain-specific context engineering, and the ability to drive change management for customers.

There still are huge openings in many categories.

[Aaron Levie @levie]

This chart is a good reminder of how much opportunity there is in AI agents right now.

There will be plenty of horizontal opportunities for agents, but equally many workflows that need deep domain expertise to actually make the user successful at automating the unique processes in their vertical.

The template is to build agentic software that taps into proprietary data, handles the workflow in a way that bridges the user and the agent collaboration effectively, and has a deep domain-specific context engineering, and the ability to drive change management for customers.

There still are huge openings in many categories.

[Felix Beccar @felixbeccar]

@Lovable small feature request: can you automatically email invoices/receipts every month? I dont want to build a mini app to go and fetch lovable invoices *in* lovable... that would be kind of weird/meta right? 🙏

[Felix Beccar @felixbeccar]

@SoundCloud if you send me a ‘rewind email’ (wtv that is) dont tell me my account is suspended… give me a pass or something so that I can ‘hit play’ as you want

[cinesthetic. @TheCinesthetic]

Robin Williams explaining how golf was invented remains one of the greatest stand-up bits ever recorded.

[Felix Beccar @felixbeccar]

Nice touch @Lovable 🤣 👏

[Andrej Karpathy @karpathy]

Don't think of LLMs as entities but as simulators. For example, when exploring a topic, don't ask:

"What do you think about xyz"?

There is no "you". Next time try:

"What would be a good group of people to explore xyz? What would they say?"

The LLM can channel/simulate many perspectives but it hasn't "thought about" xyz for a while and over time and formed its own opinions in the way we're used to. If you force it via the use of "you", it will give you something by adopting a personality embedding vector implied by the statistics of its finetuning data and then simulate that. It's fine to do, but there is a lot less mystique to it than I find people naively attribute to "asking an AI".

[Felix Beccar @felixbeccar]

Excel doesn't allow you to name a tab 'History'...makes total sense to have it as a forbidden 'character'

https://t.co/EYi7NGIfuE

[PROTECT ALL WILDLIFE @Protect_Wldlife]

.@RickyGervais explains why he absolutely loves Dogs. 🐶

‘It's the closest I get to
spirituality, just watching a Dog." ❤️

[Felix Beccar @felixbeccar]

so UK... 🫶

[Felix Beccar @felixbeccar]

Funny how my ex-employers show up in my Gmail....

Imagine when Lio is there too – bringing the insights I’ve already built straight into my emails 😍 @aqmen_ai

[Felix Beccar @felixbeccar]

@AlexandrePesant Backend debugging for non-coders to make the ‘last 20%’ work. Always.

Tried to show an example here in Anton’s question but lmk if you need more details! 🙏

https://t.co/UNjY6WlJu4

[Felix Beccar @felixbeccar]

For my million followers I’ve gathered over the last 15 (!) years: Do you remember when you joined X? I do! #MyXAnniversary
More millions to follow

[Tom Johnson @tomjohndesign]

This is how I feel about vibe coding.

Any project I try that has any kind of complication has this immediate burst of progress. Things are amazing and it feels like a superpower. Then... as I add more complexity, things crash to a halt.

The only projects that I think I can create are ones that fall in this "vibe zone". Prototypes, UIs, products—anything that's simple and has low complexity fits right in that zone. Proof of concepts, interactions, stuff like that. The tools are able to make things that fit in that slot.

But.

Everything falls to pieces as that complexity curve increases. And the problem is that any good product design process has increasing complexity. A basic prototype turns into a good prototype as soon as it has layered interactions, transitions, good affordances, hover states, 1000 tiny little details that make something feel correct and real.

The benefit of vibe coding is supposed to be that you move fast and you can whip things out—letting AI do all the work for you. The problem is it loses steam as soon as the necessary complexity is added. It keeps redoing itself, rewriting code, affecting things that are unrelated and then causing other issues.

But if you add that complexity, every vibe coding session quickly turns into a whack-a-mole bug-bashing session.

I'm not sure the solution to this. With traditional prototyping the solution is to duplicate, add more complexity, create more frames/scenes, tweak, fork, etc.

However with vibe coding, one little prompt can destroy literally everything. There's a stage where I end up walking on prompt eggshells-- trying not to give it too much or too little context so that it doesn't go rogue and break everything.

There's only a few exceptions to this. @cursor and @framer.

I can make great progress with Cursor, give it narrow context, and I have to approve the edits that it makes. This feels like a correct workflow. The problem is, I can't see the thing that it's making because it's an IDE, not a visual environment. Yes, I can create local builds and refresh my browser and all that kind of stuff. But the visual aspect is totally lost from the coding experience. It's a developer tool.

Framer gets this right because it only allows narrow updates within a single component on the page. Yes, it's limiting because it can only do a single thing at once, but at least it's not trying to create the entire page from scratch and manage it all through a prompt interface.

These seem like the right approach.

@Cursor: Allow the AI to edit anything but allow the user to approve those edits and see them in context.

@Framer: Allow the AI to only narrowly edit a single file or component to keep the complexity down to a minimum and reduce catastrophic edits.

I'm optimistic that tools like @Figma, @Lovable, @Bolt, and @V0 can make cool prototypes, but I just keep running into walls when it comes to doing anything more than just a basic interaction prototype. They need to do less IMO.

Hopeful that those tools add more controls that are in the same line as Cursor and Framer. I'll also add that this is similar to how we do it with @Basedash chart generation as well. But we're not a vibe tool in the normal sense so the parallels are a little bit harder to draw.