supertron

Aha. Very good. Not sure how I missed that at the time. I’ll definitely be giving this a shot.

And your excellent blog is already in my RSS reader so I have even less excuse for missing this detail… :)

About 15 or maybe even 20(?) years ago I could RDP into a Windows server over a crappy mobile phone data connection connected to my laptop on a moving train and get stuff done. It is a phenomenal protocol, when implemented correctly!!

Last time I played with RDP on Linux it really just seemed to be a wrapper around {the equivalent of} a VNC connection - so even when it worked, it was nothing like the streaming experience when RDP'ing into a Windows machine. Not sure if things have improved since, or FreeRDP does things differently.

I had a quick glance through the FreeRDP site but didn't spot any immediate clues as to whether this is a true Windows-style optimised/streamed RDP implementation or a "we'll send you a constanst stream of compressed bitmap screenshots" VNC-style...

RDP on Windows is one of the few things I really miss from the Windows ecosystem. There is nothing on Mac or Linux that I've seen to date which comes even close to the near-instantanous experience of using a Windows machine over RDP.

> I think to get good value out of it you really have to get a sense for what it's good for and what it's not.

> I don't have it write my day to day code, because that's complicated and usually niche enough that it's not likely to give a good result.

Yep totally agree. I don't think you should just treat it as a black box - throw in literally any prompt you can think of and then use the response verbatim, without even reading it, and expect to have success.

You need to exercise some judgement and be a bit discerning. And think about what areas of your work are most unique to your own skills and experience, and what are the bits of work around the fringes that don't need to be done by you - and are not really part of your core "craft", and, are likely to be well suited to the capabilities of something like GPT-4.

And like every other tool, using it effectively is a skill and requires perserverance, practice, and adjusting your approach as you go. Which means the user can get better at getting value of out an LLM over time. It's not a static or all or nothing thing.

I use it (LLMs / GPT-4) as a sort of "realtime intern" to offload the more commoditised tasks that I don't really need to do - and that I don't contribute unique value to by doing myself. So some boilerplate CSS layout code, sketching out unit tests, initial stubs of API client code. Lots of "filling in the gaps" - which frees me up to spend more time thinking about higher level architecture, structure, business problems, abstraction/refactoring, planning, design etc.

Due to the way my brain seems to work, it also keeps me from getting stuck on small distracting problems which would previously create some resistance or procrastination - causing a break in my flow of work. It essentially keeps me in a productive flow state for longer periods than I could sustain without it. Any problem that is not in my "critical path" that I want to be focused on in the moment, and that could be easily solved by an LLM, gets "outsourced" as such.

This is in addition to it replacing about 80% of my software development / devops related Google searches. Because I work across quite a wide range of disciplines, I'm often looking for quick answers to questions about some technology stack that I'm not using daily. It's perfect for that. And I have enough familiarity with what I'm working with to sense-check/QA the responses.

I believe you do need some subject matter knowledge and experience to get the best out of LLMs though. I think many people are verbatim copy/pasting code out and complaining when it doesn't work. I very rarely find I waste any time debugging or correcting problems - because I either spot them and correct them in real time - still saving me a lot of time regardless - or I structure my prompts in a way that avoids these problems in the first place - by breaking the request down in to granular enough parts that I can pretty much predict how accurate the response will be (most of the time; very).

And in the scenarios where there is a bit of back and forth, trying different ideas and debugging in realtime - this is almost always a much faster (net) process than if I had done the same iteration myself.

As a point on usage and confidentiality, I don't use integrated coding assistants like Copilot - everything I do is sandboxed - so nothing confidential goes into the LLM. Specific details in my prompts are "anonymised" as I enter them (as in, I self-censor) - so I get the benefit of a lot of assistance from LLMs but with no sharing of any information that I would deem confidential. I plan to experiment with tighter integration into my workflow (eg. Copilot type assistance) with a private LLM instance at some point, but I'm comfortable with the balance of productivity and confidentiality at this point.

I do also have a Hammerspoon shortcut that will take the currently highlighted text in any app, and send it directly into OpenAI's endpoint. So I can highlight a mixture of comments and/or code in my IDE and immediately send them to GPT-4 and have that highlighted text replaced (or appended to) by the response. This gives me contextual assistance without having a constant live feed into a proprietary LLM ala Copilot.

> At first glance, I thought this was another Linux distro with a custom window manager, not a new operating system. But it is its own operating system!

Indeed, these "reskinned"* Linux distros seem to be so common, it's easy just to make assumptions.

This (Essence) looks pretty impressive - to be built from scratch and have a nice clean (dare I say it... "non-linuxy looking") UI is even more impressive.

* "Reskinned" is probably a bit of a lazy term here - many of them are a lot more than that - but still, the point is that the value prop. is often the nicer more user-friendly aesthetics layered on top of an existing distro. What we're looking at here seems a lot rarer. Snapping at the heels of ChromeOS?

Agreed, sadly 1Password's biggest threat is themselves at this point, not Keychain.