API pricing?
1,811 karma · joined March 5, 2013
I think this is a bad take... if you are going that long without noticing, you are (hopefully) delivering end user value all that time. That is the main driver of code. You can normally dig/hack/rearchitect your way out of an ugly code situation. If you've been building value for the last year based on the hacky code, that's a win.
I’ve been building https://smalldocs.org, it’s a simply styled, but functionally deep, artifact layer for agents. It’s open source and free to use.
Because it can incorporate charts, diagrams, spreadsheets, etc. in one artifact, it’s good for creating (and optionally sharing) agent created analysis.
It has a local library for all your Markdown files, and a cloud library (my one paid feature) too. Both support tagging and rich search/filtering. I find it turns SmallDoc artifacts into little checkpoints in work I can easily circle back to.
Thanks for reading!
https://smalldocs.org/s/6kEgfy54oclH4KR9HX847w#k=ywVL86PcTCo...
It's an interesting result (agents develop biases in their context) which reflects a lot of my experience working with agent, where I observe a lot of, what I kind of call, "context nudging" - where a droplet of an idea in an agent's context pushes its direction/output significantly. When it happens to me it always makes me question the type of intelligence LLMs provide.
[I am the developer behind SmallDocs. Source: https://github.com/espressoplease/smalldocs]
Humans have been the dominant species because of our ability to think, not our ability to get from A to B in any particular way/cook food. If we abstract ~the bulk of our thinking to LLMs, don't we lose something as a species which makes us more vulnerable... Or is it always the case during an automation?
https://smalldocs.org/s/scB6O8KiZEmLWgK855A1vt#k=yiw8FB_G5Ld...
I do agree that we are on a pathway to losing much. If you focusing on maximising LLM-powered productivity you basically lose the learning that used to naturally happen when doing actual work. At the company I work for the focus is on productivity, and it's easy in many ways (less mental workload and I receive more praise) to go with it instead of fight it.
I do think on device AI will be a BIG thing... and basically change how we interact with our computers entirely - you will just ask to get things done. Low latency, free to use as much as you want. I think this future is hard to avoid/this will be a chunk of the future.
I am unsure the direction that AI assisted document creation work will go in. I am opinionated and building something in the space. In this reply I discuss my view + what I have been building.
My opinion is: We now have AI, this new amazing flexible tool. We can throw it at any problem. But in terms of document creation we have a choice between old fashioned siloed document formats (.pptx, .pdf, .xlsx, .docx, etc.) and a freshly rendered - slightly randomly styled - html site with some basic javascript within it. I think these combinations are odd and do not maximise the powers of AI.
I've been building something called SmallDocs [0][1] which is a new take on work documents. It's all Markdown, but it always renders (100% privately) on the SmallDocs site. This means the SmallDocs renderer can convert recognised Markdown combinations into powerful traditional document formats [2]. For example, we convert a ```cells block into an in-line spreadsheet you can export to Excel.
This gives an agent the ability to express itself with a great deal of depth and flexibility. For example, your agent can produce a single data analysis "SmallDoc" with text, charts, spreadsheets, etc. [3] I find that combining formats quickens the speed I can understand a topic.
SmallDocs also have standardised and pretty boring styling. This means you spend less time understanding the layout of a flashy HTML page and more time on the content.
I also believe a pre-determined rendering engine has a lot of advantages over a freslhy built HTML artifact. It allows you to build in lot's of useful defaults that the agent doesn't have to code from scratch. These can be small things, for example, every time your agent renders a Markdown table in SmallDocs you can instantly copy it as a CSV or a PNG. And these can be bigger things, such as a rich slides DSL with solid styling defaults, which saves your agents a lot of tokens and results in consistently attractive HTML slides [4]. (Slides can also be automatically exported to .pdf and .pptx.)
I've been at it for a few months, and am still working on the project. I am looking for feedback and open source collaborators. Thanks for reading!
[1] https://github.com/espressoplease/smalldocs
[2] https://smalldocs.org/blogs/what-is-a-smalldoc
[3] https://smalldocs.org/s/46fWiAyF77T9c7tqYwAQqp#k=j78ZEOOrgo8...
[4] https://smalldocs.org/s/QrmeWMsULGS871nXQYOacB#k=ubOHH9QtTWp...
(And something totally different, your agent can also use SmallDocs to walk you through code files: https://smalldocs.org/s/JsI_-tWSH0UpSd_YXxVLPm#k=G5jLCYA4JUX...)
My opinion is: We now have AI, this new amazing flexible tool. We can throw it at any problem. But in terms of document creation we have a choice between old fashioned siloed document formats (.pptx, .pdf, .xlsx, .docx, etc.) and a freshly rendered - slightly randomly styled - html site with some basic javascript within it. I think these combinations are odd and do not maximise the powers of AI.
I've been building something called SmallDocs [0][1] which is a new take on work documents. It's all Markdown, but it always renders (100% privately) on the SmallDocs site. This means the SmallDocs renderer can convert recognised Markdown combinations into powerful traditional document formats [2]. For example, we convert a ```cells block into an in-line spreadsheet you can export to Excel.
This gives an agent the ability to express itself with a great deal of depth and flexibility. For example, your agent can produce a single data analysis "SmallDoc" with text, charts, spreadsheets, etc. [3] I find that combining formats quickens the speed I can understand a topic.
I also believe a pre-determined rendering engine has a lot of advantages over a freslhy built HTML artifact. It allows you to build in lot's of useful defaults that the agent doesn't have to code from scratch. These can be small things, for example, every time your agent renders a Markdown table in SmallDocs you can instantly copy it as a CSV or a PNG. And these can be bigger things, such as a rich slides DSL with solid styling defaults, which saves your agents a lot of tokens and results in consistently attractive HTML slides [4]. (Slides can also be automatically exported to .pdf and .pptx.)
I've been at it for a few months, and am still working on the project. I am looking for feedback and open source collaborators. Thanks for reading!
[1] https://github.com/espressoplease/smalldocs
[2] https://smalldocs.org/blogs/what-is-a-smalldoc
[3] https://smalldocs.org/s/46fWiAyF77T9c7tqYwAQqp#k=j78ZEOOrgo8...
[4] https://smalldocs.org/s/QrmeWMsULGS871nXQYOacB#k=ubOHH9QtTWp...
(And something totally different, your agent can also use SmallDocs to walk you through code files: https://smalldocs.org/s/JsI_-tWSH0UpSd_YXxVLPm#k=G5jLCYA4JUX...)
Homepage: https://smalldocs.org/
Example presentations:
https://smalldocs.org/s/mTBw58ut_eTAIlGkYePw6-#k=4MotlKf-sLc...
https://smalldocs.org/s/cGRzzCv7LA9Kd8BxZ4bBAP#k=B7_NNXPbpLw...
I run https://smalldocs.org, which focuses on making Markdown a highly expressive space for agents (think slides, spreadsheets, charts, mermaid diagrams, etc.). I have built a local library which lives in the browser but reflects your local file system - explainer here: https://smalldocs.org/connect?return=%2Flibrary, demo here: https://smalldocs.org/library?demo=1. Which is pretty useful when you want to find local Markdown files.
However I am just about to introduce very similar functionality to yours - a cloud + agent access. Right now I don't know if this will actually be useful, but I think it will likely be something I can charge for. I have a few hundred developers that use SmallDocs on a weekly basis (https://smalldocs.org/analytics), but right now it's just a free local-first tool.
Code available here: https://github.com/espressoplease/smalldocs
Curious about how your customers are responding to pricing. 20 agents for $499/month without API costs included feels steep... but perhaps within the range of "worth it if we don't have to think about this".
Is there anything else going on in the dream? Other people you are with/could be with/what kind of location/can you fight this thing or are you sure it will get you?
When you are awake: Your executive function is active, your default mode network (a network of brain areas which light up together which are focused on social interaction + long term memory) is active, your amygdala (threat) is active (at a high level if you are stressed, but has some base level of activity even when not), the "fight or flight" neurotransmitter norepinephrine is also circulating at a reasonable level (again, higher if you're stressed).
During REM sleep: Your executive functions are disabled, your default mode network is extremely active, your amygdala is inactive, and norepinephrine is 85% below base waking levels.
So... even though you might be having a scary dream, your brain is actually in a supremely relaxed state. You are also in a state where you cannot control your behaviour (no executive functioning; I am excluding lucid dreams from this statement).
Why is this useful?
[I am training to be a Attachment-based psychotherapist, the following is learnt from my training + dealing with my own issues in therapy + a substantive evidence base:]
The primary driver of unnecessary adult psychological suffering comes from a miscalibrated fear response. When we are infants we are highly sensitive to the emotional connection between us and our caregivers, and will be scared when our parents become anxious. Unfortunately, our parent’s anxieties are not always rational (just like ours eventually will not be), and they are frequently triggered by what are natural expressions of emotion the infant will (and should) express. Some overly simplistic examples might be a “tough father” who is angry when their child shows weakness, or an “anxious mother” who is scared in case the natural exuberance of their child may offend someone. Infants pick up on this fear response and develop a fear about expressing the emotion which generates the fear response in their parent.
This all happens unconsciously. The infant does not decide to do this. The infant is not aware that it is doing this. The infant does not have the cognitive capacity to understand that it is doing this. Then the infant grows up, but this deep fear has not left. This adult is then stuck with the side effects. That fear of appearing weak persists; that fear of upsetting others persists. For most of us, we are not even conscious of these fears as adults, but these fears will have a powerful effect on our behaviours.
The mind is quite like a pressure based physics system. Bad mental health emerges when the system cannot release pressure, good mental health is associated with quick releases of pressure. You will have a more stressful internal world if you can’t allow yourself to be weak and cry; you will have a more tense experience of life if you’re worried that everything you do might upset someone. Both of these are blockages in the flow of natural healthy emotional expression.
Mental health gets better if you can unblock these blockages. But remember… you’re not aware you even have them. This is where dreams help. Dreams are effectively the inverse of anxious mind wandering.
Anxious mind wandering: You are awake, the brain is in a stressed state: you worry about the worst things that could happen. Objectively, these things are normally far fetched, but unfortunately it doesn’t feel like that on the inside.
Dreaming: You are asleep, the brain is in a relaxed state: the brain creates situations where it would be healthy/useful to not be so scared. And the brain turns off your executive functioning, but not your default mode network, so any behaviour with observe you take in the dream reveals the state of your emotional/long-term-memory/relational brain. When you focus on the behaviour of the dreamer, you will notice the behaviour will be miscalibrated to the situation they are dreaming about - and in the direction of revealing too much fear.
Examples from real dreams: Someone is mugged by a child robber, and hands over all their stuff without fighting back. Someone is getting a tattoo they don’t want, but lets the tattooing continue instead of saying “stop!”.
This allows the analyser of the dream (a therapist or perhaps yourself) to pinpoint the underlying fear that must be dealt with to unblock the system of emotional expression.
(This note was a bit rushed... so sorry if it is written casually.)
I wrote a paper about this. Preprint here: https://osf.io/preprints/psyarxiv/k6trz_v1
Previously discussed on hacker news here: https://news.ycombinator.com/item?id=19143590