nigma

I'm having a lot of fun chatting with characters using Faraday and koboldcpp. Faraday has a great UI that lets you adjust character profiles, generate alternative model responses, undo, or edit dialogue, and experiment with how models react to your input. There's also SillyTavern that I have yet to try out.

- https://faraday.dev/

- https://github.com/LostRuins/koboldcpp

- https://github.com/SillyTavern/SillyTavern

I hate this kind of clickbait marketing suggesting the project is delivering 1/100 of the size or 100x-35000x the speed of other solutions because it uses a different language for a wrapper around core library and completely neglecting tooling and community expertise built around other solutions.

First of all the project is based on llama.cpp[1], which does the heavy work of loading and running multi-GB model files on GPU/CPU and the inference speed is not limited by the wrapper choice (there are other wrappers in Go, Python, Node, Rust, etc. or one can use llama.cpp directly). The size of the binary is also not that important when common quantized model files are often in the range of 5GB-40GB and require a beefy GPU or a MB with 16-64GB of RAM.

[1] https://github.com/ggerganov/llama.cpp

I’m using Jupyter Book (https://jupyterbook.org/) to build all kinds of daily reports and it works really well. Individual notebooks can also be converted to HTML or pdf with nbconvert using command line or “download as” menu item.

Mine came with a manual in German and some hardly readable photocopy of a translation written on a typewriter. That was a steep learning curve for a kid. Fortunately there were a lot of young and older folks who shared knowledge, engaged into demo scene or just played games. Later on I got a couple books and subscribed to the C&A magazine which helped me a lot with diving into graphics programming, extension ports, SID, etc.

The best part about C64 was it immediately booted into a Basic prompt that invited you to experiment with the hardware, like typing these magic POKE commands to set screen and text colors.

Just guessing, but there may be other devices providing DNS service on your network. For example I have found that AppleTV is listening for DNS queries on a couple ports and MacOS will happily fallback to that.

Wavelets are fun. I first heard about them in the early 2000s when I read about JPEG 2000 image compression format [1]. Back then the primary tool to play with signal transformation was the Matlab Wavelet Toolbox. As I got more interested in the topic I started work on PyWavelets [2] Python package for my master's thesis about medical signals processing and ML classification.

I'm not actively involved in the package development anymore but it is still maintained [3] and there is a great chance that you have it already in your Python environment as a dependency of scikit-image/scikit-learn. Just give it a try, it's very simple:

  >>> import pywt
  >>> cA, cD = pywt.dwt([1, 2, 3, 4], 'db1')

There are many reasons for using other databases like PostgreSQL or MySQL in production - feature set, (managed) hosting, backup and replication, etc.

SQLite is primarily embedded/local database and cannot be easily separated and shared over network [1] between multiple disposable backend/worker instances.

[1] https://12factor.net/backing-services

The MBP 2015 with discrete GPU is hardwired to output video signal through AMD M370X. It can get quite noisy when just connected to an external display.

Apple is creating a false sense of privacy with their privacy-focused marketing. I appreciate their efforts building secure products but without a way to block or filter 3rd party app network data they leave their users vulnerable.

Also many ad-blockers that could filter app traffic were nuked from the App Store. I wish there was a way to firewall network traffic in the same way it is possible on other systems.

It looks that Miranda IM (initial release in February 2000) is still actively developed - https://www.miranda-ng.org/.

Why software updates and especially security bug fixes are not covered by manufacturer warranty as it is with hardware issues? Or maybe they are but no one enforces that?

In other words if I buy a phone with 2y warranty (a standard duration in many European countries) it would be reasonable to expect that any security updates (device fixes) will be provided in a reasonable time within that period starting from the purchase date.

It depends on the revisit time, spatial resolution, region of interest, cloud coverage and product type. For example Landsat 8 images the entire Earth every 16 days, Sentinel-2 revisit time is ~5 days with 2 satellites and MODIS provides daily data but at moderate spatial resolution (> 250m). We expect both the spatial resolution and revisit time to improve as more companies are launching satellite constellations.

They already provide Earth Engine platform which is more complete both in terms of available datasets as well as developer APIs.

AWS product basically consists of open remote sensing datasets uploaded to S3. This is convenient if you deploy on AWS (transfer costs) but still have to develop all the data processing.

I turned off JavaScript and Cookies for all sites a few months ago and only whitelist (or open in another Chrome profile) when they refuse to display or need an authenticated session.

There are some sites that require JS to render, but the great thing is that majority of pages I visit work just fine as plain html/css. In general I feel less distraction from popups, overlays, ads, etc.

The 4G-AC55U router is also vulnerable but did not receive a security firmware update (last firmware release was a year ago on 2016-05-20) and is not listed on the page.

If you happen to be running this device you may want to apply precautionary measures.

Telemetry at the OS level bothers me to the point that I'm not Windows user anymore and I I'm not planning to become one anytime soon.

But to be fair one should point out that Apple is also collecting telemetry data (search system logs for com.apple.telemetry) without any toggles in the system preferences.

Search results don't bring much info on what is collected and how it is being used. Does anyone here have insight into Apple telemetry granularity?

For clarification, the Docker Community Edition appeared in the Docker for Mac beta channel, but it looks there is no official announcement yet of the upcoming editions.

The link leads to a staging version of the store.docker.com site that is indexed in google.

This is a nice list. There's also https://github.com/vinta/awesome-python, which is a bit more comprehensive.

Using Python 3.3:

    import base64
    base64.urlsafe_b64decode(s)

SEEKING WORK - Remote or on-site (Europe/US)

Backend and frontend development, mobile APIs, devops.

I usually do Python, Django, mobile backends, PostgreSQL/*DB, JS, Angular, Scala, Go, system architecture, database design, automation, devops (Ansible, Salt) and whatever it takes to get the job done.

I'm capable of executing all stages of projects, starting from a customer idea and ending with a ready, deployed product. I have a broad technical and domain-specific knowledge (medical, financial, automotive, location-based services, machine-learning, analytics, wavelets) and several years of experience working for startups, business customers and open-source.

I deliver several projects a year. Here's some of my work:

http://en.ig.ma/projects

http://github.com/nigma

Drop me an email at en@ig.ma

PS. I'm open to cooperation with other freelancers (design, mobile, web, etc.).

They are generating PDF for online viewing. Go to your files on dropbox site and click on a .doc file. A preview popup will appear.

Open/LibreOffice with Python bridge is quite handy in converting documents to PDF format and can be run in headless mode (using virtual frame buffer like xvfb) on a server.

The Rest Framework is a lot more flexible and just don't get into your way when you need your API to do anything else than exposing CRUD operations.

The whole design of DRF makes a lot more sense for my use cases.

TastyPie provides you with Resources that do everything from accepting and dispatching methods, querying db, authentication and authorization to parsing an serializing data. If you want to modify one puzzle you have to redefine the resource.

In DRF the separation between request processing, data serialization/deserialization, rendering and other elements is more clear.

API endpoints are just views that are based on Django class-based views so you should already know how to customize them, do queries and use mixins. Serializers perform data validation (similar to forms, but can handle collections and relations) and conversion between objects and native Python datatypes. They can also be reused in multiple views or for nested relations. Other components are pluggable so you can specify parsers, renderers and auth backends for the whole API or for just a particular view.

The Rest Framework just feels right and works well when you need to do any sort of customization. On top of that you get a very detailed documentation and a browsable API.

TastyPie served me well for a long time and I'm very thankful to the developers, but I find DRF to better suit my needs.

So here's what Linode support is actually saying when asked about the breach:

   Thank you for contacting us. We have no evidence at this time that any payment information was compromised.

Just logged in to one of my servers in the London DC. 952 days of uptime, so in my case it has been pretty stable over the past couple years.

I couldn't agree more. I'm currently on an upgraded Thinkpad T61p with 1680x1050 and I'm reluctant to change it to a newer machine because of the 16:9 screens padded with tall plastic border that are available in most notebooks nowadays.

I really hope that hardware makers will finally realize that the primary reason for buying a notebook is not for watching movies on a 15" screen.

PyPy was funded by the European Union as a Specific Targeted Research Project between December 2004 and March 2007. http://cordis.europa.eu/search/index.cfm?fuseaction=proj.doc...

Have you considered using PostgreSQL foreign data wrapper (mysql_fdw) to pull data directly out of MySQL instead of the dump/load process?

It would be great to know more about your new setup, i.e. do you use streaming replication and some resource manager like Pacemaker?

Give it a break. That article is 2.6 years old. Some of the points might still be valid, but there is a solution (and probably was at the time of writing as well) to every and each of the problem mentioned there.

Regarding the quality of reusable apps, well, it's like with all other software libraries out there. Some of the apps are really invaluable (mostly the utility ones addressing things like API creation, database extensions, forms or debugging), some of them address very specific problems and some of them should't ever see the daylight. Nothing new.

For comparison a version in Python/Matplotlib is at http://jakevdp.github.com/blog/2012/10/07/xkcd-style-plots-i...

No doubt this is a great resource for getting to know very basics of all these frameworks.

The thing is that the TODO application is way too simple and does not require solving any meaningful problems. A much better and more realistic sample app would include at least handling basic relations between objects like users commenting under articles or voting on submissions. Say simple HN in JS MV* implementation would be a lot better resource.