weekay

Are there any other tools similar to pieces.app that are useful and preferably open-source, which can be integrated into the developer workflow? I’ve used Heynote, which helps to some extent, but it’s not a direct fit and isn’t a complete AI developer workflow companion.

I have been using it on and off for a few months since getting the device delivered through the kickstarter funding campaign . The code base keeps changing frequently and isn’t stable . But there is an active and helpful discord channel . Initially there was an option to bring your own API keys from open ai and deepgram . But now the ability to bring own api keys seems to be gone and that will concern me about privacy etc ., . The design is simple , device collects the voice sends it to deepgram , transcript is stored on device and then shared with open ai with relevant prompts to summarise the discussion and do what ever you want through plugins that can be configured. Use it primarily as a backup / secondary notes taker in meetings . Think of it like a Microsoft teams copilot or firefly equivalent for zoom etc There is a option to store the voice and transcripts to your own gcp bucket which is nice if you want to remember / do any prompt engineering on your meeting transcripts Something like this will replace the expensive meetings / note taking apps The integration with outlook / calendar apps is flaky and the level of details and ability to setup next steps / meetings schedule through transcripts is weak

“Any manager “who retains more than three people who don’t obviously pass the excellent, necessary and trustworthy test” should resign, he added.”

This is interesting. Get the assessment for being excellent and necessary is linked to strategy and business plans . How does one assess trustworthiness ? Interesting to understand what a trustworthy test would look like !

The risk of exposure in emerging and low market economies is significantly lesser than advanced economies according to this report . The nature of work in advanced economies by comparison then is going to significantly change. If 60% of jobs in advanced economies are at risk am surprised with statements from these countries that they are well equipped and ahead of the curve to deal with it . Is anyone seeing anything tangible being proposed and planned to deal with apart from educating people to use this technology? Or is this all a prelude to another AI winter I wonder as we start to make these forecasts and raise expectations

Wow , oracle got away with a $23 mil fine whereas SAP is stuck with 220 mil ? https://www.sec.gov/news/press-release/2022-173

If I were to self host an open source model like mistral or llama , are there options similar to this as an api gateway to proxy and authenticate , create api keys , monitor spends by api etc .,? How are people running open source LLM”s in production ? Thanks

Also a app to search and chat with papers https://apps.apple.com/us/app/neurips-papers-by-metaphor/id6...

Duplicate of discussion on this topic at - Iconic tree at Hadrian's Wall's 'Sycamore Gap' has been 'felled' https://news.ycombinator.com/item?id=37687887

This really is a hard stop being applied on Cloudflare WAF rules to stop any traffic from geo locations a sys admin believes would stop threats and also reduce their bandwidth utilisation. If companies don’t have business interest outside or their territory/ country the new trend seems to be just geo block that domain. While https://investor.caseys.com/ is accessible from Europe for eg., the main site isn’t . This isn’t a GDPR thing just a playbook some of the cyber security and ops team seem to be applying across various retail companies now a days .

Depends on the country though. It’s not easy to get a no questions asked w/o having to prove who you are SIM as PAYG in all places. What I feel we need is from the mobile operators a service like “hide my email” option from iCloud you keep your mobile number but give out per use generated or pre generated throwaway disposable numbers that can be used similar to the use case described in the article w/o having to go and buy a new sim. Shouldn’t be that hard to setup from a mobile operator perspective surely ? Also btw if you think your number which you shared with your family and banks are safe and not outed it’s a myth . Even on apps like LinkedIn I have found if you provide access to your contact list they get to harvest your contacts and the numbers.

This is very common in retail. What tends to happen is that a retail buyer would work with a supplier and order a product in . That product packaging will have a promotional or information site it will link to & is printed as a QR code. From a buyers perspective they are doing this as it’s a way to provide value or information to their customer and supplier fronts the cost of this. The IT teams within retail aren’t kept in the loop and neither are they aware of a site that is hosting any of this content. All the content and marketing of this is done by a agency who are hired and managed by the category or merchandising teams in the head office . Product sells for a quarter or maybe 6 months at the most . Products get rotated and goes back to warehouse until such time in a year they need to liquidate the stock and do promotional discount pricing as part of back to school or Black Friday etc., By then the agency that fronted this and created the site has lost its domain or the site isn’t maintained/ gets compromised etc., At that point the product is on the shelf , domain is hijacked or the hosting provider / host gets taken over by a malicious actor. Then the IT / security teams in the retail organisation are asked to step in and support their business colleagues. Every major retail corporation will have this happen to them at least once a year. IT teams will have a laugh about this and nothing ever changes as a process as it doesn’t really affect the share value or damage the reputation of the retailer as such

Excellent write up. This is the kind of content that I love to see here. Great to see how chatgpt helped you along the way to learn and solve a problem you weren’t very well versed with. Resonate with the comment that you were the developer and chatgpt was the coder ! Exactly how I felt with some of the projects. Also indeed true that Simplicity is indeed complex .

Seems interesting will definitely give it a try. Few observations/ questions from reading the documentation- > Continue will only be as helpful as the LLM you are using to power the edits and explanations

Are there any others apart from gpt4 suitable for programming copilot tasks ?

> If files get too large, it can be difficult for Continue to fit them into the limited LLM context windows. Try to highlight the section of code that include the relevant context. It's rare that you need the entire file.

Most of the value and real world use case benefits come from usage in a brownfield development where a legacy code isn’t well understood and is large (exceed current LLM context ?)

> telemetry through posthog Can organisations setup their own telemetry and development data collection to further analyse how and where the Copilot is being used ?

> Finops How does one get visibility of token / api usage and track api spends ?

Long story short it’s still a mystery why it’s broken and what caused it.

>Are you all working on providing an easy way to maybe use LLMs for chatting/search without sending my data to OpenAI?

From a brief look at the github repo there seems to be need to setup OpenAI API key so not sure if this currently has the ability to chat / search w/o sending or needing a OpenAI API access ?

Previous discussion on the topic from yesterday-

Apple forced to make major cuts to Vision Pro headset production plans https://news.ycombinator.com/item?id=36573667

Journal apps are a start

Why not rely on an robots.txt entry instead of having to explicitly include in http header to not have ai ?

https://www.nytimes.com/2021/11/09/well/mind/john-sarno-chro... “Healing Back Pain: The Mind-Body Connection.” By John Sarno . This definitely helped me through my back pain

https://github.com/outline/website has the source

Maybe try and use Huginn ?

Why do demos need Google or other login ? This is such a friction . I should be able to get access to demos w/o having to login . Also the use case for pre sales is interesting. Has anyone really had any success during pre-sales for an enterprise customer agreeing to installing a collector on their applications ?

On iOS you could also use the native built in background noise functionality which is good.

Go to Settings > Accessibility > Audio/Visual > Background Sounds, then turn on Background Sounds.

Rain , Stream and Ocean are my favourite while needing to focus

“We are also in contact with Okta with a number of requests for additional logs and information. “ - is it a common practice to share the logs with customers ? Seems unusual .

Easiest and simple self hosted option is archive box https://archivebox.io/

Firefox marketshare has gone down from approx 16% in 2015 to about 6% in 2021. All the while the strategy to monetize and generate revenue streams while maintaining trust has been a challenge. Nothing they have been doing in the recent past has got me to go back to Firefox.

Not actually clear what is open sourced here. The contents and links are to various other sites that arent necessarily open sourced. Almost all of the principles linked do not have any license attached to them. On a side note the principles tend to get written up at the beginning and are based on the thought process and outcomes agreed by a few who were there when it got defined. How often do they change or reviewed adn challenged ? To a large extent the principles are like horoscope readings, difficult to challenge & always feel right. This doesnt mean you shouldn't define and document the principles, but also isnt necessarily the one you should remix and adapt because they sound cool.

Other options are tools like Percy.io and Sauce labs which do visual diff , but they are again based on image differences rather than component level. Alternatively have been thinking of a simple home grown puppeteer script that will render the image of developed webpage and overlay with the design rendered as a image to identify differences.

It saves pages to archive.org as well. You might want to be careful while using this to archive personal content.