HN user
AI researcher/engineer. https://github.com/ricklamers
Perhaps then inventors of promising ideas should make multiple attempts at popularizing their ideas if they care about association, multiple attempts at explaining why the idea is important and demonstrations of killer applications.
I have found 'Buienalarm' to be more accurate in the Netherlands, not scientifically, just anecdotally
I want more blog posts like this: filled to the brim with useful advice. Ty pul!
FWIW I think LangChain has evolved a lot and is a nice time saver once you figure out the patterns it uses. The LangSmith observability is frankly fantastic to quickly get a sense of how your expected LLM flow engineering ends up working out in practice. So much FUD here, unwarranted IMO. Don’t forget, reading code is harder than writing it, doesn’t warrant throwing out the baby with the bath water. Don’t fall for NIH :) Haven’t had issues running in prod recently either since they’ve matured their packaging with core/community/partner etc. For agentic use cases look at LangGraph for a cleaner set of primitives that give you the amount of control needed there.
It makes no sense to estimate the total cost of the proprietary equivalent of _all_ that is currently OSS at $177M. It would be spread over at minimum thousands of companies and each company would try to get their margin, needs to be rewarded for the risk they’re taking, etc.
The HBS method to get to 3.5X isn’t sensible (as the author points out, not everyone would build) but the truth is somewhere in-between.
The COGS of software would be significantly higher if there was no OSS. But everyone knows that already. I don’t think any new information has been created here.
I really enjoy tinkering with LLM outputs that generate code that can be executed directly. Especially the faster models like GPT-3.5 Turbo are a joy to play with.
Am I the only one surprised that the author of einops is looking for work? In an era of an AI arms race between many big labs? If you’re rolling your own networks, I’d definitely reach out to this guy!
TIL. Cross-posting breaks silos
https://github.com/PipedreamHQ/pipedream/issues/954
No I don’t think so. You probably want n8n if you’re keen on self-hosting.
If you want good up to date resources on the applied side I’d recommend checking out https://hamel.dev/notes/
I have to plug one of my favorite workflow automation tools that is a namesake and was fairly recently developed: https://pipedream.com/
Would definitely give it a try if you’re looking to automate Yahoo Pipes style.
I have no affiliation to them, just a happy user
Thanks! Appreciate it
I wrote a similar thing for myself: https://github.com/ricklamers/shell-ai
It currently has 882 stars and I think a few people at least are enjoying using it.
https://codingwithintelligence.com/feed.xml
It has an RSS feed with full articles available. I understand your desire to limit JS.
Great analysis on the value of collecting and curating knowledge, even without synthesizing it into "best practices." As an AI engineer I collect a lot of resources here, hoping it helps someone https://codingwithintelligence.com/
It doesn’t even support keyword arguments yet, hard to take the Python interop seriously
I found https://github.com/oblador/hush#does-hush-accept-or-deny-per...
So neither it seems. Whatever the website does when a user doesn’t make a choice.
Queries on https://github.com/pypa/flit/tree/main/flit_core/flit_core (omitted tests/)
Please let me know if anything isn’t as expected and I’ll try to look into it
Sweep is mentioned as attribution in multiple places a) https://github.com/definitive-io/code-indexer-loop#attributi... b) https://github.com/definitive-io/code-indexer-loop/blob/fd9d...
The difference is packaging it as a consumable PyPI package that can easily be used in a project (they even call out for separating this out into a stand alone project but that they lack the time to do so: https://docs.sweep.dev/blogs/chunking-2m-files#future- )
In addition, we expand and fix the implementation, for example it now supports limiting on token count instead of character count, and we fix some white space inconsistencies in parsing/chunk reconstruction.
If you can make sure all the resources are namespaced well I’d actually start moving some local workloads to our GKE cluster. Very nice work!
Using introspection tools like queryObjects in Chrome Dev Tools should get you quite far:
https://developer.chrome.com/docs/devtools/console/utilities...
The UI toolkit it uses is Yue which I hadn’t heard of: https://libyue.com/docs/latest/js/
Jeremy Howard calling it out as a fake https://twitter.com/jeremyphoward/status/1681817279133253632...
Yeah tell this to the guys at MosaicML. Spend less than you earn is a fine strategy but it definitely isn’t the only road to Rome.
It is difficult to get a man to understand something, when his salary depends upon his not understanding it.
I’ll just leave this here.
The unlock opportunity here is likely being underestimated. I heard once "you can be ahead of so many curves by being on Twitter", now add Discord and Slack.
Also, you can remove the tediousness of Twitter feed scrolling because AI will make it easy to just ask for specific knowledge (if you know what you're looking for) or perform discovery based searching (what are some of the interesting ways in which people are using LangChain in this community). This is wild!
I think parsimony is great for human readability but also creates a bias that excludes within reach solutions that overall have meaningfully better properties https://en.wikipedia.org/wiki/Evolved_antenna