There are many things to ask to my manager (non-meeting days, remove non mandatory people from invites, open team discussion on the topic). I guess this is more of a culture thing at work where everyone is "expected" to show up. I see my boss' situation as even worst (although one might argue that that is his job, I see this as quite unhealthy no matter the role)
The opposite viewpoint is that you are being included in these meetings so that you can prevent bad decisions by management. What if you aren't in a meeting where it is decided that you should implement feature x because they imagine it to be low cost, not realising the complexity?
First off, I would set the strict max 30 minutes time limit for each and every meeting. If it’s not enough to solve something: do a follow up next day but ask everyone to prepare properly. Or just move the discussion to emails.
2nd: be an ass as a moderator. Cut all the small talk, chit chat, warm ups, derailing, or ad hoc brainstorming (usually performed by two people while the rest of the attendees are slowly dying inside).
The point is to see if they already have a solution in mind, and (if you're a good manager) either do it, tell them why it can't or shouldn't be done [yet?], or tell them they can do it themselves.
Pretty interface, although I remain unconvinced of how I'd actually use it. If I'm just prototyping for myself, LLM providers offer a decent history, and I rarely need to share notebook-style explorations of LLMs with my team. For production use cases at logicloop.com/ai we just add our prompts into code.
What's the use case you're envisioning people using AI notebooks for?
Appreciate the effort you put into this. In terms of user flow, I typically need one or two of these use cases at a time. In that case, I just type my conversion into a search engine like Google, and often use their default box.
Can you share what types of use cases you've seen people use KodyTools for?
Thanks for appreciation. Actually, user does not cover all units. It only shows most common one in terms of length. There are various units in terms of weight, area, and length that are used on regional level. If you just look at the area and length category dropdown, you will be suprised.
Great starting point! These diagrams notably miss a LLM firewall layer, which is critical in practice to safe LLM adoption. Source: We work with thousands of users for logicloop.com/ai
These common issues tend to prevent LLMs from being used in the wild:
* Data Leakage
* Hallucination
* Prompt Injection
* Toxicity
So yes it does include prompt injection, but is a bit broader. Data Leakage is one that several customers have called out, aka accidentally leakage PII to underlying models when asking them questions about your data.
I'm evaluating tools like Private AI, Arthur AI etc. but they're all fairly nascent.
I’m a researcher in the space exploring few ideas with the intention of starting up. Would love to reach out to you and talk to you. Is there a way I can contact you?
Yup, that's part of it but I mean it bidirectionally - users can accidentally leak data to models too, which is concerning to SecOps teams without a way to monitor / auto-redact.
Very cool, but curious if you see people actually directly interacting with LLMs vs in a script as part of a larger application? I see myself needing debugging, visualizing output etc. so much that an IDE makes more sense to me as an interface, so want to learn about cases where that doesn't.
Aw man, sorry to hear this about your friend. Inanimate objects are directly subject to the laws of physics, but living beings that have intention and will are able to circumvent those. For example, I can jump despite gravity existing. Yes, "in the long run, we're all dead", but applying laws of entropy as a reason to not live seems indicative of a lack of will, rather than a natural law every being must follow.
As long it's clear that this is fiction, how would something like this be more damaging than a series like The Man in the High Castle, or other sci-fi that imagines an alternate universe? I think it's a nifty technique that allows us to viscerally imagine and live out our parallel universes.
Yeah, in general the more data you're able to use (assuming the context window supports it), the better results tend to be. We arrived at the data schema being a good enough compromise at which the benefits outweigh the risks for several use cases. Besides, some data stores that are generated by third-parties actually have common schemas (think Sendgrid / Hubspot activity data), so you're not risking much but potentially gaining a lot of sales ops productivity.
This seems overall well-written and well-explained, but curious for that piece on fine-tuning. This article only recommends it as a last resort. That makes sense for a casual user, but if you're a company seriously using LLMs to provide services for your customers, wouldn't the cost of training data be offset by the potential gains you have and the edge cases you might automatically cover by fine-tuning instead of trying to whack-a-mole predict every single way the prompt can fail?
The concern with finetuning, even for specialized use-cases, is that you are binding yourself to the underlying model. Given rapid advancements in the field, this does not seem a prudent use of engineering time.
Having a hierarchy of prompts with context stuffing allows for rapid switching across models with a few (non-trivial) surface-level prompt updates while the deeper prompts stay static.
