HN user
Yes — encryption is the solution for client side caching.
But even if it’s not — I can’t build a scenario in my head where recalculating it on real GPUs is cheaper/faster than retrieving it from some kind of slower cache tier
Boris, wait, wait, wait,
Why not use tired cache?
Obviously storage is waaay cheaper than recalculation of embeddings all the way from the very beginning of the session.
No matter how to put this explanation — it still sounds strange. Hell — you can even store the cache on the client if you must.
Please, tell me I’m not understanding what is going on..
otherwise you really need to hire someone to look at this!)
Next time you use true real independently audited e2e communication channel, don’t forget to check who is the authority who says that the "other end" is "the end" you think it is
you lose the code that has been battle-tested
I agree that this is still the most important thing, and I don’t try to challenge this.
At the same time we have quite adopted bumping our dependencies when it does not incorporate breaking changes (especially if there are know security vulnerabilities) — and my point is exactly about it, why even simple renames, extraction or flattening or other simple changes have to be treated so differently than internal changes that do not touch public interface?
This is super cool, but unfortunately has to be open source and with signed reproducible builds.
Please, not another `strings` programming language
`‹tr : for="user of users">`
Actually, I think creating google alternative has never been as doable as it is today.
You would be surprised, but nvidia’s employee stock plans allow to select the purchase price within the last 2 years https://www.nvidia.com/en-us/benefits/money/espp/
Needed Word on Mac – you can’t imagine how surprised I was to see Skype starting too.
glorified token predicting machine trained on existing data (made by humans)
sorry to disappoint, but human brain fits the same definition
I’m afraid the problem is not indexing, but monetization. Alternative google search will not be profitable (especially if you have to pay a share to google indexing) because no one will buy ads there - even for bing it is a challenge
Wow! This is insanely cool!
Under ecosystem I mean people using ChatGPT daily on their phones and browsers, developers (and now virtually anyone) writing extensions. For most of the world all of the progress is condensed at chat.openai.com, and it will be only harder to beat this adoption.
Tech superiority might be relevant today, but I highly doubt it will stay the same for a long time even if openai continues to hide details (which I agree is bad). We could argue about the training data, but we have so much publicity available so that is not an issue as well.
Ecosystem around chat GPT is the differentiator that Meta and Mistral can’t beat – so I’d say that Altman is more relevant today than ever. And, for example, if you’ve read Mistral’s paper – I think you would agree that it’s straightforward to replicate similar results for every other major player. Replicating ecosystem is much harder.
Performance is never a complete product – neither for Apple, nor for Open AI (its for-profit part).
52k after taxes or before?
How come refactoring is not fun??