barefeg
Joined 5 years ago
Karma
180
Submissions
202
Member since
Dec 19
Recent submissions
Comment · 1 year ago
Comment · 1 year ago
Thanks for sharing your blogpost. We had a similar journey. I installed and tried both Langfuse and Phoenix and ended up choosing Langfuse due to some versioning conflicts on the python dependency. I’m curious if your thoughts change after V3? I also liked that it only depended on Postgres but the scalable version requires other dependencies.
The thing I liked about Phoenix is that it uses OpenTelemetry. In the end we’re building our Agents SDK in a way that the observability platform can be swapped (https://github.com/zetaalphavector/platform/tree/master/agen...) and the abstraction is OpenTelemetry-inspired.
Comment · 2 years ago
He hinted at wanted to be convinced to work at the company. It seems as if he wants people to just know he’s good and people offer him the job instead of applying for it. It’s a bit contradictory since he applied for the job in the first place.
Comment · 2 years ago
From this interview https://youtu.be/Nlkk3glap_U?feature=shared it seemed Anthropic was focusing more on those topics rather than winning the race. He hinted at being “forced” by the competition to release their models.
Comment · 2 years ago
I was confused for a bit but there is no relation to https://haystack.deepset.ai/
Comment · 2 years ago
This technique had a very recent resurgence via https://txt.cohere.com/int8-binary-embeddings/. Hugging face also covered the technique here https://huggingface.co/blog/embedding-quantization. It seems like a very good tradeoff compared to the shorter embeddings which require fine tuning via the matryoshka technique. On the other hand, Nils Reimers suggests that trivial quantization of the full precision embeddings is not as good as using “compression friendly” embeddings like Cohere’s Embed V3. Does anyone know what’s the difference in precision between trivial quantization and optimized embeddings?
Comment · 2 years ago
Could you give more details/resources on the distributed in cluster buildkit cache?
Comment · 2 years ago
Have you tried the arc browser? It embraces having lots of open tabs and organize them as you wish (or not) https://arc.net/
Comment · 2 years ago
Do you need to have the same number of positive and negatives? Is there any meaning of pairing a positive an a negative in the triplet?
Comment · 3 years ago
Out of curiosity, how does it compare to YouTube’s own generated transcripts?
Comment · 3 years ago
I wish they had cut all benefits from tier 3 companies only^[1] while leaving other tiers intact. Big tech salaries in Europe are already so much higher in comparison, that it would probably not impact their ability to hire.
On the contrary, tier 1 and 2 companies already have a hard time hiring even with the benefit (from personal experience).
[1] highest band in the trimodal salary distribution https://blog.pragmaticengineer.com/software-engineering-sala...
Comment · 3 years ago
Are there any disadvantages of using let’s encrypt for certs? It would solve the renewal issue.
Comment · 3 years ago
We started with something like this as well. The problem is that the savings and disposable income will also be proportional. If the difference in salaries is large then it could seem unfair. But then again it depends whether you view wealth as an individual or shared affair.
I think it’s important to release SDKs that are secure by default, so not providing this in the reference MCP would be a big issue.
In my view, MCP should be maintained by the vendors themselves. It’s too complicated to use in the enterprise if everything comes from the community with questionable security. So I applaud initiatives that try to solve this. I think smithery.ai provides something similar while also being a repository of servers (I’m not associated with them), but again the problem is needing to trust an extra middleman vendor.
Does anyone else share this view? For example, will AWS (or insert any other hyperscaler) end up providing the “Bedrock” of MCP where security is native to the platform? Or will individual companies (Box, Google, MS, etc.) start rolling them out as part of their standard developer APIs?