HackerTrans
TopNewTrendsCommentsPastAskShowJobs

pranay01

no profile record

Submissions

Elastic agrees to buy CRV-backed DeductiveAI for up to $85M

techcrunch.com
2 points·by pranay01·il y a 22 jours·0 comments

Why should a Trace-ID be 128 bits?

newsletter.signoz.io
2 points·by pranay01·il y a 2 mois·0 comments

The System of Context for Production AI

mezmo.com
1 points·by pranay01·il y a 3 mois·0 comments

Claude Code channels not available for Personal Max plan

twitter.com
3 points·by pranay01·il y a 3 mois·0 comments

An open source benchmarking framework for IT automation

github.com
2 points·by pranay01·il y a 4 mois·0 comments

Safely evolve your JSON schemas. Check backward/forward compatibility

jsoncompat.com
2 points·by pranay01·il y a 4 mois·0 comments

OpenClaw Monitoring and Observability with OpenTelemetry

signoz.io
2 points·by pranay01·il y a 4 mois·0 comments

One More Prompt: The Dopamine Trap of Agentic Coding

blog.quent.in
2 points·by pranay01·il y a 4 mois·0 comments

AI Isn't Replacing SREs, It's Deskilling Them

newsletter.signoz.io
4 points·by pranay01·il y a 4 mois·0 comments

Claude Code Monitoring

code.claude.com
2 points·by pranay01·il y a 4 mois·0 comments

OpenClaw's hidden OTel plugin shows where all your tokens go

signoz.io
3 points·by pranay01·il y a 5 mois·0 comments

Passing user_id through 6 services? OTel Baggage fixes this

signoz.io
1 points·by pranay01·il y a 5 mois·0 comments

How we achieved 30% Faster Queries by overcoming ClickHouse's native JSON limits

newsletter.signoz.io
2 points·by pranay01·il y a 7 mois·0 comments

Overcoming ClickHouse's Constraints to Build a High Performance JSON Log Store

newsletter.signoz.io
1 points·by pranay01·il y a 7 mois·0 comments

Trust Technical Writers, Not LLMs

literally.dev
5 points·by pranay01·il y a 8 mois·2 comments

[untitled]

1 points·by pranay01·il y a 8 mois·0 comments

Root Cause Discovery: RCA of Failures in Microservices Through Causal Discovery

github.com
1 points·by pranay01·il y a 9 mois·0 comments

Thinking Machines Lab Co-Founder Andrew Tulloch Heads to Meta

techcrunch.com
17 points·by pranay01·il y a 9 mois·0 comments

Reflection AI raises $2B to be America's open frontier AI lab

techcrunch.com
3 points·by pranay01·il y a 9 mois·0 comments

Olly – AI Native Observability

olly.new
2 points·by pranay01·il y a 10 mois·0 comments

comments

pranay01
·il y a 7 mois·discuss
open source observability platform - https://github.com/signoz/signoz
pranay01
·il y a 9 mois·discuss
SigNoz | US Remote | Forward Deployed Engineer, DevRel and Growth Marketing | Full-Time | $120K-$200K

SigNoz is an open source observability platform based natively on OpenTelemetry. We developers monitor their applications & infrastructure, and troubleshoot problems quickly. https://github.com/SigNoz/signoz

We have crossed 23000+ Github stars, 6000+ members in the slack community and 150+ contributors.

We are expanding our US team & hiring for the following roles:

Forward Deployed Engineer - https://jobs.ashbyhq.com/SigNoz/8f0a2404-ae99-4e27-9127-3bd6...

DevRel Engineer - https://jobs.ashbyhq.com/SigNoz/8447522c-1163-48d0-8f55-fac2...

Growth Marketing - https://jobs.ashbyhq.com/SigNoz/a3644d27-3dfc-44cb-962d-5f27...

if interested, reach out directly to us at [email protected]. Mention that you saw this post in HN
pranay01
·il y a 10 mois·discuss
like that it is based on OTel. can you share the project if it is public?
pranay01
·il y a 10 mois·discuss
I guess, agents are making workflows much smarter - where the LLMs can decide what tools to call and make a decision, rather than following condition based work flows.

Agents are not that different than what lot of us are already doing. they just add a tad bit of non-detereminism and possibly intelligence to these workflows :)
pranay01
·il y a 10 mois·discuss
Yes, it is happening because OpenInference assumes these span kind values https://github.com/Arize-ai/openinference/blob/b827f3dd659fc...

Anything which doesn't fall in other span kinds is classified as `unknown`

For reference, these are span kinds which opentelemetry emits - https://github.com/open-telemetry/opentelemetry-python/blob/...
pranay01
·il y a 10 mois·discuss
one of the cases we have observed is that Phoenix doesn't completely stick to OTel conventions.

More specifically, one issue I observed is how it handles span kinds. If you send via OTel, the span Kinds are classified as unknown

e.g. The Phoneix screenshot here - https://signoz.io/blog/llm-observability-opentelemetry/#the-...
pranay01
·il y a 10 mois·discuss
interesting. So, you mean say if an agent is working on automatically doing a PR review, how many such calls to agents are failing, how much time they are taking, etc?

Lot of this you can do with traces today which trace AI specific calls
pranay01
·il y a 10 mois·discuss
> leveraged for agent platforms & orchestration

can you share more on what you mean by this?
pranay01
·il y a 10 mois·discuss
thanks for the detailed note

> My first "sniff test" for observability platforms is a tool to quickly jump to a given trace/span by ID.

You should be able to do this in SigNoz https://www.loom.com/share/71a2a95b76584b3983d9eeebb60ac420?...

> "show this event within the surrounding context"

we have this in the context logs. does this solve your use case or you mean something else? https://www.loom.com/share/9039afd5c4bf45e7b357a22c9943bb32?...

>But you make up for that by having bad search in traces

Did you mean for this to search across all attributes in spans or when you know which attribute you want to search in? If later, than you can do this through our query builder even today.

Your feedback on "Trace View" is fair. We are planning some improvements on that
pranay01
·il y a 10 mois·discuss
I don't think the primary goal here is "surveillance" but better understanding where in the team are tools like claude code getting adopted, what models are being used, are there best practices to learn in token usage which could make it more efficient
pranay01
·il y a 10 mois·discuss
great to hear. yes, it can help understand how developers are using Claude Code and also optimise token usage etc.
pranay01
·il y a 10 mois·discuss
SigNoz maintainer here. Curious, when did you try SigNoz (which version/which timeframe) and any specific feedback on what you don't like about it's tracing UI? Would be helpful for us to understand areas to improve on
pranay01
·il y a 10 mois·discuss
you might want to take a look at SigNoz - https://github.com/SigNoz/signoz logs, metrics & traces in a single pane and you can create advanced alerts and dashboards as well

PS: I am one of the maintainers
pranay01
·il y a 10 mois·discuss
hey, SigNoz maintainer here.

Can you share which version of SigNoz did you try or what time frame? We recently made a lot of improvement in how you can host SigNoz including support for Postgres and better docs fro self hosting corretcly - https://signoz.io/docs/collection-agents/get-started/