benjaminfh

Congrats team! Really enjoyed the warts and all video - those fly-away moments remind me of my first drone flights :D

Are you mostly software stack focused or designing lots of hardware too?

Super interesting. I need to give it a proper read through with fresh eyes!

I just posted a Show HN re my graph storage for research chat sessions - curious on your thoughts!

Really awesome and thoughtful thing you've built - bravo!

I'm so aligned on your take on context engineering / context management. I found the default linear flow of conversation turns really frustrating and limiting. In fact, I still do. Sometimes you know upfront that the next thing you're to do will flood/poison the nicely crafted context you've built up... other times you realise after the fact. In both cases, you didn't have that many alternatives but to press on... Trees are the answer for sure.

I actually spent most of Dec building something with the same philosphy for my own use (aka me as the agent) when doing research and ideation with LLMs. Frustrated by most of the same limitations - want to build context to a good place then preserve/reuse it over and over, fire off side quests etc, bring back only the good stuff. Be able to traverse the tree forwards and back to understand how I got to a place...

Anyway, you've definitely built the more valuable incarnation of this - great work. I'm glad I peeled back the surface of the moltbot hysteria to learn about Pi.

This is cool - I’ll definitely give it a try.

Re the patent of voice control, does it really sound defendable? That sounds a bit too obvious to be patentable at the level of “observe speaker’s speech and adjust text accordingly”, I’d have thought. Maybe they’ve patented a particular technical approach but now there must be dozens of voice to text models that you could leverage in a slightly different way. I’d love to try the result of something like that.

Seems to get a bit funky if I scroll on the screen while it’s playing. It changes the speed permanently until I reset. The speed slider also seems to invert after that??

I love the premise and I felt that a lot in SF. The transport system is not really a complex enough network that I need to be shown routing options. Just wanted to know when to leave the house and not stand at the stop for 20 minutes :’(

(In a highly networked place like London, seeing all options is helpful)

In those places salary (and good public services) follows respect

The next worst is to popularise its beauty on Instagram :’( . As a hobbyist landscape photog I have a complicated relationship with this

Do you do extra spam filtering? I see the advantage of not always giving out my email (I use Apple relay sometimes) but ultimately, a thing that routes to my email is another avenue for spam (until I kill that route).

Clay is expensive for sure. To clarify, it’s more of a data enrichment tool than a sequencing tool.

Do you do much in terms of SEO on the post pages?

Does WP actually provide (1) any more? I built my first personal (photog) website on WP about 10 years ago and it was ideal. I went to do a simple website this year and WP is web builder framework inception - it’s web builders all the way down. You install a theme and it brings its own rat nest. So yes, I think it’s cooked but was before this spat. Webflow is simple. I assume there’s an OSS alternative by now(?)

I had mixed feelings until I read the quote “better not to waste the credit”. That attitude rubs me up the wrong way for (a) a take what you need if/when you need it type perk and (b) someone being paid 400k.

I wouldn’t want to employ someone who saw their sick leave as something they deliberated used up in full each year (even when they didn’t need it). It’s a similar attitude IMO.

Do you have an ICP in mind right now? Reason I ask, is that while hyper scaler to hyper scaler makes sense and I can see that being easy to digest and therefore valuable to many, many enterprises are actually making more complicated trade offs. Namely a managed SaaS solution vs. (a pipe dream) of build it themselves on hyper scaler infra. IMO that’s the really interesting question plaguing enterprises and I saw it a lot when at Palantir doing pre sales engagement.

In practice, the hyper scalers often “buy” an enterprise customer by undercutting the incumbent (eg when a new CIO comes in), which makes the sticker price arbitrary a lot of the time.

I think a lot about software for productivity (my own niche obsession is note taking / retrieval). How much do you see this as a people problem? Specifically, I think there’s something usefully weighty about manual friction in defining follow up tasks (and writing notes manually) and automating these things can be unhelpful. Creating these artefacts helps my think, remember, re-think and prioritise. I basically wonder if automating things that engineering teams don’t like doing, means they can avoid engaging in the planning and put a tick in a box that it’s being done. I’m old fashioned though ;)

No question here, but love to see this, having been the grateful recipient of your support in the past, Peter! Thanks again.

(Peter is awesome!)

Ahah. Totally missed that, I will admit. I gratefully accept the pun and will be using it even more going forward.

If you're willing to chat on the technical details of that notebook, we'd love to. Of course, if you're hoping to build it one day and don't feel comfortable sharing, understand. If yes, it's founders@getpatchwork.io :)

We are definitely eyeing up what can be done when you control the log strings and the rest of the payload. And along the lines of what you say, our first step would be to see how much ClickHouse could squeeze that, and then see what other clever compression could be added in advance.

Anyone crushing it in the code analysis and refactoring space is a challenger. I think for now our sense is that the full-blown agentic SWE tools have bitten off more than they can chew and aren't viewed as credible just yet. However there are people out there taking a focused, use-case-specific approach (like us) who are building impressive things. komment.ai is one that springs to mind. SonarQube looks interesting - thanks for flagging.

In terms of logging stack players, we're hoping some could be friend rather than foe, at least to begin with. We thought ClickHouse might see unstructured logs as an unlock for their customers / GTM motion. However, they have invested a lot in their query-time materialisation tech, which they said their log storage customers love. Expensive, in practice, I suspect. Grafana actually pinged me yesterday.

Apologies, for all the thought put in to balancing conciseness with completeness, that was a bad miss. Right now we are focusing on Go and Java. We're flexible on logging libraries - if you have strong prefs here, we'd love to get that signal.

Moving forward we will be able to support Python, Ruby, TypeScript, JavaScript, Scala, and Kotlin as well.

I'll check the page issue on firefox. Thanks for the flag.

Thanks! Yeah, we're finding a lot of interest from small teams who want to move fast without accumulating tech debt / creating a negative trend between customer count an reliability as they start to find traction themselves.

Want to drop us an email (founders@getpatchwork.io)? Right now we do our best to make pricing work for our customers because the real value for us in this early stage is your feedback. (Cliche but true :) )

Thanks for the support, it means a lot to us! It would be a dream to see our products working together in the near future. Here's to a high-context future of debugging :)

The folk at Patched are doing great work - they are our YC batch mates! Alas, we cannot take credit for that write-up, sadly, nor answer the question re their source code. We are getpatchwork.io / Patchwork Technologies.

Thanks for the congrats :)

Thanks for pointing this one out, we weren't aware it could do that. Do you use those features yourself? We think it's an important enough problem that there's room for multiple people to be solving it, but very curious to hear if you think they have.

On the OSS piece, we are not ignoring this. It's very early days for us so we are figuring out how best to balance our limited resources and, in the future, make a thoughtful contribution to the community.

(Edit: just clocked that you _are_ OneUptime.com, so some of my questions won't make total sense. We'd love to understand how your users have responded to those capabilities, if you're willing to share)

Glad to hear that resonates. Goes without saying that we get the best reception with people who've literately done manual surges on this. Speaking from experience?

Going to double tap my own reply here and come back to the OTel peice. Do you find there's a lot of effort required in adding attributes to spans through your code? A lot of people we speak to who are all-in on tracing are (we think) getting by with minimal/auto span implementation, without attributes. We're trying to keep digging and learning about how this looks at different orgs / figure out if this approach holds as systems get more complex. Would our workflow as applied to adding attributes and messages to spans be useful to you?

We're thinking alike. While we're iterating with customers, we're also thinking about how we can use it to contribute beneficially to projects (and in doing so prove it works reliably). One thing we are keeping a list of is popular OSS repos with notoriously spammy logs - if you know any, please let us know! We are planning to start with some of our YC batch mates' OSS projects once we get the quality right. I won't say exactly when we started showing the "fixes" but it was _very_ recently. Ensuring accuracy on identifying exceptions to the rules (aka the appropriate statements to touch in the first place) is the first thing we are perfecting.

We could expand to comments. The code maintenance direction is a possibility but the reason we get out of bed right now is to make a worthy contribution to logging -> debugging -> SRE sleep :)

Thanks for flagging that one. It has turned out to be a very busy namespace. We're focusing on making sure the product sticks first... then figuring out if the name needs changing is a good problem to have! :D

Thanks for catching this and providing the feedback. We're iterating very hard to make sure the fixes are indeed always fixes!

I won't waste the chance to engage a logging connoisseur – could you see yourself using this if the hit rate was 99%?

Understood. The landing page so far is taking a back seat relative to making the product better for our early customers, which I'm sure you can appreciate. We hope to open source components of the product. In the mean time are there specific parts of the technical approach that you'd like us to see better described?

Structured/JSON saves a tonne of time building regex parsers. The regex parsing at query-time is also pretty expensive. This is where Splunk excels - dealing with the noise with powerful querying. ClickHouse is also very performant at this, we hear. It's an expensive task though (computationally and cost wise)

I thought this was well put together from Better Stack: https://betterstack.com/community/guides/logging/logging-bes...

Charity, CTO of Honeycomb has strong views (which we enjoy a lot): https://charity.wtf/tag/observability-2-0/ - they come at it from a tracing/OT angle which is Honeycomb's forte, but we agree a lot on the intended outcomes - actionable (not spammy/noisy) + make it easy to gather the variable/state context in the context of a single event.

That's very fair feedback, we appreciate it!

Great catch - we didn't include that rule in the demo but it's in the works. To share our thinking a little more: analysing the contents of the statement is easiest (but still quite hard) so we're nailing that down. Analysing the level requires a bit more careful understanding of what the method/code around it is attempting and where this logging statement sits (harder still). Soon we hope to nail adding statements to fresh code (where we'd have to understand where to put them, what the level should be, and then the contents).