I have no insight, but I would assume it's a 1-1 sort of split, that is that everyone that previously had one share of sourcegraph now has one share of sourcegraph and one of amp? That seems like the least legally fraught way to do it.
No insight here either, but I would guess it is a spin-off ... mostly because it is a US company and in the US spin-off's are generally tax free to both company and shareholders.
Spin-off is where the parent company creates a subsidiary and distributes the shares in the subsidiary to the existing shareholders. So the shareholders end up holding shares of two companies. Share allocation is done on a pro-rata basis so each shareholder still has the same exposure they did before.
What are the chances we see local models rendering these paid IDEs useless? I presume it will be a very long time before we see a good enough local model that can compete with their ad supported frontier models on the vast majority of machines out there (I presume most people don't have the latest and greatest)?
I was watching the CEO of that Chad IDE give an interview the other day, they are doing the same thing as amp just with "brain rot" ads/games etc instead (different segment, fine), they are using that activity to produce value (ads/game usage or whatever) for another business such they can offset the costs of more expensive models. (I presume this could extend out into selling data also, but I don't know they do that today)
Congrats to the amp team on all the success btw, all I hear is great things about the product, good work.
You have to pay by the token, without being able to use your subscription, right? If so, is it better enough than the coding agent that the others ship with to make up for that loss? This is a crowded space.
I do wonder what the moat is around this class of products (call it "coding agents").
My intuition is that it's not deep... the differentiating factor is "regular" (non LLM) code which assembles the LLM context and invokes the LLM in a loop.
Claude/Codex have some advantage, because they can RLHF/finetune better than others. But ultimately this is about context assembly and prompting.
I love AMP, it delivers great results. I like that it’s opinionated in how it should be used and for example tells me that I need to hand off context.
I love that I am not welded to one model and someone smart has evaluated what’s best fit for what.
It’s a bit a shame they lost Steve Yegge as their brand ambassador. A respected and practicing coder is big endorsement.
16 comments
[ 0.20 ms ] story [ 40.6 ms ] threadAmp was built by Sourcegraph, so I assume all investors and employees of Sourcegraph now get equity in Amp?
Spin-off is where the parent company creates a subsidiary and distributes the shares in the subsidiary to the existing shareholders. So the shareholders end up holding shares of two companies. Share allocation is done on a pro-rata basis so each shareholder still has the same exposure they did before.
I was watching the CEO of that Chad IDE give an interview the other day, they are doing the same thing as amp just with "brain rot" ads/games etc instead (different segment, fine), they are using that activity to produce value (ads/game usage or whatever) for another business such they can offset the costs of more expensive models. (I presume this could extend out into selling data also, but I don't know they do that today)
Congrats to the amp team on all the success btw, all I hear is great things about the product, good work.
But then I switched to GLM 4.6 using Claude CLI tool and that was good enough and significantly cheaper/faster.
Then Opus 4.5 came out with better pricing and might as well just use that directly. Still working great.
With Amp I was spending $5 here and there every day. Great, but pricey.
Because if I understand them correctly, aren’t they a wrapper around all the major LLMs (focused specially on developer use cases?
My intuition is that it's not deep... the differentiating factor is "regular" (non LLM) code which assembles the LLM context and invokes the LLM in a loop.
Claude/Codex have some advantage, because they can RLHF/finetune better than others. But ultimately this is about context assembly and prompting.
I love that I am not welded to one model and someone smart has evaluated what’s best fit for what. It’s a bit a shame they lost Steve Yegge as their brand ambassador. A respected and practicing coder is big endorsement.
To anyone on the fence - give it a go.