31–40 of 42 posts
Can folks who have compared Amp with other agents share their experience? Some of my colleagues swear this is the best agent out there.
That aligns with my annecdata :)
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.
There is no moat. It's all prompts. The only potential moat is building your own specialized models using the code your customers send your way I believe.
The same thing is going to happen with all of the human language artifacts present in the agentic coding universe. Role definitions, skills, agentic loop prompts....the specific language, choice of words, sequence, etc really matters and will continue to evolve really rapidly, and there will be benchmarkers, I am sure of it, because quite a lot of orgs will consider their prompt artifacts to be IP.
I have personally found that a very high precision prompt will mean a smaller model on personal hardware will outperform a lazy prompt given to a foundation model. These word calculators are very very (very) sensitive. There will be gradations of quality among those who drive them best.
The best law firms are the best because they hire the best with (legal) language and are able to retain the reputation and pricing of the best. That is the moat. Same will be the case here.
Earlier quoted context omitted.
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.
yes that is easiest; or just be a 100% owned subsidiary. (that's what say, waymo is). the good thing is that you afterwards the cap table of the subsidiary or the spunoff can evolve (ex: waymo / amp can raise money independent of the parent company).
Earlier quoted context omitted.
yes that is easiest; or just be a 100% owned subsidiary. (that's what say, waymo is). the good thing is that you afterwards the cap table of the subsidiary or the spunoff can evolve (ex: waymo / amp can raise money independent of the parent company).
Why is that preferable to just pivoting?
Earlier quoted context omitted.
I don't understand how people use these tools without a subscription. Unless you are using it very infrequently paying per token gets costly very fast.
Work pays for it. I don't work for stingy companies that don't provide the tools required to do the job. (our team spends > $1000/m EACH on Amp alone)
Earlier quoted context omitted.
There is no moat. It's all prompts. The only potential moat is building your own specialized models using the code your customers send your way I believe.
I think "prompts" are a much richer kind of intellectual property than they are given credit for. Will put in here a pointer to the Odd Lots recent podcast with Noetica AI- a give to get M&A/complex debt/deal terms benchmarker. Noetica CEO said they now have over 1 billion "deal terms" in their database, which is only half a dozen years old. Growing constantly. Over 1 billion different legal points on which a complex…
You might get an 80% “good enough” prompt easily but then all the differentiation (moat) is in that 20% but that 20% is tied to the model idiosyncrasies, making the moat fragile and volatile.
Earlier quoted context omitted.
Work pays for it. I don't work for stingy companies that don't provide the tools required to do the job. (our team spends > $1000/m EACH on Amp alone)
Could you please share a little on why it's noticeably better than Claude Code on a sub (or 5? I mean, sometimes you can brute force a solution with agents)?
Earlier quoted context omitted.
I think "prompts" are a much richer kind of intellectual property than they are given credit for. Will put in here a pointer to the Odd Lots recent podcast with Noetica AI- a give to get M&A/complex debt/deal terms benchmarker. Noetica CEO said they now have over 1 billion "deal terms" in their database, which is only half a dozen years old. Growing constantly. Over 1 billion different legal points on which a complex…
But the problem is the tight coupling of prompts to the models. The half-life of prompt value is short because the frequency of new models is high, how do you defend a moat that can half (or worse) any day a new model comes out? You might get an 80% “good enough” prompt easily but then all the differentiation (moat) is in that 20% but that 20% is tied to the model idiosyncrasies, making the moat fragile and volatile.
Can folks who have compared Amp with other agents share their experience? Some of my colleagues swear this is the best agent out there.
https://www.askmodu.com/rankings independently aggregates traffic from a variety of agents and amp consistently has the highest success rate for small and large tasks That aligns with my annecdata :)
But my first thought looking at this is that the numbers are probably skewed due to distribution of user skill levels, and what types of users choose which tool.
My hypothesis is that Amp is chosen by people who are VERY highly skilled in agentic development. Meaning these are the people most likely to provide solid context, good prompts, etc. That means these same people would likely get the best results from ANY coding agent. This also tracks with Amp being so expensive -- users or companies are more likely to pay a premium if they can get the most from the tool.
Claude Code on the other hand is used by (I assume) a way larger population. So the percentage of low-skill users is likely to be much higher. Those users may still get value from the tool, but their success rate will be lower by some factor with ANY coding agent. And this issue (if my hypothesis is correct) is likely 10x as true for GitHub Copilot.
Therefore I don't know how much we should read into stats like the total PR merge success percentage, because it's hard to tell the degree of noise caused by this user skill distribution imbalance.
Still interesting to see the numbers though!
Can folks who have compared Amp with other agents share their experience? Some of my colleagues swear this is the best agent out there.
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.