Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Microsoft Amplifier

github.com

Post reply on HN
Print view View original

141–150 of 171 posts

Re: Microsoft Amplifier

#141

Post by tclancy »

alganet wrote: post #36

> "I have more ideas than time to try them out" — The problem we're solving I see a possible paradox here. For exploration, my goal is _to learn_. Trying out multiple things is not wasting time, it's an intensive learning experience. It's not about finding what works fast, but understanding why the thing that works best works best. I want to go through it. Maybe that's just me though, and most people just want to get…

Yeah, this seems like the opposite of invention. You can throw paint at a canvas but it won’t make you Pollock. And will you feel a sense of accomplishment?

Re: Microsoft Amplifier

#142

Post by meander_water »

danmaz74 wrote: post #95
nightshift1 wrote: post #69

I think that letting an LLM run unsupervised on a task is a good way to waste time and tokens. You need to catch them before they stray too far off-path. I stopped using subagents in Claude because I wasn't able to see what they were doing and intervene. Indirectly asking an LLM to prompt another LLM to work on a long, multi-step task doesn't seem like a good idea to me. I think community efforts should go toward mak…

When the task is bigger than I trust the agent to work on it on its own, or for me to review the results, I ask it to create a plan with steps. Then create a md file for each step. I review the steps, and ask the agent to implement the first one. Review that one, fix it, then ask it to update the next steps, and then implement the next one. And so on, until finished.

This is built into Cursor now with plan mode https://cursor.com/docs/agent/planning

Re: Microsoft Amplifier

#143

Post by thethimble »

pjc50 wrote: post #128
thethimble wrote: post #112

Earlier quoted context omitted.

Separately, you have to consider that "wasting tokens spinning" might be acceptable if you're able to run hundreds of thousands of these things in parallel. If even a small subset of them translate to value, then you're far net ahead vs with a strictly manual/human process.

> hundreds of thousands of these things in parallel At what cost,. monetary and environmental?

If the system provides value that is greater than its cost, then paying the cost to gain the value is always worthwhile - regardless of the magnitude of the cost.

As costs drop exponentially (a reasonable expectation for LLMs, etc.) then increasing agent parallelism becomes more and more economically viable over time.

Re: Microsoft Amplifier

#144

Post by danmaz74 »

meander_water wrote: post #142
danmaz74 wrote: post #95

Earlier quoted context omitted.

When the task is bigger than I trust the agent to work on it on its own, or for me to review the results, I ask it to create a plan with steps. Then create a md file for each step. I review the steps, and ask the agent to implement the first one. Review that one, fix it, then ask it to update the next steps, and then implement the next one. And so on, until finished.

This is built into Cursor now with plan mode https://cursor.com/docs/agent/planning

How does Cursor plan mode differ from Claude Code plan mode? I've used the latter a lot (it's been there a long time), and the description seems very similar. The big difference with the workflow I described is that with that plan mode you don't get to review and correct what happened between steps.

Re: Microsoft Amplifier

#145

Post by ahartmetz »

thethimble wrote: post #143
pjc50 wrote: post #128

Earlier quoted context omitted.

> hundreds of thousands of these things in parallel At what cost,. monetary and environmental?

If the system provides value that is greater than its cost, then paying the cost to gain the value is always worthwhile - regardless of the magnitude of the cost. As costs drop exponentially (a reasonable expectation for LLMs, etc.) then increasing agent parallelism becomes more and more economically viable over time.

>As costs drop exponentially

Not a reasonable expectation anymore. Moore's Law has been dead for more than a decade and we're getting close to physical limits.

Re: Microsoft Amplifier

#146

Post by nsonha »

hansmayer wrote: post #64
ramraj07 wrote: post #41

Earlier quoted context omitted.

[flagged]

Nothing to do with ego, but you may want to check your own projections, you know how when you speak of the others, you mainly speak of yourself (Jung or Freud, not sure). No need to be bitter about not having the grind and focus to become an engineer yourself, it is after all much harder than say, earning an MBA and you should be OK with whatever you turned out to be. Not to mention that the tools themselves, were in…

> Recently the quality is degrading so much

You can say it sucked and still continue to suck, but that LLM/agentic AI is degrading is simply false. Such a statement really makes me question the genuinity of the rest of the comment.

Re: Microsoft Amplifier

#147

Post by hansmayer »

nsonha wrote: post #146
hansmayer wrote: post #64

Earlier quoted context omitted.

Nothing to do with ego, but you may want to check your own projections, you know how when you speak of the others, you mainly speak of yourself (Jung or Freud, not sure). No need to be bitter about not having the grind and focus to become an engineer yourself, it is after all much harder than say, earning an MBA and you should be OK with whatever you turned out to be. Not to mention that the tools themselves, were in…

> Recently the quality is degrading so much You can say it sucked and still continue to suck, but that LLM/agentic AI is degrading is simply false. Such a statement really makes me question the genuinity of the rest of the comment.

Well, unlike mine, "simply false" as we know, is the ultimate argument to prove one's point, isn´t it?

Re: Microsoft Amplifier

#148

Post by meander_water »

danmaz74 wrote: post #144
meander_water wrote: post #142

Earlier quoted context omitted.

This is built into Cursor now with plan mode https://cursor.com/docs/agent/planning

How does Cursor plan mode differ from Claude Code plan mode? I've used the latter a lot (it's been there a long time), and the description seems very similar. The big difference with the workflow I described is that with that plan mode you don't get to review and correct what happened between steps.

I've not used Claude Code, so my answer might not be that useful. But I would think that because both are chat-based interfaces you would be able to instruct the model to either continue without approval or wait for your approval at each step. I certainly do that with Cursor. Cursor has also recently started automatically generating TODO lists in the background (with a tool call I'm assuming), and displaying them as part of the thinking process without explicit instruction. I find that useful.

Re: Microsoft Amplifier

#149

Post by redhale »

genghisjahn wrote: post #129
anditherobot wrote: post #127

Earlier quoted context omitted.

Have you tried Scoped context packages? Basically for each task, I create a .md file that includes relevant file paths, the purpose of the task, key dependencies, a clear plan of action, and a test strategy. It’s like a mini local design doc. I found that it helps ground implementation and stabilizes the output of the agents.

I read this suggestion a lot. “Make clear steps, a clear plan of action.” Which I get. But then instead of having an LLM flail away at it could we give to an actual developer? It seems like we’ve finally realized that clear specs makes dev work much easier for LLMs. But the same is true for a human. The human will ask more clarifying questions and not hallucinate. The llm will role the dice and pick a path. Maybe we…

Yes, but the difference is that an LLM produces the result instantly, whereas a human might take hours or days.

So if you can get the spec right, and the LLM+agent harness is good enough, you can move much, much faster. It's not always true to the same degree, obviously.

Getting the spec right, and knowing what tasks to use it on -- that's the hard part that people are grappling with, in most contexts.

Re: Microsoft Amplifier

#150

Post by Incipient »

fishmicrowaver wrote: post #80
hansmayer wrote: post #57

Earlier quoted context omitted.

I think most of us are irritated by the constant A/B Testing and underwhelming releases. Lets just have the bubble pop so we can solve real problems instead of this.

Hehe suddenly many people will have the real problem of paying bills unfortunately

I'm super confused how anyone can actually afford to pay per token for llms to actually do dev.

I tried it with a feature, took about 10 minutes and a lot of iterations, and would easily have used hundreds of thousands of tokens. Doing this 20, 30 times a day would be crazy expensive.

Post reply on HN