[HN Gopher] Microsoft Amplifier
       ___________________________________________________________________
        
       Microsoft Amplifier
        
       Author : JDEW
       Score  : 194 points
       Date   : 2025-10-11 15:19 UTC (7 hours ago)
        
 (HTM) web link (github.com)
 (TXT) w3m dump (github.com)
        
       | ukFxqnLa2sBSBf6 wrote:
       | [flagged]
        
         | dang wrote:
         | Please don't post like this to this site. It's against the
         | guidelines (https://news.ycombinator.com/newsguidelines.html)
         | because we're trying for something else here.
        
           | ukFxqnLa2sBSBf6 wrote:
           | My apologies, won't happen again
        
       | hansmayer wrote:
       | >"Amplifier is a complete development environment that takes AI
       | coding assistants and supercharges them with discovered patterns,
       | specialized expertise, and powerful automation -- turning a
       | helpful assistant into a force multiplier that can deliver
       | complex solutions with minimal hand-holding."
       | 
       | Again this "supercharging" nonsense? Maybe in Satiyas
       | confabulated AI-powered universe, but not in the real world I am
       | afraid...
        
       | zb3 wrote:
       | README files in the "ai_context" directory provide the ultimate
       | AI Slop reading experience..
        
         | qsort wrote:
         | Yeah, I'm not even that opposed to using AI for documentation
         | if it helps, but everything from Microsoft recently has been
         | full-on slop. It's almost like they're trying to make sure you
         | can't miss it's AI generated.
        
           | rectang wrote:
           | "Eat your own dog slop" isn't bad practice, though.
           | 
           | Some people in the organization will experience the
           | limitations and some will learn -- although there are bound
           | to be people elsewhere in the organization who have a vested
           | interest in not learning anything and pushing the product
           | regardless.
        
       | npalli wrote:
       | Contributors
       | 
       | claude Claude
       | 
       | Interesting given Microsoft's history with OpenAI
        
         | wiether wrote:
         | History in AI is rewritten on a daily basis
         | 
         | https://techcrunch.com/2025/09/09/microsoft-to-lessen-relian...
        
         | mark212 wrote:
         | more than history -- early, massive investment in OpenAI by
         | Microsoft and formerly their exclusive compute provider.
         | 
         | This stood out to me too, seems like a months-long project with
         | heavy use of Claude
        
       | neuroelectron wrote:
       | aka Winamp
        
       | bgwalter wrote:
       | Can we get Windows 7 back instead? Nadella rode the cloud wave in
       | an easy upmarket, his "AI" obsession will fail. No one wants
       | this.
       | 
       | The Austrian army already switched to LibreOffice for security
       | reasons, we don't need another spyware and code stealing tool.
        
         | SilverElfin wrote:
         | > Nadella rode the cloud wave in an easy upmarket
         | 
         | I would say it's more the result of anti competitive bundling
         | of cloud things into existing enterprise contracts rather than
         | the wave. Microsoft is far worse than it ever was in the 90s
         | but there's no semblance of antitrust action in America.
        
         | falcor84 wrote:
         | > No one wants this
         | 
         | There are many many people who want better AI coding tools,
         | myself included. It might or might not fail, but there is a
         | clear and strong opportunity here, that it would be foolish of
         | any large tech company to not pursue.
        
           | bgwalter wrote:
           | Their own employees have to be surveilled and coerced to use
           | their own dog food:
           | 
           | https://news.ycombinator.com/item?id=45540174
        
       | jug wrote:
       | I'll always be skeptical about using AI to amplify AI. I think
       | humans are needed to amplify AI since humans are so far
       | documented to be significantly more creative and proactive in
       | pushing the frontier than AI. I know, it's maybe a radical
       | concept to digest.
        
         | dr_dshiv wrote:
         | Based on clear, operational definitions, AI is definitely more
         | creative than humans. E.g., can easily produce higher scores on
         | a Torrance test of divergent thinking. Humans may still be more
         | innovative (defined as creativity adopted into larger systems),
         | though that may be changing.
        
           | qlm wrote:
           | This is absurd to the point of being comical. Do you really
           | believe that?
           | 
           | If an "objective" test purports to show that AI is more
           | creative than humans then I'm sorry but the test is deeply
           | flawed. I don't even need to look at the methodology to
           | confidently state that.
        
           | hansmayer wrote:
           | More creative? I've just seen my premium subscription "AI"
           | struggling to find a trivial issue of a missing import in a
           | very small / toy project. Maybe these tools are getting all
           | sorts of scores on all sorts of benchmarks, I dont doubt it,
           | but why are there no significant real-world results after
           | more than 3 years of hype? It reminds of that situation when
           | the geniuses at Google offered the job to the guy who created
           | Homebrew and then rejected him after he supposedly did not do
           | well on one of those algorithmic tasks (inverting a binary
           | tree? - not sure if I remember correctly). There are also all
           | sorts of people scoring super high on various IQ tests, but
           | what counts, with humans as with the supposed AI is the real
           | world results. Benchmarks without results do not mean
           | anything.
        
           | vachina wrote:
           | It is as creative as it's training material.
           | 
           | You think it is creative because you lack the knowledge of
           | what it has learnt.
        
         | jsheard wrote:
         | > I'll always be skeptical about using AI to amplify AI.
         | 
         | This project was in part written by Claude, so for better or
         | worse I think we're at least 3 levels deep here (AI-written
         | code which directs an AI to direct other AIs to write code).
        
         | Balinares wrote:
         | I think I'm more optimistic about this than brute-forcing model
         | training with ever larger datasets, myself. Here's why.
         | 
         | Most models I've benchmarked, even the expensive proprietary
         | models, tend to lose coherence when the context grows beyond a
         | certain size. The thing is, they typically do not need the
         | entire context to perform whatever step of the process is
         | currently going on.
         | 
         | And there appears to be a lot of experimentation going on along
         | the line of having subagents in charge of curating the long
         | term view of the context to feed more focused work items to
         | other subagents, and I find that genuinely intriguing.
         | 
         | My hope is that this approach will eventually become refined
         | enough that we'll get dependable capability out of cheap open
         | weight models. That might come in darn handy, depending on the
         | blast radius of the bubble burst.
        
       | tcdent wrote:
       | > Never lose context again. Amplifier automatically exports your
       | entire conversation before compaction, preserving all the details
       | that would otherwise be lost. When Claude Code compacts your
       | conversation to stay within token limits, you can instantly
       | restore the full history.
       | 
       | If this is restoring the entire context (and looking at the
       | source code, it seems like it is just reloading the entire
       | context) how does this not result in an infinite compaction loop?
        
       | chews wrote:
       | Billions in investment into OpenAI and this is a wrapper for
       | Claude API usage. This is very much a microsoft product.
        
       | rco8786 wrote:
       | A lot of snark in these comments. Has anyone actually tried it
       | yet?
        
         | SilverElfin wrote:
         | I've seen people discuss these types of approaches on X. To me
         | it looks like the concepts here are already tried and popular -
         | they're just packaging it up so that people who aren't as deep
         | in that world can get the same benefits. But I'm not an expert.
        
           | ridruejo wrote:
           | Exactly. I don't understand the cynicism in the comments and
           | they literally are just trying to make the technology more
           | accessible
        
             | nozzlegear wrote:
             | That's a very altruistic outlook on Microsoft's intent with
             | getting everyone to use and depend on AI.
        
               | vachina wrote:
               | Microsoft is on a roll, on a roll at repackaging open
               | source efforts and branding them, and then saying they
               | made it.
        
               | otterley wrote:
               | Isn't that what every company that sells technology does
               | --build demos and showcase uses in order to provoke the
               | imagination and motivate sales? No company is perfect,
               | but what Microsoft is doing here is hardly unusual.
        
         | ramraj07 wrote:
         | I have two hypotheses:
         | 
         | 1. It affects the fundamental ego of these engineers that a
         | computer can do what they thought only they could do and what
         | they thought made them better than the rest of the population.
         | They might not realize this of course.
         | 
         | 2. AI and all these AI systems are intelligence multipliers,
         | with a zero around IQ 100. Zero multiplied by zero is zero, and
         | negative multiplier just leads to garbage. So the people who
         | say "I used AI and its garbage" should really think hard about
         | what it says about them. I thought I was crazy to think of this
         | hypothesis but someone else also mentioned the exact statement
         | and I didnt think I was just being especially mean anymore.
        
           | Angostura wrote:
           | You seem to be assuming that the negative multiplier is on
           | the human side of the equation. There's your mistake
        
           | milutinovici wrote:
           | Alternative hypothesis is that you work on trivial problems,
           | and therefore you get a lot of help from LLMs. Have you
           | considered this?
        
             | ramraj07 wrote:
             | Im definitely not creating the next StuxNet for sure. So
             | Ill bow down to whoever is writing the next C compiler I
             | suppose.
        
           | hansmayer wrote:
           | 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
           | fact built by engineers and not by the "rest of the
           | population", like yourself. Now having said that, I am early
           | adopter myself, was happy to pay the premium costs for my
           | entire company, if the tool was any kind of amplifier. But
           | the crap just does not work. Recently the quality is
           | degrading so much that we simply reduced it to using it for
           | simple consultation - and we only do it because unfortunately
           | the search has been ruined. Otherwise most of the folks both
           | internally and externally that I know using these tools would
           | be happy to just go back to google search and SO.
           | Unfortunately that's not an option. Also see if your second
           | argument makes any sense at all. Maybe it comes out of a
           | lacking math background? Firstly, you don't need two zeroes
           | to get a zero out at the end of the multiplication. And
           | secondly, if an average engineer is a zero, what are folks
           | like you then? But again, it maybe just your own
           | projections...
        
             | ramraj07 wrote:
             | For some reason youre assuming Im not an engineer which is
             | funny and revealing.
             | 
             | I am an engineer and my vibe coded prototype is now in
             | production, one of the best applications of its type in the
             | industry, and doing really well. So well, I have a pretty
             | large team working on it now. This project was and still is
             | 95% written by AI. No complaints, never going back. That's
             | my experience.
             | 
             | Clearly the eng community is splitting into two categories,
             | people who think this is all never going to work and people
             | who think otherwise. Time will tell who's right.
             | 
             | To anyone else reading and thinking closer to the second
             | side, we're hiring :)
        
               | bgwalter wrote:
               | Which company so we can avoid it?
        
               | hansmayer wrote:
               | Hey no need to prove yourself to a stranger on the
               | Internet. I'll take your word for it, including your
               | "pretty large team working on it", which for some reason
               | is necessary, although you have "vibe coded 95%" of your
               | application. So if you were to be taken by your word, the
               | LLMs are fantastic and you can do 95% production-ready on
               | your own, just using the LLMs, but for some reason,
               | you'll still need a "pretty large team" to work on it
               | afterwards. Yeah, that sounds very consistent with your
               | main line. Also feel free to share your company and
               | product name, so we can avoid it - thanks.
        
               | system2 wrote:
               | hansmayer, I think your "debate" skills need some
               | improvement.
               | 
               | >"no need to prove yourself to a stranger on the
               | Internet"
               | 
               | In this case, the stranger is you, and you say it as if
               | he is debating with someone else. This proves you lost
               | the debate and are now attacking personally.
               | 
               | People can easily detect these little nuances.
        
               | LtWorf wrote:
               | phd in medical engineering doesn't scream "computer
               | science expert" to me.
        
               | Keyframe wrote:
               | trust me bro vibes
        
           | bgwalter wrote:
           | This is like a person who thinks that making a photocopy of
           | an Einstein paper makes him Einstein. You know, Einstein
           | wasn't that special after all and the photocopier affects his
           | fundamental ego.
        
         | hansmayer wrote:
         | 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.
        
           | fishmicrowaver wrote:
           | Hehe suddenly many people will have the real problem of
           | paying bills unfortunately
        
             | hansmayer wrote:
             | They will, especially when it comes to paying back the VCs
             | all the burnt GenAI-dollars
        
               | bee_rider wrote:
               | I thought VCs were investors.
               | 
               | Generally when your investment fails you don't get paid
               | back, right?
        
         | rs186 wrote:
         | The repo is full of big AI words without any metrics/benchmark.
         | 
         | People are correct to question it.
         | 
         | If anything, Microsoft needs to show something meaningful to
         | make people believe it's worth trying it out.
        
       | rs186 wrote:
       | > This project is a research demonstrator.
       | 
       | I went through the whole README but couldn't find any hint about
       | this actually making existing agents more effective/accurate or
       | make fewer mistakes.
       | 
       | The whole thing, at the very least, throws the simplicity of
       | existing tools out of the window, and make everything 20x
       | complicated.
       | 
       | I seriously doubt if Microsoft has any objective metrics
       | (benchmarks) -- even cherry-picked ones -- to show this project
       | is not a complete waste of time.
       | 
       | btw the whole repo looks like it's AI generated slop.
       | 
       | [To cowards who downvoted me without leaving a comment: show me
       | some numbers and prove me wrong.]
        
       | alganet wrote:
       | > "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 it done quickly.
        
       | vincnetas wrote:
       | Starting in Claude bypass mode does not give me confidence:
       | 
       | WARNING: Claude Code running in Bypass Permissions mode | | | |
       | In Bypass Permissions mode, Claude Code will not ask for your
       | approval before running potentially dangerous commands. | | This
       | mode should only be used in a sandboxed container/VM that has
       | restricted internet access and can easily be restored if damaged.
        
         | nine_k wrote:
         | The Readme clearly states:
         | 
         |  _Caution
         | 
         | This project is a research demonstrator. It is in early
         | development and may change significantly. Using permissive AI
         | tools in your repository requires careful attention to security
         | considerations and careful human supervision, and even then
         | things can still go wrong. Use it with caution, and at your own
         | risk._
        
           | vincnetas wrote:
           | Claude Code will not ask for your approval before running
           | potentially dangerous commands.
           | 
           | and
           | 
           | requires careful attention to security considerations and
           | careful human supervision
           | 
           | is a bit orthogonal no?
        
             | otterley wrote:
             | It's not orthogonal at all. On the contrary, it's directly
             | related:
             | 
             | "Using permissive AI tools [that is, ones that do not ask
             | for your approval] in your repository requires careful
             | attention to security considerations and careful human
             | supervision". Supervision isn't necessarily approving every
             | action: it might be as simple as inspecting the work after
             | it's done. And security considerations might mean to
             | perform the work in a sandbox where it can't impact
             | anything of value.
        
             | nine_k wrote:
             | As a token of careful attention, run this in a clean VM,
             | properly firewalled not to access the host, your internal
             | network, GitHub or wherever your valuable code lives, and
             | ideally anything but the relevant Anthropic and Microsoft
             | API endpoints.
        
               | thethimble wrote:
               | And even then if you give it Internet access you're at
               | risk of code exfiltration attacks.
        
         | cyral wrote:
         | If they didn't have this warning you'd see comments on how
         | irresponsible they are being
        
         | nicwolff wrote:
         | I assumed, especially with the VS Code recommendation, that
         | this would automatically use devcontainers...
        
       | koakuma-chan wrote:
       | Is this is a Claude Code wrapper?
        
         | skrebbel wrote:
         | Yes
        
       | xorgun wrote:
       | Is this going to be another HN dropbox moment?
        
       | furyofantares wrote:
       | I do a lot of work with claude code and codex cli but frankly as
       | soon as I see all the LLM-tells in the readme, and then all the
       | commit messages written by claude, I immediately don't want to
       | read the readme or try the project until someone else recommends
       | it to me.
       | 
       | This is gaining stars and forks but I don't know if that's just
       | because it's under the github.com/microsoft, and I don't really
       | know how much that means.
        
         | nightshift1 wrote:
         | Future LLMs are going to be trained on this. Github really
         | ought to start tagging repos that are vibe-coded.
        
         | typpilol wrote:
         | I'd rather have in-depth commit messages then three word ones
        
           | furyofantares wrote:
           | When I blind-commit claude code commit messages they are
           | sometimes totally wrong. Not even hallucinations necessarily
           | - by the time I'm committing the context may be large and
           | confusing, or some context lost.
           | 
           | I'd rather have the three word message than detailed but
           | wrong messages.
           | 
           | I think I agree with you anyway on average. Most of the time
           | a claude-authored commit message is better than a garbage
           | message.
           | 
           | But it's still a red flag that the project may be filled with
           | holes and not really ready for other people. It's just so
           | easy to vibe your way to a project that works for you but is
           | buggy and missing tons of features for anyone who strays from
           | your use case.
        
             | typpilol wrote:
             | You're not wrong.
             | 
             | I'd never encourage anyone to blind commit the messages But
             | if they are correct they seem a lot more useful than 90% of
             | commit messages.
             | 
             | I found the biggest mistakes that I've seen other people do
             | are like - they move a file, and the commit message acts
             | like it's a brand new feature they added because the llm
             | doesn't put it together it's just a moved file
        
       | nightshift1 wrote:
       | 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 making LLMs more deterministic
       | with the help of good old-fashioned software tooling instead of
       | role-playing and writing prayers to the LLM god.
        
         | hu3 wrote:
         | Yeah in my experience, LLMs are great but they still need
         | babysitting lest they add 20k lines of code that could have
         | been 2k.
        
         | danmaz74 wrote:
         | 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.
        
           | thethimble wrote:
           | 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.
        
             | pjc50 wrote:
             | > hundreds of thousands of these things in parallel
             | 
             | At what cost,. monetary and environmental?
        
           | spike021 wrote:
           | this plus a reset in between steps usually helps focus
           | context in my experience
        
           | anditherobot wrote:
           | 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.
        
             | genghisjahn wrote:
             | 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 as devs would just rather talk with machines.
        
         | tummler wrote:
         | I also use AI to do discrete, well-defined tasks so I can keep
         | an eye on things before they go astray.
         | 
         | But I thought there are lots of agentic systems that loop back
         | and ask for approval every few steps, or after every agent does
         | its piece. Is that not the case?
        
       | lpcvoid wrote:
       | [flagged]
        
         | dang wrote:
         | Ok, but please don't post shallow dismissals of other people's
         | work to HN. This is in the site guidelines:
         | https://news.ycombinator.com/newsguidelines.html.
        
           | lpcvoid wrote:
           | You're right, my comment was not good.
        
       | estimator7292 wrote:
       | The very first line in the readme is a quote, attributed to "the
       | problem we're solving".
       | 
       | That's cute
        
         | nvader wrote:
         | If you think about it, that's because "the problem we're
         | solving" is running out of time. Once it's solved it won't be
         | able to try out ideas.
        
       | theusus wrote:
       | Didn't GitHub create something similar called Spec.
        
         | janpio wrote:
         | You are thinking of https://github.com/github/spec-kit
        
       | CuriouslyC wrote:
       | A lot of the ideas in this aren't bad, but in general it's hacky.
       | Context export? Just use industry standard observability! This is
       | so bad it makes me cringe. Parallel worktrees? These are prone to
       | putting your repo in bad states when you run a lot of agents, and
       | you have to deal with security, just put your agent in a
       | container and have it clone the repo. Everything this project
       | does it's doing the wrong way.
       | 
       | I have a repo that shows you how to do this stuff the correct way
       | that's very easy to adapt, along with a detailed explanation,
       | just do yourself a favor, skip the amateur hour re-
       | implementations and instrument/silo your agents properly:
       | https://sibylline.dev/articles/2025-10-04-hacking-claude-cod...
        
       | stillsut wrote:
       | I've actually written my own a homebrew framework like this which
       | is a.) cli-coder agnostic and b.) leans heavily on git worktrees
       | [0].
       | 
       | The secret weapon to this approach is asking for 2-4 solutions to
       | your prompt running in parallel. This helps avoid the most time
       | consuming aspect of ai-coding: reviewing a large commit, and
       | ultimately finding the approach to the ai took is hopeless or
       | requires major revision.
       | 
       | By generating multiple solutions, you can cutdown investing fully
       | into the first solution and use clever ways to select from all
       | the 2-4 candidate solutions and usually apply a small tweak at
       | the end. Anyone else doing something like this?
       | 
       | [0]: https://github.com/sutt/agro
        
         | thethimble wrote:
         | There is a related idea called "alloying" where the 2-4
         | candidate solutions are pursued in parallel with _different
         | models_ , yielding better results vs any single model. Very
         | interesting ideas.
         | 
         | https://xbow.com/blog/alloy-agents
        
           | michaelbarton wrote:
           | This reminds me of an an approach in mcmc where you run
           | mutiple chains at different temperatures and then share the
           | results between them (replica exchange MCMC sampling) the
           | goal being not to get stuck in one "solution"
        
           | stillsut wrote:
           | Exactly what I was looking for, thanks.
           | 
           | I've been doing something similiar: aider+gpt-5, claude-
           | code+sonnet, gemini-cli+2.5-pro. I want to coder-cli next.
           | 
           | A main problem with this approach is summarizing the
           | different approaches before drilling down into reviewing the
           | best approach.
           | 
           | Looking at a `git diff --stat` across all the model outputs
           | can give you a good measure of if there was an existing
           | common pattern for your requested implementation. If only one
           | of the models adds code to a module that the others do not,
           | it's usually a good jumping off point to exploring the
           | differing assumptions each of the agents built towards.
        
       | nopelynopington wrote:
       | I was hoping this was going to be an awesome new music player,
       | but no, everything new thing is AI now. Welcome to the future
        
       | willahmad wrote:
       | Project looks interesting, but no demos. As much I want to try it
       | because of all cool concepts mentioned, but I am not sure I want
       | to invest my time if I don't see any demos
        
         | fishmicrowaver wrote:
         | I mean that's fair but doing a make install and providing your
         | API key is pretty easy?
        
       | lordofgibbons wrote:
       | There are hundreds of these on github. Why should we care? Why
       | not release any benchmarks or examples?
        
       | ripped_britches wrote:
       | Please comment under this thread if you have actually tried this
       | and can compare it to another tool like Cursor, Codex, raw
       | Claude, etc.
       | 
       | I'm super not interested in hearing what people have to say from
       | a distance without actually using it.
        
       ___________________________________________________________________
       (page generated 2025-10-11 23:00 UTC)