Hermes basically rules my personal life at this point - it is a _very_ useful personal assistant.

I also use it at work (integrated at Slack) and at this point it answers most of both my emails and slack messages (I calibrated https://github.com/blader/humanizer with a large corpus of my own voice to make it less annoying for the others). My routine now involving walking in circles while exchanging messages with hermes directing it how to answer this or that... Hermes uses an llm-wiki ( https://gist.github.com/karpathy/442a6bf555914893e9891c11519... ) as a source of information when drafting suggested replies - I have a cronjob that feeds it all emails, slack messages, meeting minutes every single day.

Claude Code with Opus 4.6 for multimodal/vision, design and writing tasks ("Create a crisp memo from this meeting transcription" is a prompt that will bring great results with either Opus 4.6 or GLM-5.1) - very recently I started to use https://github.com/anomalyco/opencode occasionally with opus models too (I am forcing myself a little bit because it is hard to help people with a tool you are unfamiliar with).

For building software automatically I currently use one of the harness above for for launching https://tamandua-tetradactyla.nfshost.com/ feature-dev-merge-worktree runs (it provides workflows on top of PI+deepseek).

Where it comes from: until recently I used https://steve-yegge.medium.com/welcome-to-gas-town-4f25ee16d... for automatic software building but while planning an AI bootcamp I concluded that teaching Gas Town along with everything else would be impossible (too hard/complex), and decided to teach https://github.com/snarktank/antfarm instead but did not want to add OpenClaw as one more dependency - so I built Tamandua ( https://github.com/igorhvr/tamandua ) and I ended up using it all the time! I now every single day before going to sleep launch a couple of runs and it is very cool waking up to see them done.

For autoresearch-like, optimization, and other tasks with a very clear measurable goal (such as increasing test coverage, changing things from one programming language to another, etc) I use https://github.com/davebcn87/pi-autoresearch (100% of the time on top of deepseek-v4-pro).

For debugging or very hard problems I use codex w/ GPT5.5. I don´t like its personality (lazy) but I do think it is smartest model available. As evidence, here is a commit of a problem where I tried Opus 4.8, Deepseek-v4-pro and a couple of other models and they all failed to understand what the bug was: https://github.com/NousResearch/hermes-agent/pull/38198/chan... - once the bug was found within codex I launched from it a tamandua bug-fix-merge-worktree run on top of deepseek-v4-pro that created the commit itself...

As a web application I use OpenWebUI and I am specially fond of the notes feature ( https://docs.openwebui.com/features/notes/ ) which I did not find anywhere else.

Last but not least, I love playing with local models. https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct is my current favorite for coding and deepseek-r1 for general tasks. I also started yesterday testing https://github.com/antirez/ds4 - it works _very_ well from what I could see so far.

What comes next? Trying to figure out what is the "deepseek-v4-pro of multimodal" model (frontier performance, efficient/comparatively cheap to run, support for image/audio/video/etc). Currently using kimi-k2.6, will test Minimax M3 soon.

Ah, almost forgot: https://huggingface.co/microsoft/VibeVoice-ASR will give you AMAZINGLY good meeting transcriptions (my hermes vibecoded a program to use it). Seriously, night and day difference from what the big players provide natively in their platforms. Have 8 people talking in 3 different languages? No problem - you will need a bit of patience and beefy hardware, only..

Milquetoast perfectly describes it, I am happy to see less common words used around here (specially when the convey the intended meaning this precisely), and I find claiming "affectation" of the person who used it unnecessarily rude.

Comments URL: https://news.ycombinator.com/item?id=35357323

Points: 2

# Comments: 0

   ls -lah | croc send  

Thanks for this link!

Two quotes from one of the posts referenced in the submission (from Steve Yegge):

...I know I haven’t gone into a lot of specific details about GCP’s deprecations. I can tell you that virtually everything I’ve used, from networking (legacy to VPC) to storage (Cloud SQL v1 to v2) to Firebase (now Firestore with a totally different API) to App Engine (don’t even get me started) to Cloud Endpoints to… I dunno, everything, has forced me to rewrite it all after at most 2–3 years, and they never automate it for you, and often there is no documented migration path at all. It’s just crickets. And every time, I look over at AWS, and I ask myself what the fuck I’m still doing on GCP. ...

... Update 3, Aug 31 2020: A Google engineer in Cloud Marketplace who happens to be an old friend of mine contacted me to find out why C2D didn’t work, and we eventually figured out that it was because I had committed the sin of creating my network a few years ago, and C2D was failing for legacy networks due to a missing subnet parameter in their templates. I guess my advice to prospective GCP users is to make sure you know a lot of people at Google… ...

The thing here is that if you run hundreds of services in production - many of which work smoothly and you don't need to touch often, you will find that Google's habit of forcing you to change how to use their tooling will generate a huge burden...

They discourage you from using it and make it clear that for every use case some other tool at AWS would be best, and have been doing so for several years now... They wont even list it anymore under https://aws.amazon.com/products/databases/ ..

Still, they support it ( https://aws.amazon.com/simpledb/ ) because there are customers with legacy systems that depend upon this service.

Comments URL: https://news.ycombinator.com/item?id=26897106

Points: 391

# Comments: 243

https://git-annex.branchable.com/walkthrough/

When someone in the business team mentioned they were using this tool to automate a few flows I assumed it would be an abject failure (as happened in so many similar projects I saw before - in some cases in multi-million deployments with huge teams of tools such as PEGA ).

Fast forward a couple of weeks and to my surprise an entire pipeline of needs from the operation where solved/fulfilled with almost no interaction from anyone in the development team. More than that: the end result is understandable.

Cavet emptor, maybe other teams will build horrible piles of crap with it, etc, etc but overall I am still impressed.

Nowadays I send the email I will paste below to every new hire after a couple of months in the team..

Some people never bother to schedule the conversation (less than 20%) and I leave it at that. For the other folks - the big majority - I had great conversations/results from this effort. Learned a ton of surprising things, found hidden talents within the team, found and then went to fix serious problems.

The email:

Subject: Talk.

Oi , how are you doing?

I would like to establish a communication channel between us, and as a first step towards this have a conversation - can you please schedule a 30 minutes conversation with me using https://.youcanbook.me/ ? Feel free to pick any available slot there - if it is open it means I will be available and working at this time. We can talk using (if we happen to be at the same building we can have the conversation personally).

Before the conversation I would like to ask you to please think carefully about the following questions, and be prepared to discuss what you understand as most important:

- How can I help you?

- Is there anything you would like to tell me?

- Is there anything you would like to ask me?

- What is your profile? What are your strenghts that you like to mention? What do you like doing the most? What motivates you?

- If you were in my place, is there anything you would change? What?

- Who are the 2 people you most admire within the company? Why?

- What information you assume I don't have that you can give me and will allow me to do my work better?

- Where do you inconsistencies between what we preach and what is in our culture document at and between day-to-day practice?

- Is there anything you would change in our culture document? Is there anything missing that you judge it is important?

- What are you current attributions? Do you judge you day-to-day challenging enough and do you see the company helping you grow or do you feel you need more space?

- Is there any self-managed project ( ) that you would like to establish?

- What do you understand as key to grow in our company?

- Do you receive enough feedback to grow and improve performance?

- Do you consider your leadership micromanages you, stays pretty far, or typically can find right balance in each situation?

- Do you feel your leadership cares about you?

- In your view does your leadership communicate very clearly what are the objectives to be achieved? Does it support the team in staying focused on what is most important?

- How do you evaluate the quality of the company information you receive? Do you feel you regularly receive relevant information from senior leadership to understand where we are going? How do you evaluate your own participation in setting the company direction?

- Do you feel your leaders have the necessary technical skills to manage your work effectively?

- Would you recommend your leader to other people in the company?

- What feedbacks you have to give me? What concerns you the most in my work? What makes you happy and you want to make sure I continue doing?

Regards,

At any case, I hired him fairly recently for a security audit and he worked quickly, and was very effective (he found several important vulnerabilities and reported them in a crystal clear manner). He was also a pleasure to deal with (no bullshit stance, something I find enjoyable).

The 4000 USD for ~20 hours of work were definitely well spent!

Of course it is as secure as the virtualbox Sanbox is, but some variation of this statement would also be true for Flash, for Java and a host of other technologies that despite whatever flaws they had did allow a lot of interesting things to be built.

I am here musing, trying to come up with something nice I could build once the Linux-packaged version is made available...