HNHacker News
TopNewBestAskShowJobs

thecopy

2,080 karma · joined March 26, 2014

Building https://www.gatana.ai - secure agentic communications platform
submissionscomments
thecopy··on Tokens too cheap to meter
Well, the thing with renewables is that the energy is not destroyed. When you use a solar panel is does not disappear
thecopy··on Show HN: Laptop is the last place your secrets are still in plaintext
What is wrong with it?
thecopy··on DeepSeek API Pricing Update
Peak Hours: 01:00–04:00 and 06:00–10:00 UTC

For European and US customers this is effectively 2x increase. I think i wll keep using both Flash and Pro as before.

EDIT: Misread numbers to believe off-peak kept old prices

thecopy··on llama.cpp
Except the first time you do it
thecopy··on llama.cpp
Sure, but doesn't this assume that you cannot the publisher anyway? So why would you not trust their homepage but trust their source-code
thecopy··on llama.cpp
How so? As i understand your point, this would mean we cannot trust GitHub enough to return the same content in git clone vs curl?
thecopy··on llama.cpp
>Nothing is arbitrary nor mutable in the default state.

What do you mean with this?

thecopy··on llama.cpp
>Anything that suggests curl into bash just plain sketches me out.

How is it different than trusting any other method of installation? If URL has https and is from an author you trust i dont see the difference.

thecopy··on Ask HN: What are you working on? (August 2026)
Im working on an extensible and flexible agentic connectivity platform (MCP, OpenAPI/Swagger, FaaS) with niceties like built-in CodeMode, compression, SIEM integration, access token forwarding, SCIM 2.0, on-demand agentic sandboxes (e.g. LangChains "Deep Agents").

For private use not that useful tbh (although i found the OpenAPI -> MCP mapper useful), but found sales success with organizations with more complex agentic setups.

Gatana: https://www.gatana.ai/

thecopy··on Qwen3.8-Max: A New Bar for Coding and Cowork
I agree with parent. OpenRouter might be cheaper list-price, but i have been using 10$ on DS platform since April/May, still have 2$ left. Using OpenRouter i depleted the same dollar-amount in a 1-2 weeks with same usage pattern. No idea why.
thecopy··on Kubeside – a Kubernetes client that shows your app, not your cluster
Love the idea, any plans on making TUI based? Like k9s? :)
thecopy··on Passkeys were invented by engineers with zero understanding of consumer brain
1. Use Passkey from 1Password

2. Profit

thecopy··on Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA
When DeepSeek was released, it had an immidiate and significant impact on the US stock-market. Now when its becoming common knowledge that China is almost at parity with US SOTA models with good momentum, why is there no sentiment change on the market?
thecopy··on Kimi K3: second only to Fable 5 on AA-Briefcase
When DeepSeek was released, it had an immidiate and significant impact on the US stock-market. Now when its becoming common knowledge that China is almost at parity with US SOTA models with good momentum, why is there no sentiment change on the market?
thecopy··on LongCat-2.0, a large-scale MoE model with 1.6T total and 48B Active
Am i the only one feeling my soul being emptied every time i read another "brutal shorthand" or "honest take"?
thecopy··on MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second
DS through OpenRouter is significantly slower than direct from DS platform in my experience
thecopy··on MCP is dead?
Every mature MCP gateway solution should implement Code Mode (e.g. https://docs.gatana.ai/code-mode/) - it circumvents all the arguments.

In the end MCP is just a protocol for discovering tools. And agents _need_ to do stuff with tools.

thecopy··on DuckDuckGo search saw 28% more visits after Google said people love AI mode
I genuinely find DDG more effective than Google Search. I have used it as a daily driver for 2+ years now. When i cannot find anything with DDG, i try with the !g macro, but results are more often than not even worse.
thecopy··on Show HN: Airbyte Agents – context for agents across multiple data sources
Super interesting idea! Congrats on the launch. Context is definitely something that is lacking in my experience. Im always frustrated when an agent cannot answer business-related questions, and i compare them to coding agents which seem to be able to answer everything. The difference is that coding agent has the context right there at the fingertips, while for business its gated behind a bunch of services and custom data models. Context is king :)

How do you handle encryption and confidentiality? Im building in this space too (MCP gateway https://www.gatana.ai/) which already have semantic search for tool outputs, and ensuring encryption and confidentiality is not trivial.

thecopy··on Changes to GitHub Copilot individual plans
That is not necessarily true.
thecopy··on Changes to GitHub Copilot individual plans
>$39 Github Pro+ to keep using Opus,

For what its worth, i have been paying for Pro+ and i still got locked out of Opus. I only have access to Opus 4.7 at 7.5x

thecopy··on Changes to GitHub Copilot individual plans
I have Copilot Pro+ and discovered i cannot use Opus anymore today! Are we reaching the end of VC funded productivity?
thecopy··on Ask HN: What Are You Working On? (April 2026)
Gatana: https://www.gatana.ai/

Extremely flexible and configurable MCP Gateway, target users is enterprises/companies/organizations who want secure and managed MCP within their company. Support both Cloud and On-premise.

thecopy··on iPhone 17 Pro Demonstrated Running a 400B LLM
Stupid question: can i run this on my 64GB/1TB mac somehow easily? Or this requires custom coding? 4bit is ~200GB

EDIT: found this in the replies: https://github.com/Anemll/flash-moe/tree/iOS-App

thecopy··on Mistral AI Releases Forge
Looks interesting. But how to explore or test or use? The product page (https://mistral.ai/products/forge) also does not contain anything useful. Just "Contact us"

Dissapointing.

thecopy··on Apideck CLI – An AI-agent interface with much lower context consumption than MCP
Shameless plug: im working on a product that aims to solve this: https://www.gatana.ai/
thecopy··on Ask HN: What Are You Working On? (March 2026)
Building Gatana, a platform for securely connecting an organizations agents to their services, with very flexible credential management and federated IDP trust.

Currently my mini-projects includes:

* 0% USA dependency, aim is 100% EU. Currently still using AWS SES for email-sending and GCP KMS for customer data key encryption for envelope encryption.

* Tool output compression, inspired by https://news.ycombinator.com/item?id=47193064 Added semantic search on top of this using a local model running on Hetzner. Next phase is making the entire chain envelop encrypted.

* "Firewall" for tool calls

* AI Sandboxes ("OpenClaw but secure") with the credential integration mentiond above

https://www.gatana.ai/

thecopy··on Apple Studio Display and Studio Display XDR
I use Ergotron, super happy.
thecopy··on Iran war wreaking havoc on shipping and air cargo, could create global delays
Air power alone has _never_ achieved regime change.
thecopy··on MCP server that reduces Claude Code context consumption by 98%
I implemented this as well successfully. Re structured data i transformed it from JSON into more "natural language". Also ended up using MiniLM-L6-v2. Will post GitHub link when i have packaged it independently (currently in main app code, want to extract into independent micro-service)

You wrote:

>A search for “review configuration” matches every JSON file with a review key.

Its good point, not sure how to de-rank the keys or to encode the "commonness" of those words

Page 1 of 16Next →