Hacker News Reader

smartbiton PaperPilot – Zero-Cloud, Pure-Rust PDF Engine with WASM and MCP

Thanks for your reply. Will look into Jules [0] [1].

Are you using Antigravity IDE v2.5.5 that hasn't been updated since 2026-08-13 and that supports 3 legacy models + Gemini Flash 3.8? I assume you're using Gemini Flash 3.8?

[0] https://news.ycombinator.com/item?id=44034918 [1] https://news.ycombinator.com/item?id=44813854

smartbiton There are now 5 inference providers for abliterated DeepSeek

> using another unaligned model to rewrite reasoning and then feeding it back into the model

Indeed, would be interested to understand how you do that. And where do you run the model? On a local or a rented system and what are the specs?

smartbiton There are now 5 inference providers for abliterated DeepSeek

Selfhosted or one of the listed? If external/hosted, which one did you use?

smartbiton The new iPad mini

No Face ID, still Touch ID. Are they serious?

I was considering buying one, but will skip until the older model becomes unsupported or when Apple adds Face ID.

smartbiton PaperPilot – Zero-Cloud, Pure-Rust PDF Engine with WASM and MCP

Congrats with your product, hope it works out well. Nice competitor analysis & (future) features list at https://github.com/KrushnaVardhanReddy/PaperPilot/blob/main/..., IMHO easier to read than your above list.

Question: seemingly you’re using Antigravity, an harness not many use. Please tell use about the choice of LLM and your experience with it.

smartbiton New Apple TV 4K

Netflix works fine with the device directly connected to the TV. With a long hdmi-cable (5m+) + an usbc-to-hdmi converter you can keep de phone/pad in your hands. Using a short (≤2m) hdmi-usbc cable you probably need to put the device next to the TV. I bring either when traveling to watch TV in hotels rooms.

smartbiton Postgres isn't slow, your storage is

CloudNativePG supports Kubernetes Local Storage as one of its main features [0]

  Persistent volume management, including:
    Support for Local Persistent Volumes with PVC templates.
    Reuse of Persistent Volumes storage in Pods.
    Separate volumes for WAL files and tablespaces.

Chapter Temporary PostgreSQL Cluster Degradation [1] describes how to set it up and starts with this

> While the standard approach ensures service reliability and leverages Kubernetes' self-healing capabilities, there are scenarios where operating with a temporarily degraded cluster may be acceptable. This is particularly relevant for PostgreSQL clusters relying on node-local storage, where the storage is local to the Kubernetes worker node running the PostgreSQL database. Node-local storage, or simply local storage, is employed to enhance performance.

[0] https://cloudnative-pg.io/docs/devel/#main-features [1] https://cloudnative-pg.io/docs/devel/kubernetes_upgrade/#tem...

smartbiton Mistral Large 4

Too late to edit, now including AA-omni Score [0] and 'by Domain' Software Engineering [1]. Also added comparison to the eyeballs-median of the 'top 10' models and then you see that indeed Mistral Large 4 Preview scores miserable in the AA-Omni indices.

                          Inte         Cost     AA-   Omni
                          llig          per    Omni  Softw
  Open Weight model       ence  Speed  Task   score    Eng

  Mimo-V.26-Pro            46     47   $0.13      8     33
  GLM-5.3 (max)            45     73   $2.01     14     37
  DeepSeek 4.1 Flash Max   39    227   $0.27     -5     34
  Mistral Large 4 Preview  38    116   $1.13     -5      5

  Closed/proprietary      ~50   110-  $1.50-    ~43    ~85
     median top 10               242   $7.50

[0] https://artificialanalysis.ai/evaluations/omniscience [1] https://artificialanalysis.ai/evaluations/omniscience?detail...

smartbiton Mistral Large 4

https://artificialanalysis.ai/models/mistral-large-4 for the main stats

                          Inte         Cost
                          llig          per
  Open Weight model       ence  Speed  Task

  Mimo-V.26-Pro            46     47   $0.13
  GLM-5.3 (max)            45     73   $2.01
  DeepSeek 4.1 Flash Max   39    227   $0.27
  Mistral Large 4 Preview  38    116   $1.13

smartbiton Denmark Data Breach Exposes 8.8M People's Personal Data

Then this is something for you https://shop.digitalcourage.de/themen/ak-vorrat/lichtbildaus.... Either get it online, or buy at events like Chaos Computer Congress.

smartbiton Several vulnerabilities have been discovered in the Linux kernel

And normal people who can not apply for access to daybreak, should we use Abliterated GLM-5.3 ? [0] [1] [2]

[0] https://news.ycombinator.com/item?id=49605691 [1] https://news.ycombinator.com/item?id=49897075 [2] https://huggingface.co/models?other=offensive-security

smartbiton Gemini 4 Argon

do you mean?

  accept-edits

also available with shift-tab in agy cli [0]. That is not related to executing commands, only to allowing agy edit files. Unless you set Turbo-mode == yolo-mode, agy gui prompts a zillion times too.

With 'some features added' I'm referencing this but don't see change in daily work (still many prompts making getting-work-done impossible): v2.14.0 (September 15, 2026) "New Permissions System" [1]

Details: Introduced the new unified permissions system, presets (Default, Request Review, Turbo), syntax-highlighted permission requests, and restructured the settings under Global Permissions and project-level Inherit Global.

[0] https://antigravity.google/docs/cli/modes/#available-modes [1] https://antigravity.google/docs/changelog/

smartbiton Gemini 4 Argon

agy cli does not have auto mode. I've tried and tried and tried to work with agy cli sandbox-mode and just failed.

  agy --dangerously-skip-permissions

in my experience is the only workable solution that doesn't ask confirmation for every step. And I hate working in YOLO mode. Seemingly the Antigravity GUI had some features added in a recent release, but a) I don't want to work with the GUI and b) it was poorly implemented as I couldn't get it to work. VS Code plugins are allowed with subscriptions, but is not the CLI experience of Claude Code I want.

gemini-cli supported 'pre-write diff tabs' (y/n) in external editors like vscode. In Claude Code I heavily use 'pre-write diff tabs' for documentation and miss it sincerely in agy cli.

IMHO Gemini 3.8 flash is fast and good enough, but the agy-suite is below par to say it nice. Someone else in this thread calls agy a terrible harness which is probably more accurate.

smartbiton Prompting Claude Opus 5.5

to mog: to outshine, outclass

Etymology: probably from AMOG Alpha Male of the Group

First seen: 2018

smartbiton Frontier Labs Are Selling Garbage to Fools in Washington

I love it too. Seemingly written by an LLM. nr378 https://news.ycombinator.com/user?id=nr378 is the responsible ‘author’ and actively reacting in this thread.

smartbiton Typesafe-computer-use drives a Mac toward a goal for 1/50th of a cent per step

Jev docs gives a good explanation https://docs.typesafe.ai/concepts/system-one

Also see recent discussion https://news.ycombinator.com/item?id=49717558#49718350

smartbiton GLiClass: Open-Source JEV

Discussed at introduction of Jev https://news.ycombinator.com/item?id=49717558#49722740

> GLiClass performance is not is the same ballpark as Terra but the open model's still a useful foundation to work with.

smartbiton Discovery of a new OpenAI agent message board

Time to update Felony Bench https://www.felonybench.com - a benchmark you really don't want models to be saturated with

smartbiton Google Antigravity TOS: 3rd party usage can get Google account suspended

Is Antigravity CLI still the only TUI allowed for Gemini? Coming from Claude Code, agy is quite a few steps back. Particularly I miss /ide that can connect to vscode and then can display a pre-write diff which then can be acknowledged or declined in CC.

smartbiton OpenShot 4.0 – Open-source video editor

Video editor app that generates FFmpeg commands https://news.ycombinator.com/item?id=42207002

smartbiton Claude Session URL appended to commit messages and PR descriptions by default

Extend the cleanup period to 2 years in ~/.claude/settings.json with

  "cleanupPeriodDays": 720

and for personal projects move all Claude Code memory to the repo, then add a symlink eg

  PROJ="$HOME/.claude/projects/-$(echo "${PWD#/}" | tr '/' '-')"
  DST="$PWD/.claude/memory"

  [ -d "$PROJ" ] || { echo "No project dir: $PROJ" >&2; exit 1; }; mkdir -p "$DST"
  if [ -d "$PROJ/memory" ] && [ ! -L "$PROJ/memory" ]; then mv "$PROJ/memory"/* "$DST"/; rmdir "$PROJ/memory"; fi
  ln -sfn "$DST" "$PROJ/memory"

smartbiton Claude Session URL appended to commit messages and PR descriptions by default

According to https://gist.github.com/unkn0wncode/f87295d055dd0f0e8082358a... among many, the environment variable

  CLAUDE_CODE_SUPPRESS_SESSION_ATTRIBUTION

was added in CC version 2.1.202 on July 8, 2026. Setting it to value 1 will suppresses session-URL attribution (returns null instead of the session attribution info). I will set it, as suggested in this July 18 comment https://github.com/anthropics/claude-code/issues/66504#issue...

And in ~/.claude/CLAUDE.md this 'git rule' which works fine:

  Never add a Co-Authored-By line or any other reference to Claude in commit messages.

smartbiton Small Models Have Arrived

Trying until you find something that doesn’t fail is the model used throughout evolution & engineering, think of bridges collapsed, airplanes falling from the sky or exploded steam locomotives.

In engineering you learn from these mistakes and try never making them again. Do we want to go through this evolution every time we solve a software issue? Just because we can with an unlimited number of cheap tokens? I think not, I’d rather use the knowledge build up that also knows about the edge cases forgotten to test. Or better, use multiple models that evaluate each other, as Entropic describes it in their recent report https://news.ycombinator.com/item?id=49316271

> We expect that agents coordinating in the wild will act in higher variance ways than we see here, because they’ll have different backgrounds and therefore different contexts. They also, presumably, won’t all be Claudes.

smartbiton GLM-5.3-Flash Intelligence, Performance and Price Analysis

Looking at these numbers IMHO, with Gemini you get the speed what you pay for.

                    Intel    Cost    
                     lig      per
                     ence    Task   Speed

  Gemini 3.7 flash    56     0.40    338
  GLM 5.3 flash       57     0.09     49
  Factor               1      4.4    6.9

I have both GLM & Gemini in a subscription and see no reason for choosing GLM 5.3 Flash. Working with de speed of Gemini 3.7 Flash is such a delight that I accept the hassle of working with Antigravity CLI, coming from Claude Code which I use for GLM.

smartbiton A week of using Codex more than Claude

Anthropic confirmed it in their recent report https://news.ycombinator.com/item?id=49316271

smartbiton How Kubernetes Probes Work

I ported Kubernetes to the browser https://ngrok.com/blog/i-ported-kubernetes-to-the-browser

3 comments https://news.ycombinator.com/item?id=48734656

smartbiton Opus 5.0 drives incoherence into the stratosphere

  ELI5 = Explain Like I'm Five

smartbiton Dutch Train Map Simulator

Very nice.

It seems the 25kV https://en.wikipedia.org/wiki/Betuweroute is missing. Although mostly used for freight and therefor no or other type of schedule, it would be nice if it was projected at least.

smartbiton Qwen3.8 Max now ranked as the best overall model by agentic index

Any experience with Sleev as replacement of DCP?

See https://news.ycombinator.com/item?id=48883538 25 days ago

> The Sleev (the project has been renamed to make a startup) creator was shilling their project in the OpenCode Discord. That person is very convinced they have something that no one has ever built before. They focused on token reduction without any real evals for capability impacts.

I'm generally against this context pruning without prompting or details. Sleev is very opaque about how it works and definitely will bust your cache.