ahmadyan

Google is still very good, just get rid of evil stuff on their homepage to get the old google.

https://www.google.com/search?&udm=web&q=hackernews

i'm not sure if i'm hallucinating, but i swear i had codex in the chatGPT app from long time ago (like the original codex on the web).

they added some new stuff, like remote control to wherever the desktop codex app is running, but these companies need to work much more on their press releases.

yeah, even on product lines that they kill (like Stadia) they usually do right by the user (eg they refunded everyone, both on hardware and software people bought on the platform).

In my anecdotal experience, it is not. Same model, opus, works better in 3P harnesses such as Factory Droid or Amp.

Claude code, on the other hand, is the most subsidized one, both for consumers (through max subscription) and for enterprises (token discounts). It is also heavily optimized for cost, specially token caching and reduced thinking, at the expense of quality.

Previously cheapest Mac-mini was $599, M4 with 16GB RAM and 256 SSD. Apple removed the 256GB Option, so now the cheapest Mac-mini is now has 512GB SSD and MSRP of $799.

The Openclaw and personalized/proactive agents caused a sudden surge on Mac-Minis.

i just want to know where emdash came from, as it is quite rare to see it on the public internet, so it must have been synthetically added to the dataset.

They are about to lose the second 9

99.02 % uptime

look at zach's reply below.

make sense, thank you for your response.

this make sense, thanks

Congrats on open-sourcing warp.

May i ask what was the decision process behind this? What was the benefit of open-sourcing warp, as it is already a mature and established product. Also did devin cli had any impact on the decision to open-source warp?

Also how does a repo gets 29k starts in matter of 2 hours?

> Barring them from leaving the country feels a bit sinister for people who haven't been accused of committing any crimes.

Pure speculation on my part, but i would be surprised if China didn't have our equivalent of export control laws, not difficult to fabricate a crime and pin it on founders.

generally speaking

ultra ~ mythos ~ gpt-4.5 ~ 4x behemoth

pro ~ opus ~ 2x maverick

flash ~ sonnet ~ scout ~ other 20-30b active Chinese models

> ”What cannot be mended must be transcended.”

such a dark and gloomy quote as the mission statement.

I love it!

Quite the opposite, AI should work longer and interrupt the human less often (Tokens are cheap, interruptions are expensive). So we want to push the agent's horizon to infinite, now when they do make interruptions (e.g. Creating diff) it will be larger chunks and more complex, so these summaries are actually quite useful.

They aquired Vercep, and their older agent Vy did have background agent. IIRC the recent computer-use agent in Claude is based on Vy, so i'm kinda surprised that feature didn't carry over to Claude desktop app.

> I'm not going to build my business or my development flows on things I can't replicate myself.

but you can replicate these yourself! i'm happy that ant/oai are experimenting to find pmf for "llm for dev-tools". After they figure out the proper stickyness, (or if they go away or nerf or raise prices, etc) you can always take the off-ramp and implement your own llm/agent using the existing open-source models. The cost of building dev-tools is near zero. it is not like codegen where you need the frontier performance.

A few months ago, i took the bullet and migrated my notes from Notion to .md files. This was the second time i migrated my notes (last time from Evernote to Notion), and this time it was a lot easier. Kudos to the Notion team for making export so easy.

Just downloaded the notes, then told Claude to organize and remove duplicate or index mds (Notion keeps a lot of random indexes) and clean up and within 30mins i had a very clean and usable (and agent accessible) md vault. I can open it in Obsidian or other md file viewer (as well as my own code editor). I opted for obsidian.

Setup was super straight-forward. I do miss the visual editor in Notion (obsidian editor is not as smooth, and i find myself just writing the files in text instead of using their visual mode).

for sync, i use icloud, and it syncs between the iphone and the mac app flawlessly, didn't have any issue with corruptions (yet). I use the phone app as mostly an intake, and the desktop app for mostly visualizations. I also tinkered with adding git to track history (has to put the .git folder outside the repo with --separate-git-dir).

Obsidian has a terminal support (which i suppose folks can use to run agents in there) although i found it easier (habbit perhaps) to run my agents separately. They provide massive unlock as their turn my knowledge to an actual insight and can connect things that i didn't think it was possible before.

Overall, 75% happy. From first principle, file is as simple as it gets and i think this is good enough personal knowledge management. I do miss sharing capabilities as well as multi-user in Notion, so i don't think this is useful for 2player/team/corp.

the best implementation i've worked with was SuperSmartLog (SSL) at Meta, which was open-sourced at interactive smartlog (https://sapling-scm.com/docs/addons/isl/). There are also extension for it in VSCode, etc.

Surprisingly it never gained the adoption it deserved.

well, you can view it Iranian are willing to insure the vessel for $2M fee - that it will not get hit by them during the crossing ;). Once they are in the Oman sea, they can use traditional insurance.

because he is giving them at 90% discount in their subscription. they are more than happy if you use the tokens at api pricing, but when subsidized they want you to use their claude code surface.

opencode is a very meh agent.

Source: i run pretty much all of these agents (codex, cc, droid, opencode, amp, etc) side-by-side in agentastic.dev and opencode had basically 0 win-rate over other agents.

source?

Congrats on the launch

good point, they are standards, by definition society forced vendors to behave and play nice together. LLMs are not standards yet, and it is just pure bliss that english works fine across different LLMs for now. Some labs are trying to push their own format and stop it. Specially around reasoning traces, e.g. codex removing reasoning traces between calls and gemini requiring reasoning history. So don't take this for granted.

Claims in the article are incorrect. They conveniently ignore Meta CWM models, which are open-sourced [1] and open-weight [2] and are at 65% SWE-bench verified (with TTS) and 54% pass@1 and the same size (32B dense). So claims like "surpassing prior open-source state-of-the-art coding models of comparable sizes and context lengths" and conveniently leaving out the previous OSS SOTA out of your eval tables are ... sketch.

[1]https://github.com/facebookresearch/cwm [2]https://huggingface.co/facebook/cwm

> 2. What on earth is this defense of their product?

i think the distribution channel is the only defensive moat in low-to-mid-complexity fast-to-implement features like code-review agents. So in case of linear and cursor-bugbot it make a lot of sense. I wonder when Github/Gitlab/Atlassian or Xcode will release their own review agent.

Problem with Code Review is it is quite straightforward to just prompt it, and the frontier models, whether Opus or GPT5.2Codex do a great job at code-reviews. I don't need second subscription or API call when the first one i already have and focus on integration works well out of the box.

In our case, agentastic.dev, we just baked the code-review right into our IDE. It just packages the diff for the agent, with some prompt, and sends it out to different agent choice (whether claude, codex) in parallel. The reason our users like it so much is because they don't need to pay extra for code-review anymore. Hard to beat free add-on, and cherry on top is you don't need to read a freaking poems.

This is an awesome library, thank you so much for making it. I just ported it to my IDE, agentastic.dev, and works like a charm.

https://assets.agentastic.ai/agentastic-dev-assets/videos/0....