Hacker News: ting0

New comment by ting0 in "Open source memory layer so any AI agent can do what Claude.ai and ChatGPT do"

ting0 — Sat, 25 Apr 2026 11:55:11 +0000

It's not clear to me how or why this works, and how it compares to just using md files in my project. For something like this, we really need benchmarks.

New comment by ting0 in "Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)"

ting0 — Sat, 25 Apr 2026 11:45:39 +0000

Hey man, if it works it works. There's a reason everyone is creating AI tools. We're all buying them. I'm still waiting for someone to make a world-class cli harness that can replace Claude Code but solves the memory and design problem. Web design is still a nightmare with LLMs.

New comment by ting0 in "Ask HN: Open-Source Coding Model and Harness at Claude Sonnet / Opus Level Perf?"

ting0 — Sat, 25 Apr 2026 04:19:43 +0000

It's terrible, don't waste your time like I did. That bench means nothing by the way.

New comment by ting0 in "DeepSeek v4"

ting0 — Fri, 24 Apr 2026 21:03:15 +0000

> It’s my experience that models that perform very well on benchmarks do not necessarily perform well in real life

Well, yeah... Like Opus 4.5, 4.6, 4.7. Top of the benchmarks and yet it's a pile of crap at the moment and has been for months.

New comment by ting0 in "DeepSeek v4"

ting0 — Fri, 24 Apr 2026 21:01:41 +0000

This is nonsense. The real reason is because the US companies are scamming the public, as per usual.

New comment by ting0 in "DeepSeek v4"

ting0 — Fri, 24 Apr 2026 21:00:54 +0000

They don't make sense, they're a lie that these AI companies keep spamming using bots so that useful idiots perpetuate it, so that they can keep draining us of money. Straight out of the Anthropic handbook. They've always been cheap to run. I wouldn't be surprised if Anthropic is running for <$1 for 1M/tok.

New comment by ting0 in "Turtle WoW classic server announces shutdown after Blizzard wins injunction"

ting0 — Mon, 20 Apr 2026 14:30:50 +0000

Well this sucks. It's funny that Blizzard with its vast empire of wealth can't even compete with TurtleWoW.

New comment by ting0 in "Ask HN: How to solve the cold start problem for a two-sided marketplace?"

ting0 — Mon, 20 Apr 2026 14:28:17 +0000

Don't waste your time. I've been down this road and unless you've got business connections or a LOT of marketing money, it is not worth attempting.

New comment by ting0 in "Are the costs of AI agents also rising exponentially? (2025)"

ting0 — Sat, 18 Apr 2026 09:04:15 +0000

No, but the AI labs would love to frame it this way so they can continue to nerf models and increase prices while they use the cheap, highly performant, highly powerful models internally to replace all of your businesses.

New comment by ting0 in "Sometimes powerful people just do dumb shit"

ting0 — Tue, 14 Apr 2026 07:46:41 +0000

The Twitter example is a bad one. Elon Musk, at the time, was making hundreds-of-millions through crypto-market manipulation on Twitter. At that time he realized that having control over the entire Twitter platform would unlock many billions of dollars worth of profit opportunity. Attention is the most valuable and powerful currency in this world. Not only for manipulating markets, but also for political propaganda. The information we consume literally shapes the world. So yes, it was a 4D chess move.

New comment by ting0 in "Some iPhone Apps Receive Mysterious Update 'From Apple'"

ting0 — Tue, 07 Apr 2026 09:10:15 +0000

Has anyone ever done a proper security audit of VLC that is downloaded from the web? I don't trust it, and the fact that their releases on Github don't include binaries makes me trust it even less. Nobody is compiling VLC from source, and they don't provide any sort of provenance from the GH actions pipeline.

New comment by ting0 in "Issue: Claude Code is unusable for complex engineering tasks with Feb updates"

ting0 — Mon, 06 Apr 2026 18:28:13 +0000

Thinking time is not the issue. The issue is that Claude does not actually complete tasks. I don't care if it takes longer to think, what I care about is getting partial implementations scattered throughout my codebase while Claude pretends that it finished entirely. You REALLY need to fix this, it's atrocious.

New comment by ting0 in "Issue: Claude Code is unusable for complex engineering tasks with Feb updates"

ting0 — Mon, 06 Apr 2026 18:21:25 +0000

Do you guys realize that everyone is switching to Codex because Claude Code is practically unusable now, even on a Max subscription? You ask it to do tasks, and it does 1/10th of them. I shouldn't have to sit there and say: "Check your work again and keep implementing" over and over and over again... Such a garbage experience.

Does Anthropic actually care? Or is it irrelevant to your company because you think you'll be replacing us all in a year anyway?

New comment by ting0 in "Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw"

ting0 — Sun, 05 Apr 2026 00:05:45 +0000

Whenever Anthropic has an opportunity to do what's right, they go the opposite way. For example, their source leaks, and instead of open-sourcing it like people have been asking to happen for years so they can contribute fixes because Anthropic doesn't care to maintain their own software, they tighten the noose further.

If it isn't obvious by now, this problem is only going to get worse. The only reason we have subscriptions still is because they're waiting to pull off the biggest bait and switch in history. Don't get sunk on this ecosystem, or you're in for a world of pain in the future. As has always been the case; competition and open-source are our only hope.

New comment by ting0 in "The sudden fall of Sora"

ting0 — Mon, 30 Mar 2026 04:57:55 +0000

They're just removing it from public access and selling it to big money instead. Think large advertising companies, government agencies, Coke-Cola, Hollywood, etc. The scary part is now that they've removed it publicly, it's going to be harder to keep a pulse on what is real and what is fake. We can't trust any video, audio or text content now.

New comment by ting0 in "LinkedIn uses 2.4 GB RAM across two tabs"

ting0 — Mon, 30 Mar 2026 04:49:50 +0000

The only reason to ever use LinkedIn is if you're in the process of finding a job. Other than that, it's a cesspit.

Even for that though, I've never used it, and I don't feel like I'm missing out.

New comment by ting0 in "From 0% to 36% on Day 1 of ARC-AGI-3"

ting0 — Fri, 27 Mar 2026 08:22:55 +0000

You have a problem with generating synthetic data from test questions? Humans simulate experiences in their mind. What's the problem?

New comment by ting0 in "Day 1 of ARC-AGI-3"

ting0 — Fri, 27 Mar 2026 08:21:57 +0000

Does it matter though? If it accomplishes the task, it accomplishes the task. Everyone uses a harness anyway, and finding the best harness is relevant. Also perhaps this hints at something bigger, i.e.: we're wasting our time focusing on the model when we could be focusing on the harness.

New comment by ting0 in "My minute-by-minute response to the LiteLLM malware attack"

ting0 — Thu, 26 Mar 2026 17:10:15 +0000

They will certainly get worse. LLMs make it so much easier.

New comment by ting0 in "My minute-by-minute response to the LiteLLM malware attack"

ting0 — Thu, 26 Mar 2026 17:08:03 +0000

I feel like they should be legally responsible for providing scanning infrastructure for this sort of thing. The potential economic damage can be catastrophic. I don't think this is the end of the litellm story either, given that 47k+ people were infected.