Hacker News: mehdibl

New comment by mehdibl in "Microsoft is employing dark patterns to goad users into paying for storage?"

mehdibl — Thu, 09 Apr 2026 21:57:16 +0000

So to free up space you delete folders instead of moving your familyvphotos that you don't have backup.

Can we stop a bit this all evil Microsoft fault?

And the author have a solution. Yeah those headline are buzzing.

New comment by mehdibl in "Go hard on agents, not on your filesystem"

mehdibl — Sat, 28 Mar 2026 17:54:29 +0000

Docker is hard to setup. The author made a nice solution but not sure if he know devcontainer and what he can do. You do the setup once and you roll in most dev tools. I'm still surprised the effort people put in such solution ignore the dev's core requirements, like sharing the env they use in a simple way. You used it to have custom env and isolate the agent. You want to persist your credentials? Mount the target folder from home or sl into a sub folder. Might be knowledge. But for Linux or even Windows/Mac as long you don't need desktop fully. Devcontainer is simple. A standard that works. And it's very mature.

New comment by mehdibl in "Claude now creates interactive charts, diagrams and visualizations"

mehdibl — Thu, 12 Mar 2026 17:36:54 +0000

Isn't this mainly a skill injected in the context? Rather a model/platform specific feature?

New comment by mehdibl in "Show HN: A context-aware permission guard for Claude Code"

mehdibl — Thu, 12 Mar 2026 01:48:20 +0000

Lovely you discovered devcontainers.

New comment by mehdibl in "Show HN: Timber – Ollama for classical ML models, 336x faster than Python"

mehdibl — Mon, 02 Mar 2026 03:28:02 +0000

Ollama is quite a bad example here. Despite popular, it's a simple wrapper and more and more pushed by the app it wraps llama.cpp.

Don't understand here the parallel.

New comment by mehdibl in "Improving 15 LLMs at Coding in One Afternoon. Only the Harness Changed"

mehdibl — Thu, 12 Feb 2026 21:54:08 +0000

You can improve a lot the success rate with providing HELM and clear instructions with the tool description.

Over a year ago had a lot of issues and the description and example was the difference between 30-50% failure to 1%!

So I'm surprised a bit about the point. May be I'm missing it.

New comment by mehdibl in "Vouch"

mehdibl — Sun, 08 Feb 2026 19:58:14 +0000

Why in nushell? Not in go?

But I like the idea and principle. OSS need this and it's traded very lightly.

New comment by mehdibl in "Running Claude Code dangerously (safely)"

mehdibl — Wed, 21 Jan 2026 01:40:34 +0000

Devcontainer is not docker and do the trick!

New comment by mehdibl in "Get an AI code review in 10 seconds"

mehdibl — Sun, 21 Dec 2025 20:19:20 +0000

How to do agentic workflow like 2 years ago.

New comment by mehdibl in "Kimi K2 1T model runs on 2 512GB M3 Ultras"

mehdibl — Sun, 14 Dec 2025 15:57:17 +0000

Claims as always misleading as they don't show the context length or prefill if you use a lot of context. As it will be fun waiting minutes for a reply.

New comment by mehdibl in "llamafile: Distribute and Run LLMs with a Single File"

mehdibl — Sun, 14 Dec 2025 01:34:44 +0000

Issue llama.cpp is shipped and no more updated. Or you need to download it all.

New comment by mehdibl in "OpenAI are quietly adopting skills, now available in ChatGPT and Codex CLI"

mehdibl — Sat, 13 Dec 2025 02:31:30 +0000

This is killing me with complexity. We had agents.md and were supposed to augment the context there. Now back to cursor rules and another md file to ingest.

New comment by mehdibl in "I think nobody wants AI in Firefox, Mozilla"

mehdibl — Fri, 14 Nov 2025 18:04:19 +0000

May be Mozilla have a point.

Chat apps, are replacing a lot the old way we consume information and search. That is mostly made thru browser. So I see the vision is follow this transformation to keep market share and offer an alternative to big players.

Mozilla and Firefox loosing market share and revenue too and that could bite back.

New comment by mehdibl in "Benchmarking leading AI agents against Google reCAPTCHA v2"

mehdibl — Mon, 10 Nov 2025 19:07:02 +0000

Ok and then? Those models were not trained for this purpose.

It's like the last hype over using generative AI for trading.

You might use it for sentiment analysis, summarization and data pre-processing. But classic forecast models will outperform them if you feed them the right metrics.

New comment by mehdibl in "Drilling down on Uncle Sam's proposed TP-Link ban"

mehdibl — Mon, 10 Nov 2025 14:53:03 +0000

Previous report blaming TPlink slow to patch a CVE were already outdated as the CVE got patched. Yes TPlink are recieving updates if the products are not EOL. And even US products when EOL are vulnerable.

Seem more heavy lobbying to get their US marketshare here rathar than looking for secure products.

Also the report from checkpoint over firmware used to attache EU, the malware is firmware agnostic. As it can be used for other hardware.

New comment by mehdibl in "Deployment Confidence in Era of AI Coding"

mehdibl — Sun, 09 Nov 2025 17:18:19 +0000

Before investing in instruments, you should have a solid static analysis, unit tests, integration test and so on. Logging help flagging issues post deployment but you can catch a lot if you test.

New comment by mehdibl in "Grok 4 Fast now has 2M context window"

mehdibl — Sun, 09 Nov 2025 04:57:20 +0000

What matter is not context or the recod token/s you get.

But the quality for the model. And it seem Grok pushing the wrong metrics again, after launching fast.

New comment by mehdibl in "The Case That A.I. Is Thinking"

mehdibl — Mon, 03 Nov 2025 19:15:51 +0000

We are still having to read this again in 2025? Some will never get it.

New comment by mehdibl in "Tongyi DeepResearch – open-source 30B MoE Model that rivals OpenAI DeepResearch"

mehdibl — Sun, 02 Nov 2025 15:20:15 +0000

It's a Qwen 3 MoE fine tune...

New comment by mehdibl in "Most expensive laptops"

mehdibl — Tue, 21 Oct 2025 15:19:15 +0000

The funny part the 5090 mobile is more like a 5080 desktop edition!

See the Alienware laptop flagged as 5090 while it's ‎"GeForce RTX 5090 24 GB GDDR7" as laptops can't sustain the TDP and RTX XX90 full power. For AI an external GPU is less costly option.