Hacker News: pama

New comment by pama in "Ask HN: Who is using OpenClaw?"

pama — Thu, 16 Apr 2026 03:22:27 +0000

All of the ones I mentioned work great for me. You can dream up your interface and inject technical design ideas and your claw can code it up; as you test it, you fix it if you get new ideas for how it should work.)

For example my recipe project is built around a relatively simple sqlite db. Input for new recipe is in arbitrary format as it goes to an agent (image snapshot on iphone; txt file, speaking it out in a telegram message; a text prompt); the model figures out what to extract and save from the projects’ documents and the context of the specific telegram thread. Output is in whatever form I ask for; rescaled for a number of people; fit in single compact paragraph; or detailed ingredients first then instructions; possibly replace missing ingredients. Query can be arbitrary complex—it almost always finds the recipe I want so far much to my surprise; once I had to followup to select a specific option from a couple ambiguous variants. By default, I like to keep the replies for my recipe queries brief, practical, projected to my cookware. Once I set up this very simple recipe project and imported a couple old datasets, I gave up all of multiple previous recipe schemes (text files or org notes with complex syncing schemes, iPhone apps…)

New comment by pama in "Ask HN: Who is using OpenClaw?"

pama — Wed, 15 Apr 2026 22:06:51 +0000

I use it a lot for personal stuff. Off the top of my head: Best way so far to build and use personalized/family tools for dining/recipe/movie/literature/reminder/organizer/security/notes—-in addition to robust text input, all of them have a voice and image UI via telegram without extra code via an intermediate LLM agent, and all data end up on your machine in your format of choice. More fun than codex/claude-code for hobby coding projects (though worse performance, more effort, unless you directly use codex acp). Less intrusive than ChatGPT/Claude for parallel queries while outdoors (speak, then read). Fun way to explore and understand multi-agent setups. A great way to demo the ability of current AI to friends and family.

You dont have to enable scary setups to make it minimally useful. The jump in capability compared to chatbots is dramatic, and the jump in flexibility compared to coding harnesses is also dramatic.

New comment by pama in "All elementary functions from a single binary operator"

pama — Mon, 13 Apr 2026 21:39:25 +0000

It would be fun to catalogue all one-variable functions that can be represented as binary trees of fixed depth in this way and then encode the trees in binary. Lots of these functions in old math book tables would look very different with a plain hash lookup and the identities in such books would prove themselves.

New comment by pama in "All elementary functions from a single binary operator"

pama — Mon, 13 Apr 2026 20:57:28 +0000

Totally gives nerd sniping vibes:

https://xkcd.com/356/

New codex rate card

pama — Tue, 07 Apr 2026 14:24:27 +0000

Article URL: https://help.openai.com/en/articles/20001106-codex-rate-card#codex-rate-card-token-based-pricing

Comments URL: https://news.ycombinator.com/item?id=47675891

Points: 1

# Comments: 0

New comment by pama in "Google releases Gemma 4 open models"

pama — Thu, 02 Apr 2026 19:57:58 +0000

How is the sglang performance on Blackwell for this model?

New comment by pama in "Claude wrote a full FreeBSD remote kernel RCE with root shell"

pama — Wed, 01 Apr 2026 14:52:45 +0000

It is by the individual who (also with Claude) found the specific vulnerability used in this exploit.

New comment by pama in "Ollama is now powered by MLX on Apple Silicon in preview"

pama — Tue, 31 Mar 2026 12:13:10 +0000

Parallel inference on large compute scales in superlinear ways. There is no way to beat the reduction in memory transfers that a data-center inference model provides with hardware that fits at anything called a home. It is much more energy efficient to process huge batches of parallel requests compared to having one or a handful of queries running on an accelerator.

New comment by pama in "OpenClaw is a security nightmare dressed up as a daydream"

pama — Sun, 22 Mar 2026 20:51:00 +0000

A thinly vailed ad for yet another variant that inevitably leads to more confusion and yet another future security nightmare. The authors (should) know better. No, the purpose of OpenClaw is not to immediately give it all your private accounts and live in bliss and no, their system is not better long term than following the mainline developments that have enough eyes (and bots) on them by now.

New comment by pama in "Yann LeCun raises $1B to build AI that understands the physical world"

pama — Tue, 10 Mar 2026 12:35:48 +0000

You underestimate academia. Any academic that reads these two sentences only focuses on the first one: He has a named chair at Courant. In Germany, being a a Prof is added to your ID card/passport and becomes part of your official name, like knighthood in other countries.

New comment by pama in "Agent Skills Marketplace"

pama — Tue, 03 Mar 2026 13:17:45 +0000

This is a useful concept that helps discovery, with a neat and functional website aesthetic. I hope the skill sharing space will eventually become usable and safe.

Agent Skills Marketplace

pama — Tue, 03 Mar 2026 13:09:30 +0000

Article URL: https://skillsmp.com/

Comments URL: https://news.ycombinator.com/item?id=47231764

Points: 1

# Comments: 1

New comment by pama in "Anthropic Cowork feature creates 10GB VM bundle on macOS without warning"

pama — Mon, 02 Mar 2026 16:19:18 +0000

Aren't most these people recommending random tools in the github chat for this entry just attempting to exploit naive users? Why would anyone in this day and age follow advice of new users to download new repos or click at random websites when they already attempt to use claude code or cowork?

New comment by pama in "U.S. science agency moves to restrict foreign scientists from its labs"

pama — Mon, 02 Mar 2026 13:27:05 +0000

Who benefited from all the years Elon Musk studied in the US and built his early companies? Certainly not south Africa.

New comment by pama in "Mac mini will be made at a new facility in Houston"

pama — Tue, 24 Feb 2026 22:06:08 +0000

Mac minis are sold out in NYC these days because everyone gets them to try out openclaw. Even if this move by Apple is unrelated to the recent demand, it certainly was timed right for the policy and market makers.

Unified Latents (UL): How to train your latents

pama — Mon, 23 Feb 2026 13:01:58 +0000

Article URL: https://arxiv.org/abs/2602.17270

Comments URL: https://news.ycombinator.com/item?id=47121767

Points: 2

# Comments: 0

New comment by pama in "Claude Sonnet 4.6"

pama — Wed, 18 Feb 2026 01:27:27 +0000

TBH I would first walk there to check that they can take me on the spot, and if so, ask them to either please come clean it (only 50m away) or if they cannot fly it there. So walk seems very rational to me.

New comment by pama in "GLM-5: Targeting complex systems engineering and long-horizon agentic tasks"

pama — Thu, 12 Feb 2026 13:33:54 +0000

Cheap verifying of speculative decoding only works for a few tokens at a time. Long sequence generations (thousands to tens of thousands of tokens in typical rollouts for thinking models) are dominated by distribution drift on stale weights (because slightly wrong probabilities multiply over long streams), and the off policy RL training methods dont work well (high variance) for such high dimensional problems.

New comment by pama in "GLM-5: Targeting complex systems engineering and long-horizon agentic tasks"

pama — Thu, 12 Feb 2026 13:02:00 +0000

Not OP. Personal opinion on why it is a somewhat hard problem. The main problem is using the available compute correctly and productively while doing two very separate types of tasks that were previously solved independently: generating responses with llm inference engines and modifying weights with a training code. A step of training updates the weights so the inference engines have to adjust theirs, but we talk about 750B parameters and multiple inference servers. Stale weights can be used instead, but only for a tiny bit and the data from them needs special corrections that also involve large compute/memory. Your inference engines better be deterministic (for given pseudoRNG; it clashes with parallelism) or you have a way to correct the probability streams. Ideally inference and training should have same everything at the bit level when they handle the same context, but we dont live in that world yet. And of course, GPUs break. For no great reason, other than the tiny scale of their features making them fragile. And because you scale, you need to handle failures gracefully and efficiently.

New comment by pama in "Frontier AI agents violate ethical constraints 30–50% of time, pressured by KPIs"

pama — Tue, 10 Feb 2026 04:32:21 +0000

Please update the title: A Benchmark for Evaluating Outcome-Driven Constraint Violations in Autonomous AI Agents. The current editorialized title is misleading and based in part of this sentence: “…with 9 of the 12 evaluated models exhibiting misalignment rates between 30% and 50%”