Hacker News: elyase

New comment by elyase in "Deno Is Joining Cloudflare"

elyase — Fri, 09 Oct 2026 16:59:38 +0000

check rivet and terse

https://github.com/elyase/awesome-object-storage-native#stat...

New comment by elyase in "Deno Is Joining Cloudflare"

elyase — Fri, 09 Oct 2026 16:58:32 +0000

There is rivet and terse

https://github.com/elyase/awesome-object-storage-native#stat...

New comment by elyase in "Pi – A minimal terminal coding harness"

elyase — Wed, 25 Feb 2026 00:22:15 +0000

there is also pz a drop-in replacement for pi rewritten in Zig. 1.7MB static binary, 3ms startup, 1.4MB RAM idle. Find more at:

https://github.com/elyase/awesome-personal-ai-assistants?tab...

New comment by elyase in "Coding with LLMs in the summer of 2025 – an update"

elyase — Mon, 21 Jul 2025 07:55:29 +0000

https://github.com/sst/opencode

New comment by elyase in "Tools: Code Is All You Need"

elyase — Thu, 03 Jul 2025 14:01:19 +0000

This is similar to the tool call (fixed code & dynamic params) vs code generation (dynamic code & dynamic params) discussion: tools offer contrains and save tokens, code gives you flexibility. Some papers suggest that generating code is often superior and this will likely become even more true as language models improve

[1] https://huggingface.co/papers/2402.01030

[2] https://huggingface.co/papers/2401.00812

[3] https://huggingface.co/papers/2411.01747

I am working on a model that goes a step beyond and even makes the distinction between thinking and code execution unnecessary (it is all computation in the end), unfortunately no link to share yet

New comment by elyase in "Is gravity just entropy rising? Long-shot idea gets another look"

elyase — Mon, 16 Jun 2025 15:49:46 +0000

Between two models the one with the shorter Minimum Description Length (MDL) will more likely generalize better

New comment by elyase in "A Research Preview of Codex"

elyase — Sat, 17 May 2025 13:33:33 +0000

What you're missing is how to use the tools properly. With solid documentation, good project management practices, a well-organized code structure and tests, any junior engineer should be able to read up on your codebase, write linted code following your codebase style, verify it via tests and write you a report of what was done, challenges faced etc. State of the art coding agents will do that at superhuman speeds.

If you haven't set things up properly (important info lives only in people’s heads / meetings, tasks dont have clear acceptance criteria, ...) then you aren't ready for Junior Developers yet. You need to wait until your Coding Agents are at Senior level.

New comment by elyase in "Launch HN: Browser Use (YC W25) – open-source web agents"

elyase — Wed, 26 Feb 2025 01:56:58 +0000

I want to use browser-use in Cursor but I am using another option because it doesn't support MCP integration which is the common language they support for external tools

New comment by elyase in "GPT-4o with scheduled tasks (jawbone) is available in beta"

elyase — Tue, 14 Jan 2025 23:19:39 +0000

There is more information in these twitter threads:

https://x.com/karinanguyen_/status/1879270529066262733 https://x.com/OpenAI/status/1879267276291203329

New comment by elyase in "Show HN: Tonic Validate Metrics – an open-source RAG evaluation metrics package"

elyase — Wed, 25 Oct 2023 16:21:20 +0000

How does it compare to https://github.com/explodinggradients/ragas

GPT3 demos

elyase — Wed, 22 Jul 2020 12:03:05 +0000

Article URL: https://github.com/elyase/awesome-gpt3

Comments URL: https://news.ycombinator.com/item?id=23916056

Points: 3

# Comments: 0

New comment by elyase in "Flair: A simple framework for natural language processing"

elyase — Wed, 02 Jan 2019 12:30:36 +0000

The closest alternatives in this space would be allennlp [1], the recently released pytext [2] and spacy [3]. pytext's authors wrote some comparison on the accompanying paper [4] and this GitHub issue [5].

[1] https://github.com/allenai/allennlp

[2] https://github.com/facebookresearch/pytext

[3] https://spacy.io

[4] https://arxiv.org/pdf/1812.08729.pdf

[5] https://github.com/facebookresearch/pytext/issues/110

New comment by elyase in "What Kagglers Are Using for Text Classification"

elyase — Thu, 27 Dec 2018 17:40:30 +0000

We have done extensive testing in the context of chatbot intent classification and in our particular problem nothing (including CNN, LSTM, fasttext plus LUIS, Watson and other proprietary classifiers) has been able to beat a simple linear model trained on char n-gram features.

New comment by elyase in "Show HN: TabNine, an autocompleter for all languages"

elyase — Tue, 06 Nov 2018 21:42:06 +0000

Take a look here for some solutions:

https://www.openmined.org

New comment by elyase in "NLP's ImageNet Moment: From Shallow to Deep Pre-Training"

elyase — Tue, 10 Jul 2018 00:11:06 +0000

fast.ai is great and I also want to love it but I find the coding style extremely unconventional and uninviting to the point that I only use the library when there is really no better alternative (ex for the lr finding features). Variable naming and wildcard imports would be my main complains. But thanks a lot Jeremy for the course and for posting the style guide.

New comment by elyase in "Show HN: Hooks Data API – Realtime Data about Thousands of Topics Over Webhooks"

elyase — Tue, 09 Jan 2018 20:56:37 +0000

Cool project. Are you also going to allow access to the historical data?

New comment by elyase in "Parallel Python"

elyase — Tue, 14 Mar 2017 17:49:06 +0000

Dask would be an option.

New comment by elyase in "Facebook releases 300-dimensional pretrained Fasttext vectors for 90 languages"

elyase — Thu, 02 Mar 2017 11:41:31 +0000

We evaluated using ConceptNet Numberbatch but in the end went with fasttext because of the treatment of OOV words using sub word information. This is important for us because we work with Social Media where misspellings are very frequent and we have found this helps a lot. Are you also looking into these sort of enhancements? How do you usually deal with OOV words?

Deep text-pair classification with Quora's 2017 question dataset

elyase — Mon, 13 Feb 2017 20:56:45 +0000

Article URL: https://explosion.ai/blog/quora-deep-text-pair-classification

Comments URL: https://news.ycombinator.com/item?id=13638687

Points: 5

# Comments: 0

New comment by elyase in "How to use Deep Learning when you have Limited Data"

elyase — Fri, 03 Feb 2017 00:14:04 +0000

It can be argued that some algorithms like Random Forests don't impose a generalization penalty as you increase the number of parameters (forests).