Viewing profile — _jayhack_
_jayhack_
HN member- Joined
- Sun, Mar 19, 2017, 8:07 AM UTC
- HN karma
- 277
- Public activity
- 69 items
- HN profile
- View on Hacker News ↗
About _jayhack_
Recent public activity
-
comment
Comment #49150979
Only the ones that beat expectations
-
comment
Comment #49123934
formal verifiability e.g. vi Lean
- story
- story
-
comment
Comment #48734092
The content on "priming" (significant pillar of the book) has collapsed as part of the reproducibility crisis in psychology. More here: https://replicationindex.com/2017/02/02/reco…
- story
-
comment
Comment #48385988
Deep Learning is a Black Box and Here's Why You Should Use Random Forests Because They Are Interpretable This was the mantra of applied machine learning c. 2010 - 2024 for anyone p…
-
comment
Comment #48379406
For some definitions of better, yes. Chinese is more token efficient for representing fixed text, for example, although this does not always lead to better performance on downstrea…
-
comment
Comment #48379396
As the author - this was adapted from a thread posted on X in March (linked in article). AI did the adaptation, I wrote the original article. It seems like it inserted grammaticall…
-
comment
Comment #48379390
Hello, I am the author - this is not an LLM-generated article, I wrote this by hand and had an LLM adapt it from a thread on X. You can see the original thread here: https://x.com/…
- story
- story
-
comment
Comment #47663754
Would love to understand how you compare to other providers like Modal, Daytona, Blaxel, E2B and Vercel. I think most other agent builders will have the same question. Can you prov…
-
comment
Comment #46457455
Great article. For another fantastic explainer on optics, see 3Blue1Brown's video on refraction: https://www.youtube.com/watch?v=KTzGBJPuJwM
-
comment
Comment #45816426
> static analysis tools that produce flowcharts and diagrams like this have existed since antiquity, and I'm not seeing any new real innovation other than "letting the LLM produce …
-
comment
Comment #45553926
Vector embedding is not an invention of the last decade. Featurization in ML goes back to the 60s - even deep learning-based featurization is decades old at a minimum. Like everyth…
-
comment
Comment #45391617
Gary Marcus has been taking victory laps on this since mid-2023, nothing to see here. Patently obvious to all that there will be additional innovations on top of LLMs such as test-…
-
comment
Comment #44533612
Very cool and interesting project. Ideas like this are a threat to traditionally-conceived project management platforms like Linear; that being said, Linear and others (Monday, Cli…
-
comment
Comment #44524595
This does not take into account the fact that experienced developers working with AI have shifted into roles of management and triage, working on several tasks simultaneously. Woul…
-
comment
Comment #44102422
It looks like you used AI-generated videos for customer testimonials. This should be illegal
-
comment
Comment #44006622
[flagged]
-
comment
Comment #43979926
Also worth checking out MultiLSPy, effectively a python wrapper around multiple LSPs: https://github.com/microsoft/multilspy Used in multiple similar publications, including "Guidi…
-
story
Show HN: Codegen – SWE Agents for any repo
Hey folks, excited to launch Codegen: a platform for SWE agents. Codegen lets you prompt agents to perform programming tasks across code, Github, Linear, Slack and more. Ask for im…
-
comment
Comment #43693956
If you are looking for an alternative that can also chat with you in Slack, create PRs, edit/create/search tickets and Linear, search the web and more, check out codegen.com
-
comment
Comment #43649229
Related article from mid-pandemic: https://www.theinformation.com/articles/shaky-tech-and-cash-... A friend asked me to do diligence on this company circa 2021 given my personal ba…