Viewing profile — SgtBastard
SgtBastard
HN member- Joined
- Thu, Nov 07, 2019, 11:49 PM UTC
- HN karma
- 276
- Public activity
- 213 items
- HN profile
- View on Hacker News ↗
About SgtBastard
No profile information was provided.
Recent public activity
-
comment
Comment #49265522
> A lot of people seem to think of the training process as curve-fitting data (the "stochastic parrot" model), but I think of it more as "solving an inverse problem to approximate …
-
comment
Comment #48853504
You may be discounting the tokens generated in the thinking trace but not included in the output to users.
-
comment
Comment #48798666
The “problem” is exactly as you’ve framed it: individual 1-1 tutoring unambiguously improves education outcomes by a significant (2 StDev’s in Blooms study) vs any other understood…
-
comment
Comment #48798504
Thank you for this and for parent’s comment - I know what rabbit hole I’m going down today.
-
comment
Comment #48514013
Mistral in the EU, for one.
-
comment
Comment #47887450
Mistral (a French company) shouldn’t be discounted.
-
comment
Comment #47508827
What makes you think 1-2, 6-8 can’t be done by agents?
-
comment
Comment #47463368
Yes - itself.
-
comment
Comment #47238756
Friend, I bet those folks living rural West Virginia are super happy that, on average, a group whose only shared characteristics is the colour of their skin are enjoying an elevate…
-
comment
Comment #47114604
How do you feel about your current levels of dakka?
-
comment
Comment #47098488
Are you ok there? SAML, OIDC and a depressingly long tail of Kerberos is how modern enterprise identity security works.
-
comment
Comment #46890704
We have multiple threads of research demonstrating in-context learning, friend. https://github.com/dqxiu/ICL_PaperList
-
comment
Comment #46890657
This thread is about coding agents , of which a model is only one (important) part.
-
comment
Comment #46877665
Fancy while() loops is how I describe them.
-
comment
Comment #46877311
Claude, with a modicum of guidance from an engineer familiar with your monolith, could could write comprehensive unit tests of your existing system, then refactor it into coherent …
-
comment
Comment #46851727
Only if you’re relying upon the models to recall facts from its training set - intuitively, at sufficient complexity, models ability to reason is what is critical and can have its …
-
comment
Comment #46815502
Guilds of Knowledge hoarders and AI adepts are my bet as well.
-
comment
Comment #46504566
Thank you, I learnt a new term today.
-
comment
Comment #46450944
… the internet was not immediately useful in a million different ways for almost every person. Even if you skip ARPAnet, you’re forgetting the Gopher days and even if you jump stra…
-
comment
Comment #45295828
Nitpick: Language is technology, it’s not something we’re genetically born with and is critical for education to happen.
-
comment
Comment #45069866
Technically you are correct but the commenter you’re responding to means that with the amount of Western Governments spend on MS products and services, the are a d facto (if not de…
-
comment
Comment #42287773
Only if you profoundly misunderstand what GC is.
-
comment
Comment #42253753
Ping Identity run the largest enterprise identity platforms on the planet after merging with ForgeRock last year. Think HSBC, JP Morgan Chase-scale.
-
comment
Comment #41212961
>Humas learn dynamically In-context learning (Few Shot Prompting) is absolutely demonstrable by LLMs since GPT 3.5 at least.
-
comment
Comment #41152197
> In most rent controlled systems there is a per sqm pre-allowed rent. Those markets are frequently characterised by poorly maintained rental stock. >Don’t you have a moral obligat…