Joe Palermo
@joepalerm0
Followers
1K
Following
638
Media
2
Statuses
85
Machine learning engineer from Toronto; Member of Technical Staff @OpenAI
Joined December 2013
Reinforcement finetuning is just one of several strategies we're pursuing to make AI more useful in industry.
If AGI is about AI transforming our economy—how close are we, really? What's still missing, and how do we get there? OpenAI's new Strategic Deployment team tackles exactly these questions. We push frontier models to be more capable, reliable, and aligned—then deploy them to
0
0
10
We’ve been hard at work on reinforcement fine-tuning (RFT) to make it a more flexible and powerful tool. RFT is best thought of as a way to improve model capabilities on well-specified tasks with known correct answers. It shouldn't come as a surprise that models can often get
We worked with the @OpenAI team to test and evaluate fine-tuned reasoning models in SafetyKit and saw great results, especially with complex instruction following and large context windows. SafetyKit customers need lots of expert-level decision-making across lots of complex
2
12
59
"The models just want to learn" -Ilya Sutskever
Joe Palermo (@joepalerm0 - research engineer @OpenAI) talking about "Customizing GPT-4" at our inaugural AGI House hackathon @ MIT
4
4
32
David Deutsch: "We have a duty to be optimistic. Because the future is open, not predetermined and therefore cannot just be accepted: we are all responsible for what it holds. Thus it is our duty to fight for a better world."
43
156
819
Computers are great for reversing local entropy. For a start what I want is: 1) A robot to follow me around and cleanup my messes, 2) A brain-computer interface to remember all the things I forget, 3) Nanobots in my body to repair cellular damage.
2
1
17
The overwhelming feeling is of love for each other, commitment to our mission and the absolutely indomitable will of the OpenAI team.
3
3
44
Interested in designing and building lightning infrastructure for the next billion lightning users? 👇 https://t.co/y7n809e4sM
To that end, I’ve been very lucky to connect with a lot of great Lightning-minded folks on Twitter. We’ll be posting jobs for this initiative in the near future. If you’re an engineer who has been looking to get into Lightning professionally this could be a great opportunity.
1
4
10
Open state databases are the next step after open source software. They are databases anyone can read from (for free) or write to (for a price), with incentives and algorithms set up to prevent corruption. You might also call them distributed ledgers :)
Blockchains are the next step after open source, as they provide open data & open execution. You don’t just see the source code with something like Bitcoin or Ethereum. With a full node you see all historical data, all pending writes, and can retrace every step of code execution.
28
187
855
Efficient-VDVAE: Less is more abs: https://t.co/uNtYzgHHAj github: https://t.co/kJNbAKJ0I8 simple modifications to the Very Deep VAE to make it converge up to 2.6× faster, save up to 20× in memory load and improve stability during training
0
29
133
It is obvious that the current angel investing system — Docusigns and Hellosigns, Clerkys and Cartas, contracts and valuations, emails and wires — will all go on-chain. Every aspect is simplified if you can simply send USDC to an ENS address and get digital assets back.
89
225
2K
This extract from @balajis excellently summarises the main reason why I started my science newsletter Those of us on the front lines of science need to educate the public on all the amazing research going on today & if possible inspire the next generation 🙏
6
24
258
Any chance we can move this 🇨🇦 debate for the Fernandez match??
0
0
0
Much work remains to be done but we believe that program synthesis will become increasingly important in the quest to build AI capable of reasoning from limited data.
0
0
2
This work was in part inspired by @fchollet's explanation of the potential value of program synthesis ( https://t.co/rhlNUOvhMe).
joepalermo.github.io
Since his 2019 paper “The Measure of Intelligence”, I’ve been finding Francois Chollet’s line of thinking to be very insightful. This post is my attempt to walk through the ideas from his talk at...
1
0
2
See our repo for a visual depiction of the environment:
github.com
Contribute to JohnnyYeeee/math_prog_synth_env development by creating an account on GitHub.
1
0
0
Each action taken in the environment adds an operator or an input into a discrete compute graph. Graphs which compute correct answers yield positive reward, enabling the optimization of a policy to construct compute graphs conditioned on problem statements.
1
0
0