Check sécurité , intégration sur des services où la doc est nul , (comme dans mon dernier projet l’intégration IBKR), ensuite tout les petits trucs où il te prend des plombes pour analyser le bon format d’un payload alors que c’est un truc facile à fix. Mais oui l’intégration
CODE
-
Using Codex Parallel Instances for Task Automation
By
–
there are few ways to go about it but I think the easiest would be to just activate background terminal (experimental) and just ask codex to spin up parallel instances to solve your task/ list of tasks
-
PyTorch’s Signed 64-bit Index Standardization Decision
By
–
Pytorch made the right call standardizing on signed 64 bit indexes. I would probably still be rather pointlessly making case by case decisions to use int32 if it were an option. Some old habits linger.
-
Boris Highlights Compound Engineering Approach with AI Agents
By
–
so fun to see Boris from Claude Code shout out compound engineering by @kieranklaassen and me check out his thread read our overview here: https://
every.to/chain-of-thoug
ht/compound-engineering-how-every-codes-with-agents
… -
Compound Engineering Approach at Every
By
–
This is a great thread @bcherny ! For anyone interest in how we do compound engineering @every here’s a piece I wrote with @kieranklaassen
: -
LoRA Efficiency for Specific AI Tasks and Datasets
By
–
No not the opposite – they just looked at a particular subsets of tasks, datasets, and metrics. There are some things that LoRA is sufficient for.
-
Beyond PDF submission format launched for research
By
–
Thanks to the great work from our managing editor @PaulVicol, we recently launched the beyond PDF submission format, as a first step towards exploring richer formats for presenting research work:https://t.co/wLWAtnPJGH
— Hugo Larochelle (@hugo_larochelle) 2 janvier 2026Thanks to the great work from our managing editor @PaulVicol
, we recently launched the beyond PDF submission format, as a first step towards exploring richer formats for presenting research work: